April 23-27, 2026 Rio de Janeiro, Brazil
| 10006400-P | Teaching LLMs to Admit Uncertainty in OCR | Shuhao Guan | |
| 10006402-P | Clustering by Denoising: Latent plug-and-play diffusion for single-cell embeddings | Dominik Meier | |
| 10006422-P | Explain in Your Own Words: Improving Reasoning via Token-Selective Dual Knowledge Distillation | Minsang Kim | |
| 10006432-P | FieryGS: In-the-Wild Fire Synthesis with Physics-Integrated Gaussian Splatting | Ningxiao Tao | |
| 10006443-P | Accelerated Learning with Linear Temporal Logic using Differentiable Simulation | Alper Kamil Bozkurt | |
| 10006448-P | Does the Data Processing Inequality Reflect Practice? On the Utility of Low-Level Tasks | Roy Turgeman | |
| 10006451-P | Generalization Below the Edge of Stability: The Role of Data Geometry | Tongtong Liang | |
| 10006453-P | Symmetry-Aware Bayesian Optimization via Max Kernels | Anthony Bardou | |
| 10006454-P | On the Interaction of Compressibility and Adversarial Robustness | Melih Barsbey | |
| 10006455-P | Predictive Differential Training Guided by Training Dynamics | Weisheng Tang | |
| 10006463-P | G-reasoner: Foundation Models for Unified Reasoning over Graph-structured Knowledge | Linhao Luo | |
| 10006469-P | OmniText: A Training-Free Generalist for Controllable Text-Image Manipulation | Samuel Teodoro | |
| 10006483-P | Dynamic Classifier-Free Diffusion Guidance via Online Feedback | Pinelopi Papalampidi | |
| 10006487-P | S2GO: Streaming Sparse Gaussian Occupancy | Jinhyung Park | |
| 10006491-P | Seq vs Seq: An Open Suite of Paired Encoders and Decoders | Orion Weller | |
| 10006498-P | Entropy-Guided Dynamic Tokens for Graph-LLM Alignment in Molecular Understanding | Zihao Jing | |
| 10006505-P | Sharp Monocular View Synthesis in Less Than a Second | Wei Dong | |
| 10006510-P | CTC-DRO: Robust Optimization for Reducing Language Disparities in Speech Recognition | Martijn Bartelds | |
| 10006520-P | Deep Hierarchical Learning with Nested Subspace Networks for Large Language Models | Paulius Rauba | |
| 10006521-P | AutoMetrics: Approximate Human Judgments with Automatically Generated Evaluators | Michael Ryan | |
| 10006525-P | Incorporating Expert Priors into Bayesian Optimization via Dynamic Mean Decay | Chongqi Qu | |
| 10006536-P | FaSTA*: Fast-Slow Toolpath Agent with Subroutine Mining for Efficient Multi-turn Image Editing | Advait Gupta | |
| 10006553-P | The Polar Express: Optimal Matrix Sign Methods and their Application to the Muon Algorithm | David Persson | |
| 10006587-P | Hot PATE: Private Aggregation of Distributions for Diverse Tasks | Edith Cohen | |
| 10006589-P | InfoBridge: Mutual Information estimation via Bridge Matching | Sergei Kholkin | |
| 10006592-P | Improving LLM-based Global Optimization with Search Space Partitioning | Arber Zela | |
| 10006605-P | Programming by Backprop: Learning Behaviour from Symbolic Descriptions | Jonathan Cook | |
| 10006612-P | Kevin: Multi-Turn RL for Generating CUDA Kernels | Carlo Baronio | |
| 10006616-P | Revisiting [CLS] and Patch Token Interaction in Vision Transformers | Alexis Marouani | |
| 10006621-P | Contact-guided Real2Sim from Monocular Video with Planar Scene Primitives | Zihan Wang | |
| 10006633-P | MesaNet: Sequence Modeling by Locally Optimal Test-Time Training | Nino Scherrer | |
| 10006636-P | ContextBench: Modifying Contexts for Targeted Latent Activation and Behaviour Elicitation | Edward Stevinson | |
| 10006640-P | Reusing Pre-Training Data at Test Time is a Compute Multiplier | Alex Fang | |
| 10006647-P | LEXam: Benchmarking Legal Reasoning on 340 Law Exams | Yu Fan | |
| 10006648-P | Quantized Gradient Projection for Memory-Efficient Continual Learning | Dongun Kim | |
| 10006651-P | Echo: Towards Advanced Audio Comprehension via Audio-Interleaved Reasoning | Daiqing Wu | |
| 10006652-P | Traceable Black-Box Watermarks For Federated Learning | Olivera Kotevska | |
| 10006654-P | Redirection for Erasing Memory (REM): Towards a universal unlearning method for corrupted data | Stefan Schoepf | |
| 10006662-P | CauKer: Classification Time Series Foundation Models Can Be Pretrained on Synthetic Data | Ievgen Redko | |
| 10006678-P | Scaling Laws Revisited: Modeling the Role of Data Quality in Language Model Pretraining | Yuxin Chen | |
| 10006681-P | SIGMA-GEN: STRUCTURE AND IDENTITY GUIDED MULTI-SUBJECT ASSEMBLY FOR IMAGE GENERATION | Oindrila Saha | |
| 10006682-P | SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training | Jianyi Wang | |
| 10006684-P | Beyond Noisy-TVs: Noise-Robust Exploration Via Learning Progress Monitoring | Zhibo Hou | |
| 10006692-P | Causally Robust Reward Learning from Reason-Augmented Preference Feedback | Minjune Hwang | |
| 10006694-P | Gradient Descent with Large Step Sizes: Chaos and Fractal Convergence Region | Shuang Liang | |
| 10006704-P | Direct Preference Optimization for Primitive-Enabled Hierarchical RL: A Bilevel Approach | Utsav Singh | |
| 10006718-P | Noise-Aware Generalization: Robustness to In-Domain Noise and Out-of-Domain Generalization | Bryan Plummer | |
| 10006726-P | LLM Pretraining with Continuous Concepts | Jihoon Tack | |
| 10006735-P | Repurposing Foundation Model for Generalizable Medical Time Series Classification | Nan Huang | |
| 10006738-P | ReTrace: Reinforcement Learning-Guided Reconstruction Attacks on Machine Unlearning | Mengyao Ma | |
| 10006756-P | ConvT3: Structured State Kernels for Convolutional State Space Models | Jaeyoung Hong | |
| 10006762-P | Knowledgeable Language Models as Black-Box Optimizers for Personalized Medicine | Claudia Iriondo | |
| 10006764-P | Leveraging Pretrained Knowledge at Inference Time: LoRA-Gated Contrastive Decoding for Multilingual Factual Language Generation in Adapted LLMs | Gwangseon Jang | |
| 10006777-P | Boosting Open Set Recognition Performance through Modulated Representation Learning | Amit Kumar Kundu | |
| 10006779-P | Weak Correlations as the Underlying Principle for Linearization of Gradient-Based Learning Systems | Ori Shem-Ur | |
| 10006793-P | Eliciting Harmful Capabilities by Fine-Tuning on Safeguarded Outputs | Jack Kaunismaa | |
| 10006794-P | Trust The Typical | Debargha Ganguly | |
| 10006800-P | Q-Learning with Adjoint Matching | Qiyang Li | |
| 10006804-P | I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data? | Yuhang Liu | |
| 10006816-P | LightRetriever: A LLM-based Text Retrieval Architecture with Extremely Faster Query Inference | Guangyuan Ma | |
| 10006822-P | Dual Optimistic Ascent (PI Control) is the Augmented Lagrangian Method in Disguise | Juan Ramirez | |
| 10006824-P | GLASS Flows: Efficient Inference for Reward Alignment of Flow and Diffusion Models | Peter Holderrieth | |
| 10006831-P | Escaping Policy Contraction: Contraction-Aware PPO (CaPPO) for Stable Language Model Fine-Tuning | Dun Yuan | |
| 10006833-P | Reevaluating Policy Gradient Methods for Imperfect-Information Games | Max Rudolph | |
| 10006836-P | Multi-Head Low-Rank Attention | Songtao Liu | |
| 10006840-P | Hedonic Neurons: A Mechanistic Mapping of Latent Coalitions in Transformer MLPs | James Allan | |
| 10006843-P | HARDTESTGEN: A High-Quality RL Verifier Generation Pipeline for LLM Algorithmic Coding | Zhongmou He | |
| 10006852-P | Lossy Common Information in a Learnable Gray-Wyner Network | Anderson de Andrade | |
| 10006865-P | Equivariant Splitting: Self-supervised learning from incomplete data | Victor Sechaud | |
| 10006871-P | REAP the Experts: Why Pruning Prevails for One-Shot MoE Compression | Mike Lasby | |
| 10006875-P | Understanding Collaboration Mechanism In VAE Recommender Systems | Vu Nguyen | |
| 10006880-P | FS-DFM: Fast and Accurate Long Text Generation with Few-Step Diffusion Language Models | Dominic Culver | |
| 10006897-P | FrugalRAG: Less is More in RL Finetuning for Multi-hop Question Answering | Abhinav Java | |
| 10006903-P | Action-Guided Attention for Video Action Anticipation | Werner Nutt | |
| 10006907-P | Can Large Language Models Match the Conclusions of Systematic Reviews? | Christopher Polzak | |
| 10006910-P | Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control | Zeqian Long | |
| 10006914-P | Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models | Tianyu Lu | |
| 10006916-P | Weight Space Representation Learning on Diverse NeRF Architectures | Francesco Ballerini | |
| 10006917-P | PluriHarms: Benchmarking the Full Spectrum of Human Judgments on AI Harm | Jing-Jing Li | |
| 10006919-P | Thompson Sampling via Fine-Tuning of LLMs | Nicolas Menet | |
| 10006921-P | The Seismic Wavefield Common Task Framework | Alexey Yermakov | |
| 10006930-P | Durian: Dual Reference Image-Guided Portrait Animation with Attribute Transfer | Hyunsoo Cha | |
| 10006937-P | Learning is Forgetting; LLM Training As Lossy Compression | Henry Conklin | |
| 10006939-P | Resurfacing the Instance-only Dependent Label Noise Model through Loss Correction | Mustafa Enes AYDIN | |
| 10006946-P | Flattery, Fluff, and Fog: Diagnosing and Mitigating Idiosyncratic Biases in Preference Models | Anirudh Bharadwaj | |
| 10006956-P | VL-JEPA: Joint Embedding Predictive Architecture for Vision-language | Delong Chen | |
| 10006958-P | Federated Learning with Profile Mapping under Distribution Shifts and Drifts | Dario Fenoglio | |
| 10006959-P | Continuous multinomial logistic regression for neural decoding | Rupasinghe Arachchige Anuththara Rupasinghe | |
| 10006963-P | AVERE: Improving Audiovisual Emotion Reasoning with Preference Optimization | Ashutosh Chaubey | |
| 10006966-P | On the identifiability of causal graphs with multiple environments | Francesco Montagna | |
| 10006968-P | Signal in the Noise: Polysemantic Interference Transfers and Predicts Cross-Model Influence | Shiyang Lai | |
| 10006970-P | BBQ: Boosting Quantization Entropy with Bell Box Quantization | Ningfeng Yang | |
| 10006977-P | Moving Beyond Medical Exams: A Clinician-Annotated Fairness Dataset of Real-World Tasks and Ambiguity in Mental Healthcare | Max Lamparth | |
| 10006981-P | RoboCasa365: A Large-Scale Simulation Framework for Training and Benchmarking Generalist Robots | Abhiram Maddukuri | |
| 10006985-P | TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate | Majid Hadian | |
| 10006990-P | Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation | Xuanchi Ren | |
| 10006992-P | Spectral Bellman Method: Unifying Representation and Exploration in RL | Ofir Nabati | |
| 10007007-P | Vintix II: Decision Pre-Trained Transformer is a Scalable In-Context Reinforcement Learner | Andrei Polubarov | |
| 10007015-P | SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs | Dachuan Shi | |
| 10007027-P | Generalized Parallel Scaling with Interdependent Generations | Harry Dong | |
| 10007028-P | STaMP: Sequence Transformation and Mixed Precision for Low-Precision Activation Quantization | Marco Federici | |
| 10007030-P | THE SELF-RE-WATERMARKING TRAP: FROM EXPLOIT TO RESILIENCE | Vithurabiman Senthuran | |
| 10007040-P | Logit-KL Flow Matching: Non-Autoregressive Text Generation via Sampling-Hybrid Inference | Egor Sevriugov | |
| 10007044-P | Heterogeneous Federated Fine-Tuning with Parallel One-Rank Adaptation | Zikai Zhang | |
| 10007045-P | Attention Smoothing Is All You Need For Unlearning | Dongxiao Zhu | |
| 10007047-P | Spilling the Beans: Teaching LLMs to Self-Report Their Hidden Objectives | Daniel Chee Hian Tan | |
| 10007052-P | Composition of Memory Experts for Diffusion World Models | Sebastian Stapf | |
| 10007058-P | Pay Attention to CTC: Fast and Robust Pseudo-Labelling for Unified Speech Recognition | Alexandros Haliassos | |
| 10007063-P | PoLi-RL: A Point-to-List Reinforcement Learning Framework for Conditional Semantic Textual Similarity | Qian-Wen Zhang | |
| 10007064-P | Explaining Grokking and Information Bottleneck through Neural Collapse Emergence | Keitaro Sakamoto | |
| 10007067-P | Physically Valid Biomolecular Interaction Modeling with Gauss-Seidel Projection | Siyuan Chen | |
| 10007068-P | Efficient Morphology–Control Co-Design via Stackelberg PPO under Non-Differentiable Leader–Follower Interfaces | Yuhui Wang | |
| 10007081-P | What´s In My Human Feedback? Learning Interpretable Descriptions of Preference Data | Rajiv Movva | |
| 10007083-P | DRIFT: Learning from Abundant User Dissatisfaction in Real-World Preference Learning | Yifan Wang | |
| 10007085-P | ProofFlow: A Dependency Graph Approach to Faithful Proof Autoformalization | Rafael Cabral | |
| 10007105-P | Omni-iEEG: A Large-Scale, Comprehensive iEEG Dataset and Benchmark for Epilepsy Research | Chenda Duan | |
| 10007107-P | SFT Doesn´t Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMs | Zhongruo Wang | |
| 10007118-P | A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image Features | Axel Barroso-Laguna | |
| 10007119-P | $PhyWorldBench$: A Comprehensive Evaluation of Physical Realism in Text-to-Video Models | Ashwin Nagarajan | |
| 10007121-P | Bi-Lipschitz Autoencoder With Injectivity Guarantee | Qipeng Zhan | |
| 10007122-P | From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning | Chen Shani | |
| 10007132-P | HUME: Measuring the Human-Model Performance Gap in Text Embedding Tasks | Roman Solomatin | |
| 10007133-P | OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use Agents | Hongrui Jia | |
| 10007143-P | Displacement-Resistant Extensions of DPO with Nonconvex $f$-Divergences | Idan Pipano | |
| 10007155-P | TikZilla: Scaling Text-to-TikZ with High-Quality Data and Reinforcement Learning | Christian Greisinger | |
| 10007166-P | Complexity- and Statistics-Guided Anomaly Detection in Time Series Foundation Models | Jongwon Kim | |
| 10007169-P | Monotone Near-Zero-Sum Games | Ruichen Luo | |
| 10007170-P | ShapeGen4D: Towards High Quality 4D Shape Generation from Videos | Jiraphon Yenphraphai | |
| 10007179-P | Self-Supervised Learning from Structural Invariance | Yipeng Zhang | |
| 10007188-P | Do LLM Agents Know How to Ground, Recover, and Assess? A Benchmark for Epistemic Competence in Information-Seeking Agents | Bing Luo | |
| 10007193-P | BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design | Deepro Choudhury | |
| 10007194-P | Scaling Laws and Symmetry, Evidence from Neural Force Fields | Nhat Khang Ngo | |
| 10007211-P | Scaling Atomistic Protein Binder Design with Generative Pretraining and Test-Time Compute | Danny Reidenbach | |
| 10007214-P | TINY BUT MIGHTY: A SOFTWARE-HARDWARE CO- DESIGN APPROACH FOR EFFICIENT MULTIMODAL IN- FERENCE ON BATTERY-POWERED SMALL DEVICES | Yilong Li | |
| 10007218-P | Unveiling the Potential of Diffusion Large Language Model in Controllable Generation | Zhen Xiong | |
| 10007219-P | SAIR: Enabling Deep Learning for Protein-Ligand Interactions with a Synthetic Structural Dataset | Thomas Merth | |
| 10007228-P | GOLDILOCS: GENERAL OBJECT-LEVEL DETECTION AND LABELING OF CHANGES IN SCENES | Almog Friedlander | |
| 10007238-P | On the Eligibility of LLMs for Counterfactual Reasoning: A Decompositional Study | Shuai Yang | |
| 10007240-P | DRIFT-Net: A Spectral-Coupled Neural Operator for PDEs Learning | Flora Salim | |
| 10007247-P | Closed-form $\ell_r$ norm scaling with data for overparameterized linear regression and diagonal linear networks under $\ell_p$ bias | Shuofeng Zhang | |
| 10007248-P | Transducing Language Models | Vésteinn Snbjarnarson | |
| 10007255-P | MOAI: Module-Optimizing Architecture for Non-Interactive Secure Transformer Inference | Jun Jie Sim | |
| 10007262-P | Mapping Semantic-Syntactic Relationships with Geometric Rotation | Lauren Alvarez | |
| 10007266-P | The Spacetime of Diffusion Models: An Information Geometry Perspective | Rafal Karczewski | |
| 10007271-P | Mapping Post-Training Forgetting in Language Models at Scale | Jackson Harmon | |
| 10007273-P | From Reproduction to Replication: Evaluating Research Agents with Progressive Code Masking | Gyeongwon Kim | |
| 10007285-P | Early Signs of Steganographic Capabilities in Frontier LLMs | Kei Nishimura-Gasparian | |
| 10007289-P | Characterizing and Optimizing the Spatial Kernel of Multi Resolution Hash Encodings | Tianxiang Dai | |
| 10007292-P | DiffusionBlocks: Block-wise Neural Network Training via Diffusion Interpretation | Makoto Shing | |
| 10007295-P | Story-Iter: A Training-free Iterative Paradigm for Long Story Visualization | Xiaoke Huang | |
| 10007301-P | Reasoning-Driven Multimodal LLM for Domain Generalization | Zhipeng Xu | |
| 10007302-P | On Discriminative vs. Generative classifiers: Rethinking MLLMs for Action Understanding | Zhanzhong Pang | |
| 10007309-P | SSDi8: Accurate and Efficient 8-bit Quantization for State Space Duality | Hyunwoo Kim | |
| 10007310-P | Local Reinforcement Learning with Action-Conditioned Root Mean Squared Q-Functions | Zequan Wu | |
| 10007311-P | Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training | Junlin Han | |
| 10007323-P | Can we generate portable representations for clinical time series data using LLMs? | Zongliang Ji | |
| 10007332-P | LLaVAction: evaluating and training multi-modal large language models for action understanding | Haozhe Qi | |
| 10007341-P | Ensembling Pruned Attention Heads For Uncertainty-Aware Efficient Transformers | firas gabetni | |
| 10007344-P | CONSIGN: Conformal Segmentation Informed by Spatial Groupings via Decomposition | Bruno Viti | |
| 10007348-P | Measurement Score-Based Diffusion Model | Chicago Y. Park | |
| 10007354-P | Adaptive Width Neural Networks | Henrik Christiansen | |
| 10007356-P | Source-Guided Flow Matching | Zifan Wang | |
| 10007358-P | Video-KTR: Reinforcing Video Reasoning via Key Token Attribution | ziyue wang | |
| 10007365-P | SimULi: Real-Time LiDAR and Camera Simulation with Unscented Transforms | Haithem Turki | |
| 10007367-P | Si-GT: Fast Interconnect Signal Integrity Analysis for Integrated Circuit Design via Graph Transformers | Yuting Hu | |
| 10007371-P | Culture in Action: Evaluating Text-to-Image Models through Social Activities | Sina Malakouti | |
| 10007388-P | Optimizing Data Augmentation through Bayesian Model Selection | Madi Matymov | |
| 10007395-P | All Patches Matter, More Patches Better: Enhance AI-Generated Image Detection via Panoptic Patch Learning | Chen Ruoxin | |
| 10007403-P | MIRA: Memory-Integrated Reinforcement Learning Agent with Limited LLM Guidance | Narjes Nourzad | |
| 10007406-P | Making, Not Taking, the Best of N | Ammar Khairi | |
| 10007444-P | Searching for Privacy Risks in LLM Agents via Simulation | Yanzhe Zhang | |
| 10007447-P | Online Minimization of Polarization and Disagreement via Low-Rank Matrix Bandits | Federico Cinus | |
| 10007454-P | LogicXGNN: Grounded Logical Rules for Explaining Graph Neural Networks | CHUQIN GENG | |
| 10007469-P | Privacy Beyond Pixels: Latent Anonymization for Privacy-Preserving Video Understanding | Joseph Fioresi | |
| 10007477-P | Constantly Improving Image Models Need Constantly Improving Benchmarks | David Chan | |
| 10007485-P | Toward Enhancing Representation Learning in Federated Multi-Task Settings | Mehdi Setayesh | |
| 10007486-P | BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation via Lens of Dynamic Interactions | Nan HUO | |
| 10007492-P | Beyond Accuracy: Are Time Series Foundation Models Well-Calibrated? | Coen Adler | |
| 10007495-P | VLMgineer: Vision-Language Models as Robotic Toolsmiths | Tianyu Li | |
| 10007497-P | Probabilistic Kernel Function for Fast Angle Testing | Kejing Lu | |
| 10007511-P | On the Impact of the Utility in Semivalue-based Data Valuation | Mélissa Tamine | |
| 10007516-P | Real-Time Reasoning Agents in Evolving Environments | Yanzhe Zhang | |
| 10007519-P | WIMLE: Uncertainty-Aware World Models with IMLE for Sample-Efficient Continuous Control | Mehran Aghabozorgi | |
| 10007525-P | Demystifying Emergent Exploration in Goal-Conditioned RL | Grace Liu | |
| 10007531-P | HSIC Bottleneck for Cross-Generator and Domain-Incremental Synthetic Image Detection | Chin-Chia Yang | |
| 10007538-P | MARL2Grid-TR: A Multi-Agent RL Benchmark in Power Grid Operations | Enrico Marchesini | |
| 10007548-P | Agnostics: Learning to Synthesize Code in Any Programming Language with a Universal Reinforcement Learning Environment | Aleksander Boruch-Gruszecki | |
| 10007556-P | Truthfulness Despite Weak Supervision: Evaluating and Training LLMs Using Peer Prediction | Tianyi Qiu | |
| 10007565-P | ViMo: A Generative Visual GUI World Model for App Agents | Dezhao LUO | |
| 10007587-P | Learning Data-Efficient and Generalizable Neural Operators via Fundamental Physics Knowledge | Siying Ma | |
| 10007597-P | HarmonyGNNs: Harmonizing Heterophily and Homophily in GNNs via Self-Supervised Node Encoding | Rui Xue | |
| 10007611-P | Discount Model Search for Quality Diversity Optimization in High-Dimensional Measure Spaces | Bryon Tjanaka | |
| 10007629-P | Composer: A Search Framework for Hybrid Neural Architecture Design | Bilge Acun | |
| 10007632-P | Towards a Sharp Analysis of Learning Offline $f$-Divergence-Regularized Contextual Bandits | Qingyue Zhao | |
| 10007635-P | Hilbert-Guided Sparse Local Attention | Yunge Li | |
| 10007639-P | In Context Semi-Supervised Learning | Paul Rosu | |
| 10007655-P | Emergence of Spatial Representation in an Actor-Critic Agent with Hippocampus-Inspired Sequence Generator | Xiao-Xiong Lin | |
| 10007666-P | An Improved Model-free Decision-estimation Coefficient with Applications in Adversarial MDPs | Haolin Liu | |
| 10007671-P | Byzantine-Robust Federated Learning with Learnable Aggregation Weights | Amir Daghestani | |
| 10007676-P | Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modeling | Tal Daniel | |
| 10007697-P | Graph Diffusion Transformers are In-Context Molecular Designers | Gang Liu | |
| 10007711-P | Graph-based Nearest Neighbors with Dynamic Updates via Random Walk-Based Analysis | Tal Wagner | |
| 10007713-P | Learn to Guide Your Diffusion Model | Mauricio Delbracio | |
| 10007721-P | FS-KAN: Permutation Equivariant Kolmogorov-Arnold Networks via Function Sharing | Ran Elbaz | |
| 10007727-P | DriftLite: Lightweight Drift Control for Inference-Time Scaling of Diffusion Models | Jiequn Han | |
| 10007730-P | FMIP: Joint Continuous-Integer Flow For Mixed-Integer Linear Programming | Hongpei Li | |
| 10007731-P | Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders | Bo Fang | |
| 10007736-P | Understanding Sensitivity of Differential Attention through the Lens of Adversarial Robustness | Tsubasa Takahashi | |
| 10007743-P | Latent Speech-Text Transformer | Yen-Ju Lu | |
| 10007746-P | Neon: Negative Extrapolation From Self-Training Improves Image Generation | Sina Alemohammad | |
| 10007755-P | No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping | Thanh-Long Le Viet | |
| 10007757-P | DAVE: A VLM Vision Encoder for Document Understanding and Web Agents | Hang Hua | |
| 10007758-P | Breaking Agent Backbones: Evaluating the Security of Backbone LLMs in AI Agents | Julia Bazinska | |
| 10007760-P | When to Ensemble: Identifying Token-Level Points for Stable and Fast LLM Ensembling | Heecheol Yun | |
| 10007761-P | Evaluating Language Models´ Evaluations of Games | Cedegao Zhang | |
| 10007778-P | C-Voting: Confidence-Based Test-Time Voting without Explicit Energy Functions | Kenji Kubo | |
| 10007785-P | Frozen Policy Iteration: Computationally Efficient RL under Linear $Q^{\pi}$ Realizability for Deterministic Dynamics | Yijing Ke | |
| 10007787-P | Unpacking Human Preference for LLMs: Demographically Aware Evaluation with the Diverse Framework | Nora Petrova | |
| 10007791-P | Avey Bidirectional Architecture | Devang Acharya | |
| 10007801-P | BRIDGE: Bi-level Reinforcement Learning for Dynamic Group Structure in Coalition Formation Games | shuqing shi | |
| 10007804-P | Random Controlled Differential Equations | Francesco Piatti | |
| 10007809-P | TGM: A Modular and Efficient Library for Machine Learning on Temporal Graphs | Jacob Chmura | |
| 10007818-P | On the Theoretical Limitations of Embedding-Based Retrieval | Orion Weller | |
| 10007820-P | House of Dextra: Cross-Embodied Co-Design for Dexterous Hands | Kehlani Fay | |
| 10007822-P | Mitigating Mismatch within Reference-based Preference Optimization | Suqin Yuan | |
| 10007828-P | Latent Concept Disentanglement in Transformer-based Language Models | Bhavya Vasudeva | |
| 10007834-P | Any-Subgroup Equivariant Networks via Symmetry Breaking | Ningyuan Huang | |
| 10007848-P | CaTS: Calibrated Test-Time Scaling for Efficient LLM Inference | Chengsong Huang | |
| 10007865-P | BIRD: Behavior Induction via Representation-structure Distillation | Galen Pogoncheff | |
| 10007868-P | BAH Dataset for Ambivalence/Hesitancy Recognition in Videos for Behavioural Change | Masoumeh Sharafi | |
| 10007878-P | GraphUniverse: Synthetic Graph Generation for Evaluating Inductive Generalization | Louis Van Langendonck | |
| 10007881-P | PropensityBench: Evaluating Latent Safety Risks in Large Language Models via an Agentic Approach | Shayan Shabihi | |
| 10007882-P | Dropping Just a Handful of Preferences Can Change Top Large Language Model Rankings | Jenny Huang | |
| 10007887-P | ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory | Jun Yan | |
| 10007902-P | ICYM2I: The illusion of multimodal informativeness under missingness | Young Sang Choi | |
| 10007910-P | Intention-Conditioned Flow Occupancy Models | Chongyi Zheng | |
| 10007919-P | Perception-Aware Policy Optimization for Multimodal Reasoning | Zhenhailong Wang | |
| 10007920-P | Internal Evaluation of Density-Based Clusterings with Noise | Pascal Weber | |
| 10007923-P | Difference Predictive Coding for Training Spiking Neural Networks | Ville Karlsson | |
| 10007930-P | Test-Time Efficient Pretrained Model Portfolios for Time Series Forecasting | Pedro Mercado | |
| 10007934-P | Tab-MIA: A Benchmark Dataset for Membership Inference Attacks on Tabular Data in LLMs | Eyal German | |
| 10007937-P | Automatic Dialectic Jailbreak: A Framework for Generating Effective Jailbreak Strategies | Dejing Dou | |
| 10007942-P | Generative Adversarial Reasoner: Enhancing LLM Reasoning with Adversarial Reinforcement Learning | Qihao Liu | |
| 10007946-P | Attribution-Guided Decoding | Piotr Komorowski | |
| 10007950-P | OSCAR: Online Soft Compression for RAG | Stephane Clinchant | |
| 10007951-P | Improving Black-Box Generative Attacks via Generator Semantic Consistency | Jongoh Jeong | |
| 10007959-P | MAC-AMP: A Closed-Loop Multi-Agent Collaboration System for Multi-Objective Antimicrobial Peptide Design | Sugitha Janarthanan | |
| 10007966-P | HiMAE: Hierarchical Masked Autoencoders Discover Resolution-Specific Structure in Wearable Time Series | Simon Lee | |
| 10007967-P | UniQL: Unified Quantization and Low-rank Compression for Adaptive Edge LLMs | Hung-Yueh Chiang | |
| 10007969-P | SpotIt: Evaluating Text-to-SQL Evaluation with Formal Verification | Haoze Wu | |
| 10007987-P | SimpleToM: Exposing the Gap between Explicit ToM Inference and Implicit ToM Application in LLMs | Ronan Le Bras | |
| 10007989-P | From Cheap Geometry to Expensive Physics: Elevating Neural Operators via Latent Shape Pretraining | Zhizhou Zhang | |
| 10007990-P | On the $O(1/T)$ Convergence of Alternating Gradient Descent–Ascent in Bilinear Games | Shuvomoy Das Gupta | |
| 10007993-P | Disentangling the Factors of Convergence between Brains and Computer Vision Models | Joséphine Raugel | |
| 10008011-P | A Theoretical Analysis of Mamba´s Training Dynamics: Filtering Relevant Features for Generalization in State Space Models | Mugunthan Shandirasegaran | |
| 10008022-P | Reliability-Adjusted Prioritized Experience Replay | Leonard Pleiss | |
| 10008025-P | The False Promise of Zero-Shot Super-Resolution in Machine-Learned Operators | Mansi Sakarvadia | |
| 10008032-P | CHROMA: Consistent Harmonization of Multi-View Appearance via Bilateral Grid Prediction | Jisu Shin | |
| 10008033-P | Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoders | Guangzhi Xiong | |
| 10008045-P | Self-Speculative Decoding Accelerates Lossless Inference in Any-Order and Any-Subset Autoregressive Models | Gabe Guo | |
| 10008067-P | Pose Prior Learner: Unsupervised Categorical Prior Learning for Pose Estimation | Ziyu Wang | |
| 10008084-P | Discrete Diffusion Trajectory Alignment via Stepwise Decomposition | Jiaqi Han | |
| 10008085-P | In-Context Learning of Temporal Point Processes with Foundation Inference Models | David Berghaus | |
| 10008091-P | Medical thinking with multiple images | Benlu Wang | |
| 10008101-P | NoisePrints: Distortion-Free Watermarks for Authorship in Private Diffusion Models | Nir Goren | |
| 10008106-P | STEM: SCALING TRANSFORMERS WITH EMBEDDING MODULES | ZECHUN Liu | |
| 10008110-P | ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation | Yongyuan Liang | |
| 10008113-P | TimeSearch-R: Adaptive Temporal Search for Long-Form Video Understanding via Self-Verification Reinforcement Learning | Junwen Pan | |
| 10008115-P | Global Resolution: Optimal Multi-Draft Speculative Sampling via Convex Optimization | Arka Pal | |
| 10008124-P | Multi-Condition Conformal Selection | Qingyang Hao | |
| 10008128-P | LiveResearchBench: A Live Benchmark for User-Centric Deep Research in the Wild | Jiayu Wang | |
| 10008132-P | TAVAE: A VAE with Adaptable Priors Explains Contextual Modulation in the Visual Cortex | Balázs Meszéna | |
| 10008136-P | APC-RL: Exceeding data-driven behavior priors with adaptive policy composition | Finn Rietz | |
| 10008138-P | DynaGuard: A Dynamic Guardian Model With User-Defined Policies | Monte Hoover | |
| 10008140-P | Evidence for Limited Metacognition in LLMs | Christopher Ackerman | |
| 10008142-P | Probability Distributions Computed by Hard-Attention Transformers | Andy Yang | |
| 10008149-P | SCRIBES: Web-Scale Script-Based Semi-Structured Data Extraction with Reinforcement Learning | Kai Sun | |
| 10008165-P | ActivationReasoning: Logical Reasoning in Latent Activation Spaces | Ruben Härle | |
| 10008176-P | Barriers for Learning in an Evolving World: Mathematical Understanding of Loss of Plasticity | Amir Joudaki | |
| 10008177-P | Plan-Answer-Refine-on-Graph: Structured Planning and Self-Refinement for Large Language Model Reasoning on Knowledge Graphs | Xiaoxue Ren | |
| 10008181-P | Enhancing Learning with Noisy Labels via Rockafellian Relaxation | Bobbie Chern | |
| 10008187-P | BoGrape: Bayesian optimization over graphs with shortest-path encoded | Yilin Xie | |
| 10008195-P | REMem: Reasoning with Episodic Memory in Language Agent | Saisri Padmaja Jonnalagedda | |
| 10008198-P | Learning Survival Distributions with Individually Calibrated Asymmetric Laplace Distribution | Ricardo Henao | |
| 10008203-P | When Machine Learning Gets Personal: Evaluating Prediction and Explanation | Louisa Cornelis | |
| 10008207-P | DiVE-k: DIFFERENTIAL VISUAL REASONING FOR FINE-GRAINED IMAGE RECOGNITION | Raja Kumar | |
| 10008208-P | KL-Regularized Reinforcement Learning is Designed to Mode Collapse | Anthony GX-Chen | |
| 10008215-P | Convergence Analysis of Tsetlin Machines under Noise-Free and Noisy Training Conditions: From 2 Bits to k Bits | Lei Jiao | |
| 10008221-P | RewardBench 2: Advancing Reward Model Evaluation | Saumya Malik | |
| 10008225-P | KRAMABENCH: A Benchmark for AI Systems on Data-to-Insight Pipelines over Data Lakes | Gerardo Vitagliano | |
| 10008228-P | Bottlenecked Transformers: Periodic KV Cache Consolidation for Generalised Reasoning | Adnan Oomerjee | |
| 10008230-P | Train on Validation (ToV): Fast data selection with applications to fine-tuning | Eren Sasoglu | |
| 10008237-P | Improving Attributed Long-form Question Answering with Intent Awareness | Jay DeYoung | |
| 10008242-P | Cancer-Myth: Evaluating Large Language Models on Patient Questions with False Presuppositions | Wang Bill Zhu | |
| 10008247-P | Scaling Sequence-to-Sequence Generative Neural Rendering | Shikun Liu | |
| 10008248-P | Talk, Evaluate, Diagnose: User-aware Agent Evaluation with Automated Error Analysis | Penny Chong | |
| 10008253-P | Risk Phase Transitions in Spiked Regression: Alignment Driven Benign and Catastrophic Overfitting | Jiping Li | |
| 10008264-P | MATA: A Trainable Hierarchical Automaton System for Multi-Agent Visual Reasoning | Zhixi Cai | |
| 10008270-P | Dual Perspectives on Non-Contrastive Self-Supervised Learning | Basile Terver | |
| 10008274-P | EdgeCape: Edge Weight Prediction For Category-Agnostic Pose Estimation | Or Hirschorn | |
| 10008278-P | Latent Veracity Inference for Identifying Errors in Stepwise Reasoning | Jean-Pierre Falet | |
| 10008279-P | Online Rounding and Learning Augmented Algorithms for Facility Location | Debmalya Panigrahi | |
| 10008285-P | SLAP: Shortcut Learning for Abstract Planning | Yijie Liu | |
| 10008287-P | QuaMo: Quaternion Motions for Vision-based 3D Human Kinematics Capture | Cuong Le | |
| 10008301-P | Discovering Novel LLM Experts via Task-Capability Coevolution | Yingtao Tian | |
| 10008308-P | Learned Meta-Tokens for Language Modeling | Keshav Ramji | |
| 10008323-P | KaVa: Latent Reasoning via Compressed KV-Cache Distillation | Anna Kuzina | |
| 10008324-P | Constitutional Classifiers++: Production-Grade Defenses against Universal Jailbreaks | Hoagy Cunningham | |
| 10008333-P | Turbo-DDCM: Fast and Flexible Zero-Shot Diffusion-Based Image Compression | Amit Vaisman | |
| 10008339-P | Memba: Membrane-driven Parameter-Efficient Fine-Tuning for Mamba | Donghyun Lee | |
| 10008343-P | Agentic Context Engineering: Learning Comprehensive Contexts for Self-Improving Language Models | Daniel Daniel | |
| 10008346-P | ATOM: A Pretrained Neural Operator for Multitask Molecular Dynamics | Luke Thompson | |
| 10008350-P | Revela: Dense Retriever Learning via Language Modeling | Fengyu Cai | |
| 10008366-P | LightMem: Lightweight and Efficient Memory-Augmented Generation | Shuofei Qiao | |
| 10008370-P | Initialization Schemes for Kolmogorov–Arnold Networks: An Empirical Study | Spyros Rigas | |
| 10008376-P | UI-Ins: Enhancing GUI Grounding with Multi-Perspective Instruction as Reasoning | Liangyu Chen | |
| 10008391-P | Identifying and Evaluating Inactive Heads in Pretrained LLMs | Pedro Sandoval Segura | |
| 10008401-P | Improving Feasibility via Fast Autoencoder-Based Projections | Maria Chzhen | |
| 10008407-P | Reward Models Inherit Value Biases from Pretraining | Brian Christian | |
| 10008411-P | Customizing Visual Emotion Evaluation for MLLMs: An Open-vocabulary, Multifaceted, and Scalable Approach | Daiqing Wu | |
| 10008418-P | AbdCTBench: Learning Clinical Biomarker Representations from Abdominal Surface Geometry | Muhammad Ahmed Chaudhry | |
| 10008420-P | BridgeDrive: Diffusion Bridge Policy for Closed-Loop Trajectory Planning in Autonomous Driving | Shu Liu | |
| 10008429-P | Closing the Gap Between Text and Speech Understanding in LLMs | Santiago Cuervo | |
| 10008433-P | Zero-Shot Adaptation of Behavioral Foundation Models to Unseen Dynamics | Maksim Bobrin | |
| 10008436-P | Monocular Normal Estimation via Shading Sequence Estimation | Zongrui Li | |
| 10008439-P | HierLoc: Hyperbolic Entity Embeddings for Hierarchical Visual Geolocation | Hari Krishna Gadi | |
| 10008442-P | Mitigating Privacy Risk via Forget Set-Free Unlearning | Aviraj Newatia | |
| 10008457-P | Gradient-Based Diversity Optimization with Differentiable Top-$k$ Objective | Tianyi Zhou | |
| 10008463-P | Text2Interact: High-Fidelity and Diverse Text-to-Two-Person Interaction Generation | Qingxuan Wu | |
| 10008472-P | Confident and Adaptive Generative Speech Recognition via Risk Control | Amit Damri | |
| 10008473-P | Pre-training under infinite compute | Suhas Kotha | |
| 10008476-P | OpenApps: Simulating Environment Variations to Measure UI Agent Reliability | Mark Ibrahim | |
| 10008481-P | WALT: Web Agents that Learn Tools | Viraj Prabhu | |
| 10008485-P | Boosting Medical Visual Understanding From Multi-Granular Language Learning | Zihan Li | |
| 10008490-P | DiaBlo: Diagonal Blocks Are Sufficient For Finetuning | Selcuk Gurses | |
| 10008491-P | INTIMA: A Benchmark for Human-AI Companionship Behavior | Giada Pistilli | |
| 10008504-P | Bayesian Parameter Shift Rules in Variational Quantum Eigensolvers | Samuele Pedrielli | |
| 10008511-P | SportR: A Benchmark for Multimodal Large Language Model Reasoning in Sports | Haotian Xia | |
| 10008512-P | Overshoot and Shrinkage in Classifier-Free Guidance: From Theory to Practice | Krunoslav Lehman Pavasovic | |
| 10008517-P | When LLMs get significantly worse: A statistical approach to detect model degradations | Jonas Kübler | |
| 10008529-P | Structurally Human, Semantically Biased: Detecting LLM-Generated References with Embeddings and GNNs | Melika Mobini | |
| 10008533-P | TerraFM: A Scalable Foundation Model for Unified Multisensor Earth Observation | Muhammad Sohail Danish | |
| 10008543-P | Attention Sinks and Compression Valleys in LLMs are Two Sides of the Same Coin | Enrique Queipo de Llano Burgos | |
| 10008545-P | gLSTM: Mitigating Over-Squashing by Increasing Storage Capacity | Hugh Blayney | |
| 10008547-P | Diagnosing Failures in Generalization from Task-Relevant Representational Geometry | Chi-Ning Chou | |
| 10008552-P | Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains | Anisha Gunjal | |
| 10008555-P | Entropy-Based Block Pruning for Efficient Large Language Models | Liangwei Yang | |
| 10008558-P | Change Point Localization and Inference in Dynamic Multilayer Networks | OSCAR HERNAN MADRID PADILLA | |
| 10008561-P | Short Window Attention Enables Long-Term Memorization | LOIC CABANNES | |
| 10008583-P | EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning | Soo Ye Kim | |
| 10008589-P | TRIBE: TRImodal Brain Encoder for whole-brain fMRI response prediction | Stéphane dAscoli | |
| 10008598-P | Beyond DAGs: A Latent Partial Causal Model for Multimodal Learning | Yuhang Liu | |
| 10008602-P | Pixel-Level Residual Diffusion Transformer: Scalable 3D CT Volume Generation | ZHENKAI ZHANG | |
| 10008605-P | Thought Branches: Interpreting LLM Reasoning Requires Resampling | Uzay Macar | |
| 10008624-P | Is In-Context Learning Learning? | Adrian de Wynter | |
| 10008635-P | Fused-Planes: Why Train a Thousand Tri-Planes When You Can Share? | Antoine Schnepf | |
| 10008637-P | Domain Expansion: A Latent Space Construction Framework for Multi-Task Learning | Chi-Yao Huang | |
| 10008644-P | Enabling arbitrary inference in spatio-temporal dynamic systems: A physics-inspired perspective | Yan Ge | |
| 10008646-P | GeomMotif: A Benchmark for Arbitrary Geometric Preservation in Protein Generation | Pavel Strashnov | |
| 10008649-P | Interpolation-Based Conditioning of Flow Matching Models for Bioisosteric Ligand Design | Yael Ziv | |
| 10008655-P | Understanding Transformers for Time Series: Rank Structure, Flow-of-ranks, and Compressibility | Boran Han | |
| 10008665-P | Decoupled Q-Chunking | Qiyang Li | |
| 10008669-P | Poly-attention: a general scheme for higher-order self-attention | Sayak Chakrabarti | |
| 10008672-P | Neuro-Symbolic Decoding of Neural Activity | Joy Hsu | |
| 10008675-P | Aligning Visual Foundation Encoders to Tokenizers for Diffusion Models | Hao Tan | |
| 10008682-P | SARM: Stage-Aware Reward Modeling for Long Horizon Robot Manipulation | Qianzhong Chen | |
| 10008683-P | Beyond Multi-Token Prediction: Pretraining LLMs with Future Summaries | Kartik Ahuja | |
| 10008692-P | Zephyrus: An Agentic Framework for Weather Science | Marshall Fisher | |
| 10008698-P | VoMP: Predicting Volumetric Mechanical Property Fields | Rishit Dagli | |
| 10008706-P | Exploring Synthesizable Chemical Space with Iterative Pathway Refinements | Seul Lee | |
| 10008708-P | KV-Cache Transform Coding for Compact Storage in LLM Inference | Konrad Staniszewski | |
| 10008710-P | Dual Goal Representations | Seohong Park | |
| 10008713-P | Type-Compliant Adaptation Cascades | Chu-Cheng Lin | |
| 10008714-P | True Self-Supervised Novel View Synthesis is Transferable | Hyunwoo Ryu | |
| 10008719-P | Robust Fine-Tuning from Non-Robust Pretrained Models: Mitigating Suboptimal Transfer With Epsilon-Scheduling | JONAS NGNAWE | |
| 10008720-P | Revisiting the Past: Data Unlearning with Model State History | Abhilasha Ravichander | |
| 10008726-P | Learning Distributions over Permutations and Rankings with Factorized Representations | Brian Karrer | |
| 10008727-P | Strictly Constrained Generative Modeling via Split Augmented Langevin Sampling | Matthieu Blanke | |
| 10008731-P | LearnIR: Learnable Posterior Sampling for Real-World Image Restoration | Yihang Bao | |
| 10008732-P | Propaganda AI: An Analysis of Semantic Divergence in Large Language Models | Nay Myat Min | |
| 10008733-P | FROST: Filtering Reasoning Outliers with Attention for Efficient Reasoning | Jiang Zhuolin | |
| 10008734-P | RAP: 3D Rasterization Augmented End-to-End Planning | Lan Feng | |
| 10008737-P | Best-of-Majority: Minimax-Optimal Strategy for Pass@k Inference Scaling | Xuheng Li | |
| 10008752-P | Language in the Flow of Time: Time-Series-Paired Texts Weaved into a Unified Temporal Narrative | Zihao Li | |
| 10008761-P | Layerwise Federated Learning for Heterogeneous Quantum Clients using Quorus | Jason Han | |
| 10008774-P | Multilingual Routing in Mixture-of-Experts | Lucas Bandarkar | |
| 10008782-P | DragFlow: Unleashing DiT Priors with Region-Based Supervision for Drag Editing | Zihan Zhou | |
| 10008790-P | TyphoonMLA: A Mixed Naive-Absorb MLA Kernel For Shared Prefix | Ahmet Caner Yuzuguler | |
| 10008791-P | Midway Network: Learning Representations for Recognition and Motion from Latent Dynamics | Christopher Hoang | |
| 10008793-P | On Smoothness Bounds for Non-Clairvoyant Scheduling with Predictions | zhiyun Jiang | |
| 10008794-P | Dynamic Chunking for End-to-End Hierarchical Sequence Modeling | Sukjun Hwang | |
| 10008804-P | NurValues: Real-World Nursing Values Evaluation for Large Language Models in Clinical Context | Ben Yao | |
| 10008812-P | Zero-shot Forecasting by Simulation Alone | Boris Oreshkin | |
| 10008814-P | Toward Safer Diffusion Language Models: Discovery and Mitigation of Priming Vulnerability | Shojiro Yamabe | |
| 10008829-P | AssoMem: Scalable Memory QA with Multi-Signal Associative Retrieval | Xinyuan Zhang | |
| 10008832-P | Energy-Based Transformers are Scalable Learners and Thinkers | Alexi Gladstone | |
| 10008850-P | How Muon´s Spectral Design Benefits Generalization: A Study on Imbalanced Data | Bhavya Vasudeva | |
| 10008853-P | Transformers are Inherently Succinct | Pascal Bergsträer | |
| 10008866-P | Diffusion and Flow-based Copulas: Forgetting and Remembering Dependencies | David Huk | |
| 10008867-P | Let´s Split Up: Zero-Shot Classifier Edits for Fine-Grained Video Understanding | Kaiting Liu | |
| 10008870-P | Pretraining Scaling Laws for Generative Evaluations of Language Models | Rylan Schaeffer | |
| 10008871-P | Detecting Data Contamination in LLMs via In-Context Learning | Michal Zawalski | |
| 10008872-P | EdiVal-Agent: An Object-Centric Framework for Automated, Fine-Grained Evaluation of Multi-Turn Editing | Tianyu Chen | |
| 10008883-P | SGD-Based Knowledge Distillation with Bayesian Teachers: Theory and Guidelines | Itai Morad | |
| 10008886-P | Towards Interpretable Visual Decoding with Attention to Brain Representations | Hossein Adeli | |
| 10008892-P | QuoKA: Query-Oriented KV Selection for Efficient LLM Prefill | Matthew Langston | |
| 10008900-P | HYPER: A Foundation Model for Inductive Link Prediction with Knowledge Hypergraphs | Xingyue Huang | |
| 10008904-P | Bayesian Influence Functions for Hessian-Free Data Attribution | Philipp Alexander Kreer | |
| 10008937-P | UniTrack: Differentiable Graph Representation Learning for Multi-Object Tracking | Bishoy Galoaa | |
| 10008938-P | More Thought, Less Accuracy? On the Dual Nature of Reasoning in Vision-Language Models | Xinyu Tian | |
| 10008973-P | Pretraining with hierarchical memories: separating long-tail and common knowledge | Michael Kirchhof | |
| 10008984-P | QVGen: Pushing the Limit of Quantized Video Generative Models | Yushi Huang | |
| 10008987-P | Toward Principled Flexible Scaling for Self-Gated Neural Activation | Shuyuan Zheng | |
| 10008988-P | Decision-Theoretic Approaches for Improved Learning-Augmented Algorithms | Christoph Dürr | |
| 10008993-P | Transductive Visual Programming: Evolving Tool Libraries from Experience for Spatial Reasoning | Shengguang Wu | |
| 10008996-P | Transitive RL: Value Learning via Divide and Conquer | Seohong Park | |
| 10009005-P | Label Smoothing Improves Machine Unlearning | Zonglin Di | |
| 10009017-P | Variational Deep Learning via Implicit Regularization | Jonathan Wenger | |
| 10009023-P | Enhancing Hallucination Detection through Noise Injection | Litian Liu | |
| 10009034-P | RESFL: An Uncertainty-Aware Framework for Responsible Federated Learning by Balancing Privacy, Fairness and Utility | Dawood Wasif | |
| 10009036-P | Conjuring Semantic Similarity | Tian Yu Liu | |
| 10009045-P | Scalable Offline Model-Based RL with Action Chunks | Kwanyoung Park | |
| 10009049-P | Reliable Weak-to-Strong Monitoring of LLM Agents | Neil Kale | |
| 10009052-P | A Unifying Framework for Causal Imitation Learning with Hidden Confounders | Daqian Shao | |
| 10009069-P | Learning Admissible Heuristics for A*: Theory and Practice | Ehsan Futuhi | |
| 10009072-P | Frayed RoPE and Long Inputs: A Geometric Perspective | Davis Wertheimer | |
| 10009100-P | Routing, Cascades, and User Choice for LLMs | Rafid Mahmood | |
| 10009127-P | Do We Need All the Synthetic Data? Targeted Image Augmentation via Diffusion Models | Tuan Hai Dang Nguyen | |
| 10009135-P | ImageRAG: Dynamic Image Retrieval for Reference-Guided Image Generation | Rotem Shalev-Arkushin | |
| 10009141-P | Small Transformers Don´t Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and Implications for Mechanistic Interpretability | Marat Subkhankulov | |
| 10009169-P | StPR: Spatiotemporal Preservation and Routing for Exemplar-Free Video Class-Incremental Learning | Huaijie Wang | |
| 10009174-P | Theoretical Guarantees for Causal Discovery on Large Random Graphs | Mathieu Chevalley | |
| 10009182-P | Summaries as Centroids for Interpretable and Scalable Text Clustering | Jairo Diaz-Rodriguez | |
| 10009183-P | Understanding the Learning Phases in Self-Supervised Learning via Critical Periods | JangHyeon Lee | |
| 10009191-P | Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning | Jun Yan | |
| 10009196-P | KGOT: Unified Knowledge Graph and Optimal Transport Pseudo-Labeling for Molecule-Protein Interaction Prediction | Jiayu Qin | |
| 10009198-P | Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction | Simon Giebenhain | |
| 10009206-P | Features Emerge as Discrete States: The First Application of SAEs to 3D Representations | Albert Miao | |
| 10009235-P | Synthesizing High-Quality Visual Question Answering from Medical Documents with Generator-Verifier LMMs | Xiaoke Huang | |
| 10009237-P | Towards Reliable Benchmarking: A Contamination Free, Controllable Evaluation Framework for Multi-step LLM Function Calling | Seiji Maekawa | |
| 10009239-P | Improving Text-guided CAD Prototyping via Modality-Specific Tokenization | Ruiyu Wang | |
| 10009242-P | Mixing Mechanisms: How Language Models Retrieve Bound Entities In-Context | Yoav Gur-Arieh | |
| 10009243-P | LLM DNA: Tracing Model Evolution via Functional Representations | Zhaomin Wu | |
| 10009245-P | Dyslexify: A Mechanistic Defense Against Typographic Attacks in CLIP | Lorenz Hufe | |
| 10009247-P | ReTabAD: A Benchmark for Restoring Semantic Context in Tabular Anomaly Detection | Sanghyu Yoon | |
| 10009256-P | DeMo: Decoupled Momentum Optimization | Bowen Peng | |
| 10009276-P | Learning Retrieval Models with Sparse Autoencoders | Stephane Clinchant | |
| 10009287-P | Correlated Policy Optimization in Multi-Agent Subteams | Qi Zhang | |
| 10009298-P | Dynamical properties of dense associative memory | Kazushi Mimura | |
| 10009303-P | Test-Time Training Done Right | Hao Tan | |
| 10009308-P | LiTo: Surface Light Field Tokenization | Jen-Hao Chang | |
| 10009309-P | Towards Self-Robust LLMs: Intrinsic Prompt Noise Resistance via CoIPO | Xin Yang | |
| 10009315-P | Can Language Models Discover Scaling Laws? | Haowei Lin | |
| 10009318-P | UnLoc: Leveraging Depth Uncertainties for Floorplan Localization | Matthias Wüest | |
| 10009319-P | SCOPED: Score–Curvature Out-of-distribution Proximity Evaluator for Diffusion | Brett Barkley | |
| 10009329-P | Function Induction and Task Generalization: An Interpretability Study with Off-by-One Addition | Qinyuan Ye | |
| 10009337-P | BioTamperNet: Affinity-Guided State-Space Model Detecting Tampered Biomedical Images | Soumyaroop Nandi | |
| 10009348-P | Market Games for Generative Models: Equilibria, Welfare, and Strategic Entry | Xiukun Wei | |
| 10009361-P | Faster Vision Transformers with Adaptive Patch Sizes | Rohan Choudhury | |
| 10009362-P | Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation | Lu Ling | |
| 10009373-P | Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning | Chongyu Fan | |
| 10009377-P | From Samples to Scenarios: A New Paradigm for Probabilistic Forecasting | Xilin Dai | |
| 10009378-P | VeriTrail: Closed-Domain Hallucination Detection with Traceability | Dasha Metropolitansky | |
| 10009381-P | Concept-based Adversarial Attack: a Probabilistic Perspective | Andi Zhang | |
| 10009387-P | Asynchronous Policy Gradient Aggregation for Efficient Distributed Reinforcement Learning | Alexander Tyurin | |
| 10009400-P | A.I.R.: Enabling Adaptive, Iterative, and Reasoning-based Frame Selection For Video Question Answering | Yuanhao Zou | |
| 10009404-P | A Fictional Q&A Dataset for Studying Memorization and Knowledge Acquisition | John Kirchenbauer | |
| 10009405-P | Positional Encoding Field | Yunpeng Bai | |
| 10009408-P | Emergent Coordination in Multi-Agent Language Models | Christoph Riedl | |
| 10009421-P | DeNOTS: Stable Deep Neural ODEs for Time Series | Ilya Kuleshov | |
| 10009427-P | SysMoBench: Evaluating AI on Formally Specifying Complex Real-World Systems | Qian Cheng | |
| 10009432-P | Sci2Pol: Evaluating and Fine-tuning LLMs on Scientific-to-Policy Brief Generation | Weimin Wu | |
| 10009435-P | Mixture of Mini Experts: Overcoming the Linear Layer Bottleneck in Multiple Instance Learning | Daniel Shao | |
| 10009443-P | Frequency-Domain Better than Time-Domain for Causal Structure Recovery in Dynamical Systems on Networks | Mohammed Tuhin Rana | |
| 10009472-P | Pisces: Cryptography-based Private Retrieval-Augmented Generation with Dual-Path Retrieval | Jun Jie Sim | |
| 10009474-P | LEGATO: Large-scale End-to-end Generalizable Approach to Typeset OMR | Victoria Ebert | |
| 10009481-P | Generative Value Conflicts Reveal LLM Priorities | Andy Liu | |
| 10009483-P | LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generation | Ingyu Seong | |
| 10009485-P | Does "Do Differentiable Simulators Give Better Policy Gradients?" Give Better Policy Gradients? | Ku Onoda | |
| 10009490-P | Two (narrow) heads are better than (an arbitrarily wide) one | Amanuel Tesfaye | |
| 10009500-P | Score Distillation Beyond Acceleration: Generative Modeling from Corrupted Data | Tianyu Chen | |
| 10009510-P | Generative Modeling from Black-Box Corruptions via Self-Consistent Stochastic Interpolants | Jiequn Han | |
| 10009518-P | La-Proteina: Atomistic Protein Generation via Partially Latent Flow Matching | Karsten Kreis | |
| 10009522-P | A Balanced Neuro-Symbolic Approach for Commonsense Abductive Logic | Joseph Cotnareanu | |
| 10009525-P | The Intricate Dance of Prompt Complexity, Quality, Diversity and Consistency in T2I Models | Xiaofeng Zhang | |
| 10009531-P | Exploring State-Space Models for Data-Specific Neural Representations | Jinsung Lee | |
| 10009541-P | No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms | Abhay Puri | |
| 10009551-P | Unifying Stable Optimization and Reference Regularization in RLHF | Li He | |
| 10009553-P | WearVox: An Egocentric Multichannel Voice Assistant Benchmark for Wearables | Wenfang Xu | |
| 10009555-P | Virtual Community: An Open World for Humans, Robots, and Society | Qinhong Zhou | |
| 10009565-P | H2OFlow: Grounding Human-Object Affordances with 3D Generative Models and Dense Diffused Flows | Harry Zhang | |
| 10009567-P | SocialJax: An Evaluation Suite for Multi-agent Reinforcement Learning in Sequential Social Dilemmas | Zihao Guo | |
| 10009569-P | Refine Drugs, Don´t Complete Them: Uniform-Source Discrete Flows for Fragment-Based Drug Discovery | benno kaech | |
| 10009580-P | Contextual Causal Bayesian Optimisation | Vahan Arsenyan | |
| 10009581-P | MARS - A Foundational Map Auto-Regressor | Suvam Bag | |
| 10009584-P | Bootstrapping MLLM for Weakly-Supervised Class-Agnostic Object Counting | Miaojing Shi | |
| 10009585-P | Same Content, Different Representations: A Controlled Study for Table QA | Seiji Maekawa | |
| 10009594-P | Spinning Straw into Gold: Relabeling LLM Agent Trajectories in Hindsight for Successful Demonstrations | Zichao Li | |
| 10009597-P | DTO-KD: Dynamic Trade-off Optimization for Effective Knowledge Distillation | Zeeshan Hayder | |
| 10009609-P | DiffVax: Optimization-Free Image Immunization Against Diffusion-Based Editing | Tarik Can Ozden | |
| 10009614-P | ATLAS: Alibaba Dataset and Benchmark for Learning-Augmented Scheduling | zhiyun Jiang | |
| 10009616-P | GAGA: Gaussianity-Aware Gaussian Approximation for Efficient 3D Molecular Generation | Jingxiang Qu | |
| 10009626-P | Oversmoothing, "Oversquashing´´, Heterophily, Long-Range, and more: Demystifying Common Beliefs in Graph Machine Learning | Federico Errica | |
| 10009635-P | Implicit Models: Expressive Power Scales with Test-Time Compute | Jialin Liu | |
| 10009652-P | A Brain Graph Foundation Model: Pre-Training and Prompt-Tuning across Broad Atlases and Disorders | Xinxu Wei | |
| 10009653-P | Reasoning on Time-Series for Financial Technical Analysis | Jan Chen | |
| 10009669-P | Don´t Pass@k: A Bayesian Framework for Large Language Model Evaluation | Mohsen Hariri | |
| 10009677-P | Harmonized Cone for Feasible and Non-conflict Directions in Training Physics-Informed Neural Networks | Dohyun Bu | |
| 10009689-P | Demystifying Robot Diffusion Policies: Action Memorization and a Simple Lookup Table Alternative | Gadiel Sznaier Camps | |
| 10009700-P | Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts | Zhaomin Wu | |
| 10009712-P | Hyperparameter Trajectory Inference with Conditional Lagrangian Optimal Transport | Harry Amad | |
| 10009726-P | Speculative Actions: A Lossless Framework for Faster AI Agents | Naimeng Ye | |
| 10009729-P | VLSU: Mapping the Limits of Joint Multimodal Understanding for AI Safety | Leon Gatys | |
| 10009730-P | PateGAIL++: Utility Optimized Private Trajectory Generation with Imitation Learning | Yingjie Ma | |
| 10009734-P | Time-to-Move: Training-Free Motion-Controlled Video Generation via Dual-Clock Denoising | Assaf Singer | |
| 10009735-P | BEAT: Visual Backdoor Attacks on VLM-based Embodied Agents via Contrastive Trigger Learning | QIUSI ZHAN | |
| 10009740-P | Alignment-Weighted DPO: A principled reasoning approach to improve alignment | Vivek Datla | |
| 10009745-P | ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs | Wonjun Kang | |
| 10009767-P | DepthLM: Metric Depth from Vision Language Models | Zhipeng Cai | |
| 10009772-P | Uncertainty as Feature Gaps: Epistemic Uncertainty Quantification of LLMs in Contextual Question-Answering | Yavuz Faruk Bakman | |
| 10009775-P | PPE: Positional Preservation Embedding for Token Compression in Multimodal Large Language Models | Mouxiao Huang | |
| 10009785-P | DOPPLER: Dual-Policy Learning for Device Assignment in Asynchronous Dataflow Graphs | Xinyu Yao | |
| 10009789-P | Markovian Transformers for Informative Language Modeling | Scott Viteri | |
| 10009793-P | Align Your Structures: Generating Trajectories with Structure Pretraining for Molecular Dynamics | Aniketh Iyengar | |
| 10009813-P | Discovering Hierarchical Software Engineering Agents via Bandit Optimization | Aldo Pareja | |
| 10009819-P | Personalized Reasoning: Just-in-time Personalization and Why LLMs Fail at It | Avinandan Bose | |
| 10009823-P | Learning Unified Representation of 3D Gaussian Splatting | Yuelin Xin | |
| 10009829-P | Incentives in Federated Learning with Heterogeneous Agents | Justin Benton | |
| 10009841-P | PAGE-4D: Disentangled Pose and Geometry Estimation for 4D Perception | Wei Dai | |
| 10009842-P | Learning from Algorithm Feedback: One-Shot SAT Solver Guidance with GNNs | Jan Toenshoff | |
| 10009852-P | Steering Autoregressive Music Generation with Recursive Feature Machines | Daniel Zhao | |
| 10009853-P | Learning to Grasp Anything By Playing with Random Toys | Yuvan Sharma | |
| 10009862-P | GneissWeb: Preparing High Quality Data for LLMs at Scale | Hajar Emami Gohari | |
| 10009864-P | Unified 3D Scene Understanding Through Physical World Modeling | Wanhee Lee | |
| 10009872-P | LABEL-FREE MITIGATION OF SPURIOUS CORRELATIONS IN VLMS USING SPARSE AUTOENCODERS | Bharat Chandra Yalavarthi | |
| 10009875-P | In-Context Learning for Pure Exploration | Ryan Welch | |
| 10009876-P | The Geometry of LLM Quantization: GPTQ as Babai´s Nearest Plane Algorithm | Jiale Chen | |
| 10009881-P | VERIFY: A Novel Multi-Domain Dataset Grounding LTL in Contextual Natural Language via Provable Intermediate Logic | Paapa Quansah | |
| 10009903-P | SmartChunk Retrieval: Query-Aware Chunk Compression with Planning for Efficient Document RAG | Xuechen Zhang | |
| 10009904-P | ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents | Ido Levy | |
| 10009919-P | Exploratory Causal Inference in SAEnce | Riccardo Cadei | |
| 10009924-P | From Collapse to Control: Understanding and Extending Context Length in Emerging Hybrid Models via Universal Position Interpolation | Davis Wertheimer | |
| 10009942-P | Unsupervised Representation Learning - an Invariant Risk Minimization Perspective | Yotam Norman | |
| 10009954-P | Search Arena: Analyzing Search-Augmented LLMs | Tsung-Han Wu | |
| 10009956-P | Multi-LCB: Extending LiveCodeBench to Multiple Programming Languages | Dmitrii Babaev | |
| 10009961-P | Discrete Compositional Generation via General Soft Operators and Robust Reinforcement Learning | Marco Jiralerspong | |
| 10009963-P | AVEX: What Matters for Animal Vocalization Encoding | Marius Miron | |
| 10009983-P | Diffusion Blend: Inference-Time Multi-Preference Alignment for Diffusion Models | Fatemeh Doudi | |
| 10009999-P | Keep the Best, Forget the Rest: Reliable Alignment with Order-Aware Preference Optimization | Jiahui Zhu | |
| 10010034-P | Massive Memorization with Hundreds of Trillions of Parameters for Sequential Transducer Generative Recommenders | Chenyu Zhao | |
| 10010041-P | Boolean Satisfiability via Imitation Learning | Zewei Zhang | |
| 10010054-P | Soft Quality-Diversity Optimization | Saeed Hedayatian | |
| 10010063-P | TEST-TIME SCALING IN DIFFUSION LLMS VIA HIDDEN SEMI-AUTOREGRESSIVE EXPERTS | Kevin Zhai | |
| 10010083-P | Locality-Attending Vision Transformer | Sina Hajimiri | |
| 10010090-P | Reconstruct Anything Model a lightweight foundation model for computational imaging | Victor Sechaud | |
| 10010096-P | 3DSMT: A Hybrid Spiking Mamba-Transformer for Point Cloud Analysis | Yong He | |
| 10010113-P | MolLangBench: A Comprehensive Benchmark for Language-Prompted Molecular Structure Recognition, Editing, and Generation | Feiyang Cai | |
| 10010121-P | RegionReasoner: Region-Grounded Multi-Round Visual Reasoning | Wenfang Sun | |
| 10010122-P | Non-Clashing Teaching in Graphs: Algorithms, Complexity, and Bounds | Liana Khazaliya | |
| 10010125-P | FlashDLM: Accelerating Diffusion Language Model Inference via Efficient KV Caching and Guided Diffusion | Jian Meng | |
| 10010128-P | Towards Efficient Optimizer Design for LLM via Structured Fisher Approximation with a Low-Rank Extension | Wenbo Gong | |
| 10010132-P | Formalising Human-in-the-Loop: Computational Reductions, Failure Modes, and Legal-Moral Responsibility | Maurice Chiodo | |
| 10010149-P | Birch SGD: A Tree Graph Framework for Local and Asynchronous SGD Methods | Alexander Tyurin | |
| 10010161-P | VLM-Guided Adaptive Negative Prompting for Creative Generation | Shelly Golan | |
| 10010168-P | Contrastive Predictive Coding Done Right for Mutual Information Estimation | Jongha Ryu | |
| 10010195-P | Characteristic Root Analysis and Regularization for Linear Time Series Forecasting | Zheng Wang | |
| 10010203-P | Continuously Augmented Discrete Diffusion model for Categorical Generative Modeling | Huangjie Zheng | |
| 10010219-P | InfoTok: Adaptive Discrete Video Tokenizer via Information-Theoretic Compression | Haotian Ye | |
| 10010221-P | What happens when generative AI models train recursively on each others´ outputs? | Hung Anh Vu | |
| 10010223-P | MC-Search: Evaluating and Enhancing Multimodal Agentic Search with Structured Long Reasoning Chains | Xuying Ning | |
| 10010230-P | Seeing but Not Believing: Probing the Disconnect Between Visual Attention and Answer Correctness in VLMs | Zhining Liu | |
| 10010239-P | Factuality Matters: When Image Generation and Editing Meet Structured Visuals | Sayak Paul | |
| 10010240-P | ATEX-CF: Attack-Informed Counterfactual Explanations for Graph Neural Networks | Yu Zhang | |
| 10010245-P | BTZSC: A Benchmark for Zero-Shot Text Classification Across Cross-Encoders, Embedding Models, and Rerankers | Ilias Aarab | |
| 10010246-P | Operator Learning with Domain Decomposition for Geometry Generalization in PDE Solving | Jianing Huang | |
| 10010249-P | Bridging Kolmogorov Complexity and Deep Learning: Asymptotically Optimal Description Length Objectives for Transformers | Peter Shaw | |
| 10010250-P | Revisiting Active Sequential Prediction-Powered Mean Estimation | Maria-Eleni Sfyraki | |
| 10010273-P | Sobolev Gradient Ascent for Optimal Transport: Barycenter Optimization and Convergence Analysis | Kaheon Kim | |
| 10010277-P | ROSETTA: Constructing Code-Based Reward from Unconstrained Language Preference | Yung-Chieh Chan | |
| 10010286-P | Reference Grounded Skill Discovery | SEUNGEUN RHO | |
| 10010287-P | AceReason-Nemotron 1.1: Advancing Math and Code Reasoning through SFT and RL Synergy | Zihan Liu | |
| 10010297-P | Sapiens2 | Rawal Khirodkar | |
| 10010321-P | DRIFT: Decompose, Retrieve, Illustrate, then Formalize Theorems | Gerasimos Lampouras | |
| 10010328-P | LRIM: a Physics-Based Benchmark for Provably Evaluating Long-Range Capabilities in Graph Learning | Joel Mathys | |
| 10010339-P | Disentangled representation learning through unsupervised symmetry group discovery | Barthélémy Dang-Nhu | |
| 10010345-P | Can Vision-Language Models Answer Face to Face Questions in the Real World? | Reza Pourreza | |
| 10010346-P | PHyCLIP: $\ell_1$-Product of Hyperbolic Factors Unifies Hierarchy and Compositionality in Vision-Language Representation Learning | Takashi Matsubara | |
| 10010363-P | Feed-forward Human Performance Capture via Progressive Canonical Space Updates | Ehsan Adeli | |
| 10010379-P | XModBench: Benchmarking Cross-Modal Capabilities and Consistency in Omni-Language Models | XINGRUI WANG | |
| 10010384-P | HeuriGym: An Agentic Benchmark for LLM-Crafted Heuristics in Combinatorial Optimization | Yingheng Wang | |
| 10010394-P | Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management | LI MO | |
| 10010399-P | Deep FlexQP: Accelerated Nonlinear Programming via Deep Unfolding | Alex Oshin | |
| 10010407-P | Exploring Real-Time Super-Resolution: Benchmarking and Fine-Tuning for Streaming Content | Evgeney Bogatyrev | |
| 10010412-P | UrbanVerse: Scaling Urban Simulation by Watching City-Tour Videos | Mingxuan Liu | |
| 10010419-P | Exposing Weaknesses of Large Reasoning Models through Graph Algorithm Problems | Qifan ZHANG | |
| 10010423-P | Can SAEs reveal and mitigate racial biases of LLMs in healthcare? | Hiba Ahsan | |
| 10010425-P | VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation | Clark Peng | |
| 10010426-P | TurboBoA: Faster and Exact Attention-aware Quantization without Backpropagation | Yeo Jeong Park | |
| 10010446-P | Cautious Weight Decay | Jonathan Li | |
| 10010448-P | Distilling and Adapting: A Topology-Aware Framework for Zero-Shot Interaction Prediction in Multiplex Biological Networks | Alana Deng | |
| 10010451-P | HiPRAG: Hierarchical Process Rewards for Efficient Agentic Retrieval Augmented Generation | Peilin Wu | |
| 10010471-P | LLMs Struggle to Balance Reasoning and World Knowledge in Causal Narrative Understanding | Khurram Yamin | |
| 10010474-P | Soft-Masked Diffusion Language Models | Michael Hersche | |
| 10010478-P | RefineBench: Evaluating Refinement Capability of Language Models via Checklists | Young-Jun Lee | |
| 10010486-P | 3D Aware Region Prompted Vision Language Model | An-Chieh Cheng | |
| 10010489-P | InnoGym: Benchmarking the Innovation Potential of AI Agents | Shuofei Qiao | |
| 10010492-P | DRPO: Efficient Reasoning via Decoupled Reward Policy Optimization | Gang Li | |
| 10010497-P | Hilbert: Recursively Building Formal Proofs with Informal Reasoning | Sumanth Varambally | |
| 10010499-P | Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training Recipes | ZECHUN LIU | |
| 10010503-P | Benchmarking Bias Mitigation Toward Fairness Without Harm from Vision to LVLMs | Xuwei Tan | |
| 10010506-P | Detective SAM: Adaptive AI-Image Forgery Localization | Gert Lek | |
| 10010509-P | SelvaBox: A high-resolution dataset for tropical tree crown detection | Hugo Baudchon | |
| 10010515-P | Fisher-Rao Sensitivity for Out-of-Distribution Detection in Deep Neural Networks | Anthony Nguyen | |
| 10010519-P | Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration | Yanzhe Zhang | |
| 10010534-P | Harpoon: Generalised Manifold Guidance for Conditional Tabular Diffusion | Aditya Shankar | |
| 10010539-P | Bayesian Robust Cooperative Multi-Agent Reinforcement Learning Against Unknown Adversaries | Kiarash Kazari | |
| 10010550-P | Inter-Agent Relative Representations for Multi-Agent Option Discovery | Raul Steleac | |
| 10010554-P | Autonomous Functional Play with Correspondence-Driven Trajectory Warping | William Liang | |
| 10010560-P | Composition-Grounded Data Synthesis for Visual Reasoning | Xinyi Gu | |
| 10010570-P | Hyper-SET: Designing Transformers via Hyperspherical Energy Minimization | Yunzhe Hu | |
| 10010572-P | SuperF: Neural Implicit Fields for Multi-Image Super-Resolution | Sander Jyhne | |
| 10010584-P | Talking Points: Describing and Localizing Pixels | Matan Rusanovsky | |
| 10010587-P | Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification | Lukas Rauch | |
| 10010592-P | Generative Adversarial Post-Training Mitigates Reward Hacking in Live Human-AI Music Interaction | Yusong Wu | |
| 10010596-P | MergePRAG: Orthogonal Merging of Passage-experts for Multi-hop Parametric RAG | Seung-Hoon Na | |
| 10010597-P | Efficient Orthogonal Fine-Tuning with Principal Subspace Adaptation | Fei Wu | |
| 10010603-P | AutoQD: Automatic Discovery of Diverse Behaviors with Quality-Diversity Optimization | Saeed Hedayatian | |
| 10010614-P | Geometric Constraints for Small Language Models to Understand and Expand Scientific Taxonomies | Liri Fang | |
| 10010617-P | EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video | Ryan Hoque | |
| 10010624-P | AutoCode: LLMs as Problem Setters for Competitive Programming | Kaiyuan Liu | |
| 10010638-P | Towards Sustainable Investment Policies Informed by Opponent Shaping | Ayoub Echchahed | |
| 10010643-P | SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning | Zhenghai Xue | |
| 10010646-P | Train Once, Answer All: Many Pretraining Experiments for the Cost of One | Sebastian Bordt | |
| 10010655-P | TPDiff: Temporal Pyramid Video Diffusion Model | Lingmin Ran | |
| 10010665-P | Light Differentiable Logic Gate Networks | Till Aczel | |
| 10010688-P | Refine Now, Query Fast: A Decoupled Refinement Paradigm for Implicit Neural Fields | Tianyu Xiong | |
| 10010701-P | Learning to Reason for Hallucination Span Detection | Ting-Yao Hu | |
| 10010704-P | Detecting Invariant Manifolds in ReLU-Based RNNs | Alena Brändle | |
| 10010707-P | Entropy-preserving reinforcement learning | Aleksei Petrenko | |
| 10010715-P | MCbiF: Measuring Topological Autocorrelation in Multiscale Clusterings via 2-Parameter Persistent Homology | Juni Schindler | |
| 10010721-P | Strategic Planning and Rationalizing on Trees Make LLMs Better Debaters | Danqing Wang | |
| 10010723-P | MetaVLA: Unified Meta Co-Training for Efficient Embodied Adaptation | Zhantao Yang | |
| 10010726-P | Scalable Chain of Thoughts via Elastic Reasoning | Yuhui Xu | |
| 10010727-P | Self-Forcing++: Towards Minute-Scale High-Quality Video Generation | Jiaxing Cui | |
| 10010728-P | Learning Explicit Single-Cell Dynamics Using ODE Representations | Jan-Philipp von Bassewitz | |
| 10010730-P | EDINET-Bench: Evaluating LLMs on Complex Financial Tasks using Japanese Financial Statements | Issa Sugiura | |
| 10010735-P | Taming Curvature: Architecture Warm-up for Stable Transformer Training | Sameera chandimal ramasinghe | |
| 10010736-P | Rethinking Causal Mask Attention for Vision-Language Inference | Xiaohuan Pei | |
| 10010755-P | Panda: A pretrained forecast model for chaotic dynamics | Anthony Bao | |
| 10010757-P | The Softmax Bottleneck Does Not Limit the Probabilities of the Most Likely Tokens | David Jacobs | |
| 10010763-P | Does FLUX Already Know How to Perform Physically Plausible Image Composition? | Shilin Lu | |
| 10010764-P | Disentanglement of Variations with Multimodal Generative Modeling | Weiran Wang | |
| 10010765-P | Variation in Verification: Understanding Verification Dynamics in Large Language Models | Yefan Zhou | |
| 10010769-P | OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM | Hanrong Ye | |
| 10010778-P | Theoretical Analysis of Contrastive Learning under Imbalanced Data: From Training Dynamics to a Pruning Solution | Haixu Liao | |
| 10010789-P | EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging Benchmark | Deheng Zhang | |
| 10010792-P | Animating the Uncaptured: Humanoid Mesh Animation with Video Diffusion Models | Marc Benedi San Millan | |
| 10010797-P | On the Generalization Capacities of MLLMs for Spatial Intelligence | Quanhao Qian | |
| 10010806-P | PQGAN: Product-Quantised Image Representation for High-Quality Image Synthesis | Denis Zavadski | |
| 10010813-P | Verifying Chain-of-Thought Reasoning via its Computational Graph | Zheng Zhao | |
| 10010815-P | Adaptive Data-Knowledge Alignment in Genetic Perturbation Prediction | Lun Ai | |
| 10010833-P | FIRE: Frobenius-Isometry Reinitialization for Balancing the Stability–Plasticity Tradeoff | Isaac Han | |
| 10010837-P | IncVGGT: Incremental VGGT for Memory-Bounded Long-Range 3D Reconstruction | Yuzhe Fu | |
| 10010839-P | All That Glitters Is Not Gold: Key-Secured 3D Secrets within 3D Gaussian Splatting | yan ren | |
| 10010848-P | On the Convergence Behavior of Preconditioned Gradient Descent Toward the Rich Learning Regime | Shuai Jiang | |
| 10010849-P | ActiveCQ: Active Estimation of Causal Quantities | Erdun Gao | |
| 10010870-P | Mathesis: Towards Formal Theorem Proving from Natural Languages | Xuejun Yu | |
| 10010875-P | BioBO: Biology-informed Bayesian Optimization for Perturbation Design | Tianyu Cui | |
| 10010882-P | RADAR: Reasoning–Ability and Difficulty-Aware Routing in Language Models | Jack Wang | |
| 10010884-P | Beyond Length: Quantifying Long-Range Information for Long-Context LLM Pretraining Data | Haoran Deng | |
| 10010885-P | ASIDE: Architectural Separation of Instructions and Data in Language Models | Egor Zverev | |
| 10010899-P | Demystifying and Enhancing the Efficiency of Large Language Model Based Search Agents | Tiannuo Yang | |
| 10010906-P | TokenSeek: Memory Efficient Fine Tuning via Instance-Aware Token Ditching | Runjia Zeng | |
| 10010914-P | Reducing information dependency does not cause training data privacy. Adversarially non-robust features do. | Adam Breuer | |
| 10010917-P | InfoNCE Induces Gaussian Distribution | Roy Betser | |
| 10010934-P | On the Computational Limits of AI4S-RL : A Unified $\varepsilon$-$N$ Analysis | qili shen | |
| 10010941-P | On the Reasoning Abilities of Masked Diffusion Language Models | Anej Svete | |
| 10010955-P | NetArena: Dynamic Benchmarks for AI Agents in Network Automations | Yajie Zhou | |
| 10010956-P | Score-based Greedy Search for Structure Identification of Partially Observed Linear Causal Models | Xinshuai Dong | |
| 10010970-P | Prediction with Expert Advice under Local Differential Privacy | Ben Jacobsen | |
| 10010974-P | Counterfactual Explanations on Robust Perceptual Geodesics | Eslam Zaher | |
| 10010983-P | Can Transformers Really Do It All? On the Compatibility of Inductive Biases Across Tasks | Damien Teney | |
| 10010993-P | Beyond Ensembles: Simulating All-Atom Protein Dynamics in a Learned Latent Space | Aditya Sengar | |
| 10011003-P | Referring Layer Decomposition | Fangyi Chen | |
| 10011007-P | MARS-Sep: Multimodal-Aligned Reinforced Sound Separation | Zihan Zhang | |
| 10011008-P | (U)NFV: Supervised and Unsupervised Neural Finite Volume Methods for Solving Hyperbolic PDEs | Zhe Fu | |
| 10011012-P | Reforming the Mechanism: Editing Reasoning Patterns in LLMs with Circuit Reshaping | Lei Zhenyu | |
| 10011028-P | LD-EnSF: Synergizing Latent Dynamics with Ensemble Score Filters for Fast Data Assimilation with Sparse Observations | Pengpeng Xiao | |
| 10011032-P | CodeQuant: Unified Clustering and Quantization for Enhanced Outlier Smoothing in Low-Precision Mixture-of-Experts | Sai Qian Zhang | |
| 10011042-P | Brain-Semantoks: Learning Semantic Tokens of Brain Dynamics with a Self-Distilled Foundation Model | Sam Gijsen | |
| 10011056-P | PatchDNA: A Flexible and Biologically-Informed Alternative to Tokenization for DNA | Chantriolnt Andreas Kapourani | |
| 10011060-P | Robust Deep Reinforcement Learning against Adversarial Behavior Manipulation | Shojiro Yamabe | |
| 10011068-P | Optimas: Optimizing Compound AI Systems with Globally Aligned Local Rewards | Nurendra Choudhary | |
| 10011072-P | CryoLVM: Self-supervised Learning from Cryo-EM Density Maps with Large Vision Models | Weining Fu | |
| 10011089-P | Bridging Explainability and Embeddings: BEE Aware of Spuriousness | Cristian Daniel Paduraru | |
| 10011091-P | Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments | Romain Froger | |
| 10011094-P | Splat and Distill: Augmenting Teachers with Feed-Forward 3D Reconstruction For 3D-Aware Distillation | David Shavin | |
| 10011098-P | Analytica: Soft Propositional Reasoning for Robust and Scalable LLM-Driven Analysis | Kyle Richardson | |
| 10011127-P | From Static Benchmarks to Dynamic Protocol: Agent-Centric Text Anomaly Detection for Evaluating LLM Reasoning | Seungdong Yoa | |
| 10011132-P | ODEBrain: Continuous-Time EEG Graph for Modeling Dynamic Brain Networks | Haohui Jia | |
| 10011134-P | reAR: Rethinking Visual Autoregressive Models via Token-wise Consistency Regularization | He Qiyuan | |
| 10011140-P | Difference-Aware Retrieval Polices for Imitation Learning | Quinn Pfeifer | |
| 10011147-P | R-Zero: Self-Evolving Reasoning LLM from Zero Data | Chengsong Huang | |
| 10011159-P | Improving Code Localization with Repository Memory | Boshi Wang | |
| 10011163-P | A New Paradigm for Genome-wide DNA Methylation Prediction Without Methylation Input | Xiaoke Huang | |
| 10011182-P | UFO-4D: Unposed Feedforward 4D Reconstruction from Two Images | Junhwa Hur | |
| 10011186-P | A Scalable Distributed Framework for Multimodal GigaVoxel Image Registration | Vedant Zope | |
| 10011196-P | LVTINO: LAtent Video consisTency INverse sOlver for High Definition Video Restoration | Alessio Spagnoletti | |
| 10011203-P | Universal Inverse Distillation for Matching Models with Real-Data Supervision (No GANs) | Nikita Gushchin | |
| 10011207-P | ARMOR: High-Performance Semi-Structured Pruning via Adaptive Matrix Factorization | Lawrence Liu | |
| 10011208-P | CounselBench: A Large-Scale Expert Evaluation and Adversarial Benchmarking of Large Language Models in Mental Health Question Answering | Yahan Li | |
| 10011210-P | Deep Think with Confidence | Yichao Fu | |
| 10011213-P | Conformal Prediction for Long-Tailed Classification | Tiffany Ding | |
| 10011249-P | No Prior, No Leakage: Revisiting Reconstruction Attacks in Trained Neural Networks | Itay Safran | |
| 10011253-P | Adaptive Conformal Anomaly Detection with Time Series Foundation Models for Signal Monitoring. | Fearghal ODonncha | |
| 10011256-P | Understanding and Improving Hyperbolic Deep Reinforcement Learning | Thomas Lang | |
| 10011268-P | Architecture-Agnostic Test-Time Adaptation via Backprop-Free Embedding Alignment | MA Xiao | |
| 10011278-P | SHAPO: Sharpness-Aware Policy Optimization for Safe Exploration | Yann Pequignot | |
| 10011281-P | WebDS: An End-to-End Benchmark for Web-based Data Science | Ethan Hsu | |
| 10011287-P | From Data Statistics to Feature Geometry: How Correlations Shape Superposition | Lucas Prieto | |
| 10011290-P | MCP-SafetyBench: A Benchmark for Safety Evaluation of Large Language Models with Real-World MCP Servers | xuanjun zong | |
| 10011294-P | ULTRA-360: Unconstrained Dataset for Large-scale Temporal 3D Reconstruction across Altitudes and Omnidirectional Views | Xijun Liu | |
| 10011303-P | Enhancing Multi-Image Understanding through Delimiter Token Scaling | Minyoung Lee | |
| 10011307-P | Decoupling Dynamical Richness from Representation Learning: Towards Practical Measurement | Yoonsoo Nam | |
| 10011314-P | Minimax Rates for Learning Pairwise Interactions in Attention-Style Models | Shai Zucker | |
| 10011331-P | BoreaRL: A Multi-Objective Reinforcement Learning Environment for Climate-Adaptive Boreal Forest Management | Kevin Bradley Dsouza | |
| 10011334-P | Seeing What´s Wrong: A Trajectory-Guided Approach to Caption Error Detection | Gabriel Afriat | |
| 10011343-P | EMFuse: Energy-based Model Fusion for Decision Making | Kejie He | |
| 10011344-P | Directional Textual Inversion for Personalized Text-to-Image Generation | NaHyeon Park | |
| 10011347-P | Learning Self-Critiquing Mechanisms for Region-Guided Chest X-Ray Report Generation | Sixing Yan | |
| 10011374-P | Evaluating Intuitive Physics Understanding in Video Diffusion Models via Likelihood Preference | Jianhao Yuan | |
| 10011376-P | Task Tokens: A Flexible Approach to Adapting Behavior Foundation Models | Ron Vainshtein | |
| 10011381-P | Using maximal information auxiliary variables to improve synthetic data generation based on TabPFN foundation models | Elias Chaibub Neto | |
| 10011382-P | DES-LOC: Desynced Low Communication Adaptive Optimizers for Foundation Models | Alexandru-Andrei Iacob | |
| 10011390-P | Semantic Regexes: Auto-Interpreting LLM Features with a Structured Language | Angie Boggust | |
| 10011396-P | Learning to Answer from Correct Demonstrations | Gene Li | |
| 10011409-P | MT-DAO: Multi-Timescale Distributed Adaptive Optimizers with Local Updates | Alexandru-Andrei Iacob | |
| 10011412-P | Ringleader ASGD: The First Asynchronous SGD with Optimal Time Complexity under Data Heterogeneity | Artavazd Maranjyan | |
| 10011415-P | Predictability Shapes Adaptation: An Evolutionary Perspective on Modes of Learning in Transformers | Alexander Ku | |
| 10011417-P | CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models | Runpeng Dai | |
| 10011420-P | Flow Autoencoders are Effective Protein Tokenizers | Rohit Dilip | |
| 10011425-P | Understanding the Implicit Biases of Design Choices for Time Series Foundation Models | Boran Han | |
| 10011437-P | Quantization-Aware Diffusion Models For Maximum Likelihood Training | Shohei Taniguchi | |
| 10011440-P | Learning Robust Intervention Representations with Delta Embeddings | Panagiotis Alimisis | |
| 10011448-P | STITCH: Simultaneous Thinking and Talking with Chunked Reasoning for Spoken Language Models | Xiaofei Wang | |
| 10011451-P | Lean Finder: Semantic Search for Mathlib That Understands User Intents | Jialin Lu | |
| 10011460-P | Anatomy-aware Representation Learning for Medical Ultrasound | Seok-Hwan Oh | |
| 10011468-P | Multiverse Mechanica: Testing World Models´ Ability to Learn Mechanics via Counterfactual Reasoning | Robert Ness | |
| 10011469-P | Scaling Generalist Data-Analytic Agents | Shuofei Qiao | |
| 10011471-P | High-dimensional limit theorems for SGD: Momentum and Adaptive Step-sizes | Taj Jones-McCormick | |
| 10011475-P | A foundation model with multi-variate parallel attention to generate neuronal activity | Francesco Carzaniga | |
| 10011482-P | Trinity: An Evolved LLM Coordinator | Jinglue Xu | |
| 10011486-P | Characterizing Deep Research: A Benchmark and Formal Definition | Abhinav Java | |
| 10011491-P | HATSolver: Learning Gröbner Bases with Hierarchical Attention Transformers | Mohamed Malhou | |
| 10011496-P | Relatron: Automating Relational Machine Learning over Relational Databases | Jian Zhang | |
| 10011503-P | Protein Structure Tokenization via Geometric Byte Pair Encoding | Michael Sun | |
| 10011505-P | Disentangled Hierarchical VAE for 3D Human-Human Interaction Generation | Zichen Geng | |
| 10011506-P | Towards Personalized Deep Research: Benchmarks and Evaluations | Shuofei Qiao | |
| 10011507-P | Universal Beta Splatting | Zhongpai Gao | |
| 10011510-P | RAVENEA: A Benchmark for Multimodal Retrieval-Augmented Visual Culture Understanding | Jiaang Li | |
| 10011512-P | 3DGEER: 3D Gaussian Rendering Made Exact and Efficient for Generic Cameras | Zixun Huang | |
| 10011515-P | Learning a distance measure from the information-estimation geometry of data | Guy Ohayon | |
| 10011528-P | CyclicReflex: Improving Reasoning Models via Cyclical Reflection Token Scheduling | Chongyu Fan | |
| 10011531-P | Sharpness-Aware Minimization in Logit Space Efficiently Enhances Direct Preference Optimization | haocheng luo | |
| 10011539-P | Data-Centric Lessons To Improve Speech-Language Pretraining | Vishaal Udandarao | |
| 10011544-P | TandemFoilSet: Datasets for Flow Field Prediction of Tandem-Airfoil Through the Reuse of Single Airfoils | Wei Xian Lim | |
| 10011548-P | Diverse and Sparse Mixture-of-Experts for Causal Subgraph–Based Out-of-Distribution Graph Learning | Jerry Sun | |
| 10011554-P | LD-MoLE: Learnable Dynamic Routing for Mixture of LoRA Experts | Yuan Zhuang | |
| 10011558-P | PRISM-Physics: Causal DAG-Based Process Evaluation for Physics Reasoning | Wanjia Zhao | |
| 10011559-P | Cultivating Pluralism In Algorithmic Monoculture: The Community Alignment Dataset | Smitha Milli | |
| 10011560-P | Unified Vision–Language Modeling via Concept Space Alignment | Yifu Qiu | |
| 10011561-P | Information-Theoretic Membership Inference for Granular Quantification of Memorization | Jiashu Tao | |
| 10011563-P | ReIn: Conversational Error Recovery with Reasoning Inception | Takyoung Kim | |
| 10011574-P | Measuring Uncertainty Calibration | Kamil Ciosek | |
| 10011579-P | IVC-Prune: Revealing the Implicit Visual Coordinates in LVLMs for Vision Token Pruning | Zhichao Sun | |
| 10011581-P | ReSplat: Degradation-agnostic Feed-forward Gaussian Splatting via Self-guided Residual Diffusion | Youngho Yoon | |
| 10011591-P | MaskInversion: Localized Embeddings via Optimization of Explainability Maps | Walid Bousselham | |
| 10011604-P | ALM-MTA: Front-Door Causal Multi-Touch Attribution Method for Creator-Ecosystem Optimization | Yuguang Liu | |
| 10011607-P | CLAP: Unsupervised 3D Representation Learning for Fusion 3D Perception via Curvature Sampling and Prototype Learning | Runjian Chen | |
| 10011619-P | Is Finer Better? The Limits of Microscaling Formats in Large Language Models | Andrea Fasoli | |
| 10011623-P | MomaGraph: State-Aware Unified Scene Graphs with Vision-Language Models for Embodied Task Planning | Yuanchen Ju | |
| 10011627-P | Rethinking JEPA: Compute-Efficient Video Self-Supervised Learning with Frozen Teachers | Vimal Thilak | |
| 10011628-P | FATE: A Formal Benchmark Series for Frontier Algebra of Multiple Difficulty Levels | He Wanyi | |
| 10011630-P | Robust Generalized Schr\"{o}dinger Bridge via Sparse Variational Gaussian Processes | Minyoung Kim | |
| 10011664-P | Belief-Based Offline Reinforcement Learning for Delay-Robust Policy Optimization | Sinong Zhan | |
| 10011668-P | Efficient Testing for Correlation Clustering: Improved Algorithms and Optimal Bounds | Songhua He | |
| 10011670-P | Diffusion & Adversarial Schrödinger Bridges via Iterative Proportional Markovian Fitting | Sergei Kholkin | |
| 10011687-P | Target-Aware Video Diffusion Models | Taeksoo Kim | |
| 10011702-P | Chessformer: A Unified Architecture for Chess Modeling | Daniel Monroe | |
| 10011714-P | Hyden: A Hybrid Dual-Path Encoder for Monocular Geometry of High-resolution Images | Marc Mapeke | |
| 10011718-P | Relational Graph Transformer | Charilaos Kanatsoulis | |
| 10011726-P | Learn-to-Distance: Distance Learning for Detecting LLM-Generated Text | Jin Zhu | |
| 10011733-P | EnvSocial-Diff: A Diffusion-Based Crowd Simulation Model with Environmental Conditioning and Individual- Group Interaction | Bingxue Zhao | |
| 10011734-P | Value Flows | Perry Dong | |
| 10011737-P | SOSBENCH: Benchmarking Safety Alignment on Scientific Knowledge | Luyao Niu | |
| 10011747-P | Leveraging Data to Say No: Memory Augmented Plug-and-Play Selective Prediction | Aditya Sarkar | |
| 10011778-P | Charts Are Not Images: On the Challenges of Scientific Chart Editing | Yue Zhao | |
| 10011781-P | Deep SPI: Safe Policy Improvement via World Models | Florent Delgrange | |
| 10011782-P | Feedback-driven recurrent quantum neural network universality | Lukas Gonon | |
| 10011793-P | pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation | Hao Tan | |
| 10011796-P | Stochastic Neural Networks for Causal Inference with Missing Confounders | Yaxin Fang | |
| 10011804-P | Latent Denoising Makes Good Visual Tokenizers | Yue Wang | |
| 10011807-P | Adaptive Conformal Guidance for Learning under Uncertainty | Rui Liu | |
| 10011808-P | Cyber-Zero: Training Cybersecurity Agents without Runtime | Dingmin Wang | |
| 10011817-P | RM-R1: Reward Modeling as Reasoning | Gaotang Li | |
| 10011819-P | Generalised Flow Maps for Few-Step Generative Modelling on Riemannian Manifolds | Oscar Davis | |
| 10011820-P | Covariate-Guided Clusterwise Linear Regression for Generalization to Unseen Data | Dohyun Bu | |
| 10011821-P | Towards Persistent Noise-Tolerant Active Learning of Regular Languages with Class Query | Alvaro Velasquez | |
| 10011823-P | Code World Models for General Game Playing | Carter Wendelken | |
| 10011824-P | ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference | Yesheng Liang | |
| 10011829-P | CoT-RVS: Zero-Shot Chain-of-Thought Reasoning Segmentation for Videos | Shiu-Hong Kao | |
| 10011867-P | Emergent Discrete Controller Modules for Symbolic Planning in Transformers | S M Rafiuddin | |
| 10011872-P | Dual-Solver: A Generalized ODE Solver for Diffusion Models with Dual Prediction | Soochul Park | |
| 10011873-P | Semantic Uncertainty Quantification of Hallucinations in LLMs: A Quantum Tensor Network Based Method | pragatheeswaran vipulanandan | |
| 10011874-P | Adversarially Pretrained Transformers may be Universally Robust In-Context Learners | Soichiro Kumano | |
| 10011878-P | The Deleuzian Representation Hypothesis | Clément Cornet | |
| 10011881-P | Sublinear Time Quantum Algorithm for Attention Approximation | Lichen Zhang | |
| 10011883-P | DPad: Efficient Diffusion Language Models with Suffix Dropout | Chiyue Wei | |
| 10011885-P | Common Corpus: The Largest Collection of Ethical Data for LLM Pre-Training | Pavel Chizhov | |
| 10011888-P | Draft-based Approximate Inference for LLMs | Kevin Galim | |
| 10011889-P | Personalized Feature Translation for Expression Recognition: An Efficient Source-Free Domain Adaptation Method | Masoumeh Sharafi | |
| 10011890-P | Diffusion Transformers with Representation Autoencoders | Boyang Zheng | |
| 10011892-P | Trained on Tokens, Calibrated on Concepts: The Emergence of Semantic Calibration in LLMs | Adam Golinski | |
| 10011906-P | UltraGauss: Ultrafast Gaussian Reconstruction of 3D Ultrasound Volumes | Mark Eid | |
| 10011915-P | Training-Free Determination of Network Width via Neural Tangent Kernel | Tatsumi Sunada | |
| 10011939-P | Bandits with Single-Peaked Preferences and Limited Resources | Gur Keinan | |
| 10011946-P | Proving the Limited Scalability of Centralized Distributed Optimization via a New Lower Bound Construction | Alexander Tyurin | |
| 10011952-P | Context and Diversity Matter: The Emergence of In-Context Learning in World Models | Pengtao Shao | |
| 10011967-P | Spatially Informed Autoencoders for Interpretable Visual Representation Learning | Dominik Sturm | |
| 10011969-P | Visual Compositional Tuning | Xindi Wu | |
| 10011974-P | ImageDoctor: Diagnosing Text-to-Image Generation via Grounded Image Reasoning | Jiang Liu | |
| 10012080-P | Learning to Maximize Rewards via Reaching Goals | Chongyi Zheng | |
| 10012083-P | The 99% Success Paradox: When Near-Perfect Retrieval Equals Random Selection | Michael Thot | |
| 10012095-P | Destruction is a General Strategy to Learn Generation; Diffusion´s Strength is to Take it Seriously; Exploration is the Future | Pierre-André Noël | |
| 10012097-P | Dynamic Parameter Reuse Augments Reasoning via Latent Chain of Thought | Kaitlin Maile | |
| 10012101-P | The human knowledge loophole in the ´bitter lesson´ for LLMs | Anna Rogers | |
| 10012106-P | The Adversarial Conditioning Paradox: Why Attacked Inputs Are More Stable, Not Less | Khazretgali Sapenov | |
| 10014017-P | A Case for Library-Level k-Means Binning in Histogram Gradient-Boosted Trees | Asher Labovich | |
| 10014020-P | MobileCLIP2: Improving Multi-Modal Reinforced Training | Fartash Faghri | |
| 10014022-P | Generalized Compressed Sensing for Image Reconstruction with Diffusion Probabilistic Models | Ling-Qi Zhang | |
| 10014024-P | LC-PLM: Long-context Protein Language Modeling Using Bidirectional Mamba with Shared Projection Layers | Yingheng Wang | |
| 10014025-P | On the stability of gradient descent with second order dynamics for time-varying cost functions | Travis Gibson | |
| 10014028-P | Temporal Test-Time Adaptation with State-Space Models | Mona Schirmer | |
| 10014031-P | Faster Diffusion Through Temporal Attention Decomposition | Haozhe Liu | |
| 10014032-P | FlashAttention on a Napkin: A Diagrammatic Approach to Deep Learning IO-Awareness | Vincent Abbott | |
| 10014056-P | Adaptive Mesh Quantization for Neural PDE Solvers | Winfried van den Dool | |
| 10014060-P | Training Dynamics of Learning 3D-Rotational Equivariance | Max Shen | |
| 10014062-P | Variational Pseudo Marginal Methods for Jet Reconstruction in Particle Physics | Antonio Moretti | |
April 23-27, 2026 Rio de Janeiro, Brazil

Digital Object Identifier. Official code used to identify documents published on internet; similar to ISBN for books. You may use this code to reference your poster in future scientific publications or CVs. It can be found from anywhere in the world. To find the poster page, log onto www.medra.org and enter the DOI, or enter in your internet browser https://dx.doi.org/ followed by the DOI string asigned to your congress. |
||||
|
|