April 23-27, 2026 Rio de Janeiro, Brazil
| 10006453-P | Symmetry-Aware Bayesian Optimization via Max Kernels | Anthony Bardou | |
| 10006469-P | OmniText: A Training-Free Generalist for Controllable Text-Image Manipulation | Samuel Teodoro | |
| 10006498-P | Entropy-Guided Dynamic Tokens for Graph-LLM Alignment in Molecular Understanding | Zihao Jing | |
| 10006525-P | Incorporating Expert Priors into Bayesian Optimization via Dynamic Mean Decay | Chongqi Qu | |
| 10006587-P | Hot PATE: Private Aggregation of Distributions for Diverse Tasks | Edith Cohen | |
| 10006652-P | Traceable Black-Box Watermarks For Federated Learning | Olivera Kotevska | |
| 10006682-P | SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training | Jianyi Wang | |
| 10006756-P | ConvT3: Structured State Kernels for Convolutional State Space Models | Jaeyoung Hong | |
| 10006764-P | Leveraging Pretrained Knowledge at Inference Time: LoRA-Gated Contrastive Decoding for Multilingual Factual Language Generation in Adapted LLMs | Gwangseon Jang | |
| 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 | |
| 10006836-P | Multi-Head Low-Rank Attention | Songtao Liu | |
| 10006880-P | FS-DFM: Fast and Accurate Long Text Generation with Few-Step Diffusion Language Models | Dominic Culver | |
| 10006917-P | PluriHarms: Benchmarking the Full Spectrum of Human Judgments on AI Harm | Jing-Jing Li | |
| 10006921-P | The Seismic Wavefield Common Task Framework | Alexey Yermakov | |
| 10006958-P | Federated Learning with Profile Mapping under Distribution Shifts and Drifts | Dario Fenoglio | |
| 10006990-P | Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation | Xuanchi Ren | |
| 10007015-P | SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs | Dachuan Shi | |
| 10007028-P | STaMP: Sequence Transformation and Mixed Precision for Low-Precision Activation Quantization | Marco Federici | |
| 10007045-P | Attention Smoothing Is All You Need For Unlearning | Dongxiao Zhu | |
| 10007064-P | Explaining Grokking and Information Bottleneck through Neural Collapse Emergence | Keitaro Sakamoto | |
| 10007118-P | A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image Features | Axel Barroso-Laguna | |
| 10007122-P | From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning | Chen Shani | |
| 10007169-P | Monotone Near-Zero-Sum Games | Ruichen Luo | |
| 10007188-P | Do LLM Agents Know How to Ground, Recover, and Assess? A Benchmark for Epistemic Competence in Information-Seeking Agents | Bing Luo | |
| 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 | |
| 10007354-P | Adaptive Width Neural Networks | Henrik Christiansen | |
| 10007403-P | MIRA: Memory-Integrated Reinforcement Learning Agent with Limited LLM Guidance | Narjes Nourzad | |
| 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 | |
| 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 | |
| 10007495-P | VLMgineer: Vision-Language Models as Robotic Toolsmiths | Tianyu Li | |
| 10007676-P | Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modeling | Tal Daniel | |
| 10007757-P | DAVE: A VLM Vision Encoder for Document Understanding and Web Agents | Hang Hua | |
| 10007785-P | Frozen Policy Iteration: Computationally Efficient RL under Linear $Q^{\pi}$ Realizability for Deterministic Dynamics | Yijing Ke | |
| 10007809-P | TGM: A Modular and Efficient Library for Machine Learning on Temporal Graphs | Jacob Chmura | |
| 10007848-P | CaTS: Calibrated Test-Time Scaling for Efficient LLM Inference | Chengsong Huang | |
| 10007865-P | BIRD: Behavior Induction via Representation-structure Distillation | Galen Pogoncheff | |
| 10007882-P | Dropping Just a Handful of Preferences Can Change Top Large Language Model Rankings | Jenny Huang | |
| 10007919-P | Perception-Aware Policy Optimization for Multimodal Reasoning | Zhenhailong Wang | |
| 10007923-P | Difference Predictive Coding for Training Spiking Neural Networks | Ville Karlsson | |
| 10007934-P | Tab-MIA: A Benchmark Dataset for Membership Inference Attacks on Tabular Data in LLMs | Eyal German | |
| 10007950-P | OSCAR: Online Soft Compression for RAG | Stephane Clinchant | |
| 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 | |
| 10008045-P | Self-Speculative Decoding Accelerates Lossless Inference in Any-Order and Any-Subset Autoregressive Models | Gabe Guo | |
| 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 | |
| 10008106-P | STEM: SCALING TRANSFORMERS WITH EMBEDDING MODULES | ZECHUN Liu | |
| 10008132-P | TAVAE: A VAE with Adaptable Priors Explains Contextual Modulation in the Visual Cortex | Balázs Meszéna | |
| 10008198-P | Learning Survival Distributions with Individually Calibrated Asymmetric Laplace Distribution | Ricardo Henao | |
| 10008247-P | Scaling Sequence-to-Sequence Generative Neural Rendering | Shikun Liu | |
| 10008278-P | Latent Veracity Inference for Identifying Errors in Stepwise Reasoning | Jean-Pierre Falet | |
| 10008285-P | SLAP: Shortcut Learning for Abstract Planning | Yijie Liu | |
| 10008370-P | Initialization Schemes for Kolmogorov–Arnold Networks: An Empirical Study | Spyros Rigas | |
| 10008429-P | Closing the Gap Between Text and Speech Understanding in LLMs | Santiago Cuervo | |
| 10008485-P | Boosting Medical Visual Understanding From Multi-Granular Language Learning | Zihan Li | |
| 10008512-P | Overshoot and Shrinkage in Classifier-Free Guidance: From Theory to Practice | Krunoslav Lehman Pavasovic | |
| 10008624-P | Is In-Context Learning Learning? | Adrian de Wynter | |
| 10008637-P | Domain Expansion: A Latent Space Construction Framework for Multi-Task Learning | Chi-Yao Huang | |
| 10008655-P | Understanding Transformers for Time Series: Rank Structure, Flow-of-ranks, and Compressibility | Boran Han | |
| 10008682-P | SARM: Stage-Aware Reward Modeling for Long Horizon Robot Manipulation | Qianzhong Chen | |
| 10008706-P | Exploring Synthesizable Chemical Space with Iterative Pathway Refinements | Seul Lee | |
| 10008710-P | Dual Goal Representations | Seohong Park | |
| 10008731-P | LearnIR: Learnable Posterior Sampling for Real-World Image Restoration | Yihang Bao | |
| 10008737-P | Best-of-Majority: Minimax-Optimal Strategy for Pass@k Inference Scaling | Xuheng Li | |
| 10008761-P | Layerwise Federated Learning for Heterogeneous Quantum Clients using Quorus | Jason Han | |
| 10008774-P | Multilingual Routing in Mixture-of-Experts | Lucas Bandarkar | |
| 10008853-P | Transformers are Inherently Succinct | Pascal Bergsträer | |
| 10008867-P | Let´s Split Up: Zero-Shot Classifier Edits for Fine-Grained Video Understanding | Kaiting Liu | |
| 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 | |
| 10008900-P | HYPER: A Foundation Model for Inductive Link Prediction with Knowledge Hypergraphs | Xingyue Huang | |
| 10008938-P | More Thought, Less Accuracy? On the Dual Nature of Reasoning in Vision-Language Models | Xinyu Tian | |
| 10008984-P | QVGen: Pushing the Limit of Quantized Video Generative Models | Yushi Huang | |
| 10008996-P | Transitive RL: Value Learning via Divide and Conquer | Seohong Park | |
| 10009034-P | RESFL: An Uncertainty-Aware Framework for Responsible Federated Learning by Balancing Privacy, Fairness and Utility | Dawood Wasif | |
| 10009052-P | A Unifying Framework for Causal Imitation Learning with Hidden Confounders | Daqian Shao | |
| 10009100-P | Routing, Cascades, and User Choice for LLMs | Rafid Mahmood | |
| 10009182-P | Summaries as Centroids for Interpretable and Scalable Text Clustering | Jairo Diaz-Rodriguez | |
| 10009235-P | Synthesizing High-Quality Visual Question Answering from Medical Documents with Generator-Verifier LMMs | Xiaoke Huang | |
| 10009276-P | Learning Retrieval Models with Sparse Autoencoders | Stephane Clinchant | |
| 10009287-P | Correlated Policy Optimization in Multi-Agent Subteams | Qi Zhang | |
| 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 | |
| 10009378-P | VeriTrail: Closed-Domain Hallucination Detection with Traceability | Dasha Metropolitansky | |
| 10009387-P | Asynchronous Policy Gradient Aggregation for Efficient Distributed Reinforcement Learning | Alexander Tyurin | |
| 10009421-P | DeNOTS: Stable Deep Neural ODEs for Time Series | Ilya Kuleshov | |
| 10009432-P | Sci2Pol: Evaluating and Fine-tuning LLMs on Scientific-to-Policy Brief Generation | Weimin Wu | |
| 10009483-P | LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generation | Ingyu Seong | |
| 10009531-P | Exploring State-Space Models for Data-Specific Neural Representations | Jinsung Lee | |
| 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 | |
| 10009616-P | GAGA: Gaussianity-Aware Gaussian Approximation for Efficient 3D Molecular Generation | Jingxiang Qu | |
| 10009767-P | DepthLM: Metric Depth from Vision Language Models | Zhipeng Cai | |
| 10009876-P | The Geometry of LLM Quantization: GPTQ as Babai´s Nearest Plane Algorithm | Jiale Chen | |
| 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 | |
| 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 | |
| 10010287-P | AceReason-Nemotron 1.1: Advancing Math and Code Reasoning through SFT and RL Synergy | Zihan Liu | |
| 10010407-P | Exploring Real-Time Super-Resolution: Benchmarking and Fine-Tuning for Streaming Content | Evgeney Bogatyrev | |
| 10010425-P | VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation | Clark Peng | |
| 10010448-P | Distilling and Adapting: A Topology-Aware Framework for Zero-Shot Interaction Prediction in Multiplex Biological Networks | Alana Deng | |
| 10010492-P | DRPO: Efficient Reasoning via Decoupled Reward Policy Optimization | Gang Li | |
| 10010499-P | Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training Recipes | ZECHUN LIU | |
| 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 | |
| 10010592-P | Generative Adversarial Post-Training Mitigates Reward Hacking in Live Human-AI Music Interaction | Yusong Wu | |
| 10010597-P | Efficient Orthogonal Fine-Tuning with Principal Subspace Adaptation | Fei Wu | |
| 10010730-P | EDINET-Bench: Evaluating LLMs on Complex Financial Tasks using Japanese Financial Statements | Issa Sugiura | |
| 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 | |
| 10010789-P | EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging Benchmark | Deheng Zhang | |
| 10010797-P | On the Generalization Capacities of MLLMs for Spatial Intelligence | Quanhao Qian | |
| 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 | |
| 10010837-P | IncVGGT: Incremental VGGT for Memory-Bounded Long-Range 3D Reconstruction | Yuzhe Fu | |
| 10010906-P | TokenSeek: Memory Efficient Fine Tuning via Instance-Aware Token Ditching | Runjia Zeng | |
| 10011007-P | MARS-Sep: Multimodal-Aligned Reinforced Sound Separation | Zihan Zhang | |
| 10011072-P | CryoLVM: Self-supervised Learning from Cryo-EM Density Maps with Large Vision Models | Weining Fu | |
| 10011147-P | R-Zero: Self-Evolving Reasoning LLM from Zero Data | Chengsong Huang | |
| 10011163-P | A New Paradigm for Genome-wide DNA Methylation Prediction Without Methylation Input | Xiaoke Huang | |
| 10011207-P | ARMOR: High-Performance Semi-Structured Pruning via Adaptive Matrix Factorization | Lawrence 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 | |
| 10011331-P | BoreaRL: A Multi-Objective Reinforcement Learning Environment for Climate-Adaptive Boreal Forest Management | Kevin Bradley Dsouza | |
| 10011347-P | Learning Self-Critiquing Mechanisms for Region-Guided Chest X-Ray Report Generation | Sixing Yan | |
| 10011425-P | Understanding the Implicit Biases of Design Choices for Time Series Foundation Models | Boran Han | |
| 10011440-P | Learning Robust Intervention Representations with Delta Embeddings | Panagiotis Alimisis | |
| 10011471-P | High-dimensional limit theorems for SGD: Momentum and Adaptive Step-sizes | Taj Jones-McCormick | |
| 10011505-P | Disentangled Hierarchical VAE for 3D Human-Human Interaction Generation | Zichen Geng | |
| 10011507-P | Universal Beta Splatting | Zhongpai Gao | |
| 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 | |
| 10011579-P | IVC-Prune: Revealing the Implicit Visual Coordinates in LVLMs for Vision Token Pruning | Zhichao Sun | |
| 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 | |
| 10011726-P | Learn-to-Distance: Distance Learning for Detecting LLM-Generated Text | Jin Zhu | |
| 10011778-P | Charts Are Not Images: On the Challenges of Scientific Chart Editing | Yue Zhao | |
| 10011782-P | Feedback-driven recurrent quantum neural network universality | Lukas Gonon | |
| 10011817-P | RM-R1: Reward Modeling as Reasoning | Gaotang Li | |
| 10011829-P | CoT-RVS: Zero-Shot Chain-of-Thought Reasoning Segmentation for Videos | Shiu-Hong Kao | |
| 10011873-P | Semantic Uncertainty Quantification of Hallucinations in LLMs: A Quantum Tensor Network Based Method | pragatheeswaran vipulanandan | |
| 10011881-P | Sublinear Time Quantum Algorithm for Attention Approximation | Lichen Zhang | |
| 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 | |
| 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 | |
| 10014060-P | Training Dynamics of Learning 3D-Rotational Equivariance | Max Shen | |
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. |
||||
|
|