April 26 and 27, 2026 Rio de Janeiro, Brazil
| 10-P | Memory-Efficient Multilingual Embeddings with a Diffusion-LM Backbone | Sarah Eslami | |
| 11-P | Who Prefers Structured Reasoning? AI Judges Do, Domain Experts Split | Jordan Rubin | |
| 13-P | BankerToolBench: Evaluating AI Agents in End-to-End Investment Banking Workflows | Elaine Lau | |
| 14-P | Distributional Machine Unlearning via Selective Data Removal | Youssef Allouah | |
| 15-P | One Language, Two Scripts: Probing Script Invariance in LLM Concept Representations | Sripad Karne | |
| 17-P | STOCHASTOK: Improving Fine-Grained Subword Understanding in LLMs | Anya Sims | |
| 72-P | MONITORING ACCESS TO PIPED WATER AND SANITATION INFRASTRUCTURE IN AFRICA AT DISAGGREGATED SCALES USING SATELLITE IMAGERY AND ELF-SUPERVISED LEARNING | Othmane Echchabi | |
| 11111-P | Understanding Representation Gaps Across Scales In Tropical Tree Species Classification From Drone Imagery | Sulagna Saha | |
| 21113-P | Semantic Self-Distillation for Language Model Uncertainty | Edward Phillips | |
| 21148-P | WebPII: Benchmarking Visual PII Detection for Computer-Use Agents | Nathan J Zhao | |
| 10012253-P | Adaptive Test-Time Compute Allocation for Neural PDE Solvers | Ben Jenkins | |
| 10012257-P | Learning Mesh-Free Discrete Differential Operators with Self-Supervised Graph Neural Networks | Lucas Gerken Starepravo | |
| 10012261-P | LEARNING EMBEDDINGS OF NON-LINEAR PDES: THE BURGERS´ EQUATION | Leonid Sarieddine | |
| 10012263-P | Representation Learning for Spatiotemporal Physical Systems | Helen Qu | |
| 10012277-P | Accelerating PINN Training via RL-based Adaptive Loss Control | Andrei Zakharov | |
| 10012278-P | From Large-Scale Winds to Urban Decision Making: A Cross-Scale Framework for Wind-Aware UAV Navigation | Liangzhu Wang | |
| 10012282-P | Learning Heat-Based Equations in Self-Similar Variables | Shihao Wang | |
| 10012301-P | (U)NFV: (Un)Supervised Neural Finite Volume Methods for Solving Hyperbolic PDEs | Alexi Canesse | |
| 10012310-P | Neural Bloch Eigensolver for Honeycomb Lattices | Haaris Mian | |
| 10012319-P | Causal Field Theory: Mechanistic Interpretability for Spatio-Temporal Biological Systems | Arash Mehrjou | |
| 10012326-P | Momentum-Accelerated Structured Preconditioning for Physics-Informed Neural Networks | Indra Priyadarsini | |
| 10012468-P | MobileMem: Evaluating Long-Horizon Memory for Language Agents in Real-World Mobile Environments | Shuofei Qiao | |
| 10012471-P | Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Training for LLM Agents | Lin Guan | |
| 10012494-P | AIF-GEN: Open-Source Platform and Synthetic Dataset Suite for Reinforcement Learning on Large Language Models | Shahrad Mohammadzadeh | |
| 10012502-P | BEYOND SYNTAX: ACTION SEMANTICS LEARNING FOR APP AGENTS | Dezhao Luo | |
| 10012512-P | OceanGym: Evaluating Language-Grounded Embodied Agents in Underwater Environments | Shuofei Qiao | |
| 10012516-P | TSR: Trajectory-Search Rollouts for Multi-Turn RL of LLM Agents | Farhan Ahmed | |
| 10012551-P | Beyond Reward Maximization: Evaluating the Diversity of Trajectories in Reinforcement Learning with Temporal Vendi Score | Tom Stanic | |
| 10012562-P | DéjŕQ: Open-Ended Evolution of Diverse, Learnable and Verifiable Problems | Willem Röpke | |
| 10012608-P | RocqSmith: Can Automatic Optimization Forge Better Proof Agents? | Andrei Kozyrev | |
| 10012622-P | Identifying and Mitigating Reasoning Errors in VLM Verifiers via Activation Decomposition | Joonhyuk Cha | |
| 10012641-P | Benchmarking Code Verification Strategies with LLMs-as-a-judge | Tom Sherborne | |
| 10012642-P | Do LLMs Game Formalization? Evaluating Faithfulness in Logical Reasoning | Kyuhee Kim | |
| 10012733-P | Operator-Consistent Graph Neural Networks for Learning Diffusion Dynamics on Irregular Meshes | Andrew Hands | |
| 10012736-P | Can Graph Foundation Models Generalize Over Architecture? | Benjamin Gutteridge | |
| 10012737-P | Lift me up: the impact of liftings on hypergraph neural networks | Marco Montagna | |
| 10012741-P | RECYCLE NET: CYCLE-AWARE, FEATURE-FREE GNN FOR COMMUNITY DETECTION | Caleb Fernandes | |
| 10012754-P | TPR-Attention for Combinatorial Generalization | Melisa Civelekoglu | |
| 10012758-P | Sparse Concept Anchoring for Interpretable and Controllable Neural Representations | Sandy Fraser | |
| 10012760-P | Metric multi-dimensional scaling for longitudinal data embeddings in pharmacometrics | Lucas Pereira | |
| 10012782-P | Symmetry, Gauss-Newton, and Whitening in Neural Network Optimization | Vedanth Nilabh | |
| 10012791-P | Semantic-Anchored, Class Variance-Optimized Clustering for Robust Semi-Supervised Few-Shot Learning | Pratik Mazumder | |
| 10012800-P | Solvaformer: Minimizing Geometric Redundancy for Scalable Solubility Prediction | Michael Bailey | |
| 10012806-P | On the Geometry of Analogical Reasoning in Latent Space | Oleg Dats | |
| 10012813-P | k-Maximum Inner Product Attention for Graph Transformers and the Expressive Power of GraphGPS | Jonas De Schouwer | |
| 10013196-P | Can Multi-Modal LLMs Provide Live Step-by-Step Task Guidance? | Roland Memisevic | |
| 10013203-P | Depth Over Specialization in Small Multimodal Transformers | Jakub Mroz | |
| 10013211-P | Towards Mitigating Hallucinations in Large Vision-Language Models by Refining Textual Embeddings | Aakriti Agrawal | |
| 10013214-P | SCOPE: Selective Cross-modal Orchestration of Visual Perception Experts | Perouz Taslakian | |
| 10013219-P | VisGym: Diverse, Customizable, Scalable Environments for Multimodal Agents | Zirui Wang | |
| 10013232-P | CARPE: Context-Aware Image Representation Prioritization via Ensemble for Large Vision-Language Models | Donghee Lee | |
| 10013233-P | Scaling Next-Brain-Token Prediction for MEG | Richard Csaky | |
| 10013234-P | GHVL: Geometry-Grounded Hyperbolic Vision-Language Models for Hierarchical Multimodal Representation Learning | Sarthak Srivastava | |
| 10013244-P | DISCO: Document Intelligence Suite for COmparative Evaluation | Kenza Benkirane | |
| 10013251-P | DiffuMamba: High-Throughput Diffusion LMs with Mamba Backbone | Pierre-Andre Noel | |
| 10013255-P | Rethinking Visual Information Processing in Multimodal LLMs | Viresh Ranjan | |
| 10013318-P | Seeing Once is Enough? Online Geometry-Aware Token Pruning for 3D Question Answering | Bolivar Solarte | |
| 10013319-P | ViTaB-A: Evaluating Multimodal Large Language Models on Visual Table Attribution | Yahia Alqurnawi | |
| 10013320-P | FROST: Filtering Reasoning Outliers with Attention for Efficient Reasoning | Jiang Zhuolin | |
| 10013322-P | VisGym: Diverse, Customizable, Scalable Environments for Multimodal Agents | Zirui Wang | |
| 10013335-P | VisualThinker: First ever R1-Zero´s Aha Moment on just a 2B non-SFT Model | Hengguang Zhou | |
| 10013336-P | Spatial Competence Benchmark | Jash Vira | |
| 10013339-P | Improving GUI Grounding with Explicit Position-to-Coordinate Mapping | Perouz Taslakian | |
| 10013343-P | DREAM-R: Multimodal Speculative Reasoning with RL-Based Refined Drafting, Precise Verification, and Fully Parallel Execution | Sai Qian Zhang | |
| 10013348-P | CivicEmbed: Feature-specific embeddings for efficient geographic reasoning and retrieval | Josephine Wang | |
| 10013426-P | Counterfactual Credit Assignment for Policy Optimization | Mykola Khandoga | |
| 10013429-P | Compute-Efficient GRPO Training | Rajat Ghosh | |
| 10013431-P | TestSmith: Reinforcement Learning for Unit Test Generation with Synthetic Perturbations | Stanley Yu | |
| 10013432-P | Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum | Gaotang Li | |
| 10013436-P | Challenges in Inference-Time Scaling with Uncertainty-Aware Tree Search | Jacopo Minniti | |
| 10013439-P | Execution-Grounded Credit Assignment for GRPO in Code Generation | Abhijit Kumar | |
| 10013443-P | DIRICHLET-PRIOR SHAPING: GUIDING EXPERT SPECIALIZATION IN UPCYCLED MOES | Babak Ehteshami Bejnordi | |
| 10013447-P | Recontextualization Mitigates Specification Gaming without Modifying the Specification | Victor Gillioz | |
| 10013453-P | DELTA4: Sparse Matrix-Vector Multiplication for Low Sparsity | Vladimir Boza | |
| 10013467-P | Training-Free Dynamic Upcycling of Expert Language Models | Eros Faně | |
| 10013468-P | A-3PO: Accelerating Asynchronous LLM Training with Staleness-aware Proximal Policy Approximation | Xiaocan Li | |
| 10013474-P | Reasoning as Compression: Unifying Budget Forcing via the Conditional Information Bottleneck | Marco Federici | |
| 10013477-P | TOUCAN: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments | Zhangchen Xu | |
| 10013480-P | Weight Decay Improves Language Model Plasticity | Sebastian Bordt | |
| 10013689-P | BiomedSQL: Text-to-SQL for Scientific Reasoning on Biomedical Knowledge Bases | Mathew Koretsky | |
| 10013694-P | Attractome: From Theory to Generative Models for Cancer Dynamics and Control | Arash Mehrjou | |
| 10013703-P | LLM-Guided Retrieval for Prediction of Molecular Perturbation Responses | Sepideh Maleki | |
| 10013726-P | DREAM-DNA: Controlled Design via Reasoning and Matched-flows for DNA | Weimin Wu | |
| 10013728-P | ON THE IMPACT OF EMBEDDING ANISOTROPY IN GENOMIC LANGUAGE MODELS FOR BACTERIAL TAXONOMY | Bruno Andrade | |
| 10013819-P | Zero-shot Multivariate Time Series Forecasting Using Tabular Prior Fitted Networks | Doron Bergman | |
| 10013827-P | PETS: Inference-Time Differentially Private Synthetic Time Series Generation | Yangzhixin Luo | |
| 10013837-P | GPT2MEG: Quantizing MEG for Autoregressive Generation | Richard Csaky | |
| 10013838-P | Factor Dimensionality and the BiasVariance Tradeoff in Diffusion Portfolio Models | Avi Bagchi | |
| 10013874-P | The Geometry of Time-Series Diffusion: Why Latent Space Diffusion Works for Generation and Imputation | Afshin Asadi | |
| 10013880-P | Impermanent: A Live Benchmark for Temporal Generalization in Time Series Forecasting | Azul Garza | |
| 10014468-P | Built-in Safeguards for Auto-regressive Protein Foundation Models through Self-play | Xiaoyi Fu | |
| 10014482-P | Evaluating Expert Specialization in Mixture-of-Experts Antibody Language Models | Sarah Burbach | |
| 10014485-P | Test-Time Tuned Language Models Enable End-to-end De Novo Molecular Structure Generation from MS/MS Spectra | Laura Mismetti | |
| 10014486-P | SciPredict: Can LLMs Predict the Outcomes of Scientific Experiments in Natural Sciences? | Elaine Lau | |
| 10014487-P | Surrogate-Assisted Pedestrian Protection Design via a Foundation ModelOrchestrated Workflow | Osamu Ito | |
| 10014507-P | From Weather to Weathering: Foundation Models for Carbon Removal via Rock Weathering | Sasankh Munukutla | |
| 10014511-P | GeoPT: Scaling Physics Simulation via Lifted Geometric Pre-Training | Haixu Wu | |
| 10014512-P | Foundation Models as Physical Priors: Decoupling Geometric Reasoning from Small-Molecule Solubility Prediction | Jonathan Broadbent | |
| 10014517-P | Vehicle Surface Pressure Prediction from 2D Sketches via a Pre-Trained Diffusion Model | shunya nakamura | |
| 10014525-P | SENDAI: A Hierarchical Sparse-measurement, EfficieNt Data AssImilation Framework | Yuxuan Bao | |
| 10014533-P | On Neural Scaling Laws for Weather Emulation through Continual Training | Shashank Subramanian | |
| 10014616-P | The Low-Frequency Trap: Why Scaling Doesn´t Solve Simple Temporal Counting | Zikui Cai | |
| 10014617-P | Spatial Reasoning is Not a Free Lunch: A Controlled Study on LLaVA | Nahid Alam | |
| 10014620-P | Lost in Translation: Why SOTA LLMs Struggle with French NLU Frontiers | David Beauchemin | |
| 10014621-P | Voice Evaluation of Reasoning Ability: Diagnosing the Modality-Induced Performance Gap | Yueqian Lin | |
| 10014624-P | The Missing Red Line: How Commercial Pressure Erodes AI Safety Boundaries | Nora Petrova | |
| 10014625-P | Evaluating Ill-Defined Tasks in Large Language Models | Yi Zhou | |
| 10014626-P | Is Evaluation Awareness Just Format Sensitivity? Limitations of Probe-Based Evidence under Controlled Prompt Structure | Viliana Devbunova | |
| 10014632-P | Can Multi-Modal LLMs Provide Live Step-by-Step Task Guidance? | Roland Memisevic | |
| 10014642-P | Probing and Steering Chain-of-Thought Unfaithfulness in Language Models | Giovanni Maria Occhipinti | |
| 10014643-P | Query Timing Produces Opposite Positional Biases Between LLMs and Humans | Jasin Cekinmez | |
| 10014651-P | EoRA: Fine-tuning-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation | Min-Hung Chen | |
| 10016017-P | On the "Induction Bias" in Sequence Models | Roland Memisevic | |
| 10016031-P | Thermodynamics of Reinforcement Learning Curricula | Jacob Adamczyk | |
| 10016035-P | TrasMuon: Trust-Region Adaptive Scaling for Orthogonalized Momentum Optimizers | Peng Cheng | |
| 10016036-P | Ablate and Rescue: A Causal Analysis of Residual Stream Hyper-Connections | William Peng | |
| 10016047-P | Process-then-Retrieve: A Mechanistic Study of Cross-Modal Alignment in Vision-Language Models | Arpita Shanbhag | |
| 10016048-P | Understanding Contextual Recall in Transformers: How Finetuning Enables In-Context Reasoning over Pretraining Knowledge | Bhavya Vasudeva | |
| 10016058-P | Training for Compositional Sensitivity Reduces Dense Retrieval Generalization | Iliya Zhechev | |
| 10016064-P | Genomic Next-Token Predictors are In-Context Learners | Aayush Mishra | |
| 10016077-P | Information spreading in diffusion models from effective field theory | Navonil Neogi | |
| 10016244-P | Reading Between the Pixels: Linking Text-Image Embedding Alignment to Typographic Attack Success on Vision-Language Models | Ravikumar Balakrishnan | |
| 10016245-P | Understanding Metacognition in Multi-Agent LLMs: Routing, Not Reasoning | Lijun Qian | |
| 10016247-P | Rapid Poison: Practical Poisoning Attacks Against the Rapid Response Framework | Chawin Sitawarin | |
| 10016253-P | ZeroDayBench: Evaluating LLM Agents on Unseen Zero-Day Vulnerabilities for Cyberdefense | Nancy Lau | |
| 10016262-P | CommandSans: Securing AI Agents with Surgical Precision Prompt Sanitization | Debeshee Das | |
| 10016266-P | Profit Is the Red Team: Stress-Testing Agents in Strategic Economic Interactions | Shouqiao Wang | |
| 10016272-P | ProActor: Timing-Aware Reinforcement Learning for Proactive Task Scheduling Agents | Bin He | |
| 10016276-P | Visual Exclusivity Attacks: Automatic Multimodal Red Teaming via Agentic Planning | Weijie Xu | |
| 10016282-P | Secure Code Generation via Online Reinforcement Learning with Vulnerability Reward Model | Tianyi Wu | |
| 10016288-P | Evaluating LLM Judges in Cybersecurity Script Analysis | Alexandra-Daniela Damir | |
| 10016293-P | Critical Mass: Phase Transitions, Covert Coordination Detection, and Contagion Dynamics in Multi-Agent Systems | Ben Jenkins | |
| 10016295-P | Agentic Rubrics as Contextual Verifiers for SWE Agents | Mohit Raghavendra | |
| 10016301-P | PrefPO: Pairwise Preference Prompt Optimization | Rahul Singhal | |
| 10016303-P | Large-scale online deanonymization with LLMs | Simon Lermen | |
| 10016310-P | Differential Harm Propensity in Personalized LLM Agents: The Curious Case of Mental Health Disclosure | Caglar Yildirim | |
| 10016311-P | Ads in ChatGPT? An Analysis of How Large Language Models Navigate Conflicts of Interest | Addison Wu | |
| 10016317-P | Quality-Diversity Evolution for Discovering Diverse Vulnerabilities in LLM Safety | Subhadip Mitra | |
| 10016337-P | HealthAdminBench: Evaluating Computer-Use Agents on Realistic Healthcare Administration Tasks | Ryan Welch | |
| 10016338-P | Efficient Test-Time Scaling of Multi-Step Reasoning by Probing Internal States of Large Language Models | Jingwei Ni | |
| 10016341-P | Scaling Agentic Capabilities, Not Context: Efficient Reinforcement Finetuning for Large Toolspaces | Yash Pandya | |
| 10016344-P | Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use | Yash Pandya | |
| 10016383-P | Recalling Too Well: Sycophancy and Bias Amplification in Memory-Augmented Models | Axel Magnuson | |
| 10016385-P | Agent Properties for Multi-Agent Safety | Cecilia Elena Tilli | |
| 10016468-P | Helping Customers In Distress: An LLM-Powered Agent That Converses, Probes, and Routes | Cristovao Iglesias de Oliveira | |
| 10016470-P | AlphaLoss: LLM-Driven Evolution of Robust and Interpretable Portfolio Optimization Objectives | Joăo Pedro Maia | |
| 10016477-P | A Modular LLM Framework for Explainable Price Outlier Detection | Shadi Sartipi | |
| 10016480-P | When AI Adds No Signal: LLM Embeddings versus Price-Based Stock Clusters | Maria Hybinette | |
| 10016489-P | The Price of Agreement: Measuring LLM Sycophancy in Agentic Financial Applications | Aparna Balagopalan | |
| 10016491-P | Large-Scale Chatbot Validation Through Customer Digital Twin Simulations | Cristovao Iglesias de Oliveira | |
| 10016493-P | BIASMIX-FINANCE: POST-GENERATION KYC GUARDRAILS FOR LLM PORTFOLIO ADVICE | Gaurav Kukreja | |
| 10016494-P | Winner Stock Prediction as Decision-Aligned Multiclass Classification | Jairo Diaz Rodriguez | |
| 10016505-P | AutoQA: An Interpretable Automation Framework for CDD Quality Assurance in Financial Services | Cristovao Iglesias de Oliveira | |
| 10016509-P | INTERACTIVE CO-CRAFTER: TEMPLATIZED DOCUMENT GENERATION | Eshani Agrawal | |
| 10016512-P | Toward An Agentic Approach in Anti-Money Laundering Investigation for Typology Classification | Remi Grzeczkowicz | |
| 10016521-P | LLM-Driven Correlation-Aware Tournaments | Joăo Pedro Maia | |
| 10016541-P | LLM-Driven Active Listwise Tournaments for Portfolio Selection in Large Asset Universes | Joăo Pedro Maia | |
| 10016544-P | Probabilistic Multivariate Time Series Forecasting with Diffusion Copulas | Miha Bresar | |
| 10016548-P | TimeSeek: Temporal Reliability of Agentic Forecasters | Dennis Lee | |
| 10016650-P | LaneRoPE: Positional Encoding for Collaborative Parallel Reasoning and Generation | Gabriele Cesa | |
| 10016653-P | Encode, Think, Decode: Scaling test-time reasoning with recursive latent thoughts | Yeskendir Koishekenov | |
| 10016654-P | Tiny Autoregressive Recursive Models | Paulius Rauba | |
| 10016659-P | Learning Efficient Latent Reasoning with Abstract Chain-of-Thought | Keshav Ramji | |
| 10016685-P | Offline RL with Hierarchical Action Chunking | Ahad Jawaid | |
| 10016688-P | Is continuous CoT better suited for multilingual reasoning? | Behzad Shomali | |
| 10016691-P | Adaptive Loops and Memory in Transformers: Think Harder or Know More? | Markus Frey | |
| 10016912-P | Hyperspherical Filtering for Online Classification under Drift | David Boekestijn | |
| 10016921-P | LogitScope: A Framework for Analyzing LLM Uncertainty Through Information Metrics | Farhan Ahmed | |
| 10016927-P | A Credal-Set Perspective on Task-Induced Distributional Drift in Text Generation | Esteban Garces Arias | |
| 10016951-P | Evaluating Performance Drift from Model Switching in Multi-Turn LLM Systems | Raad Khraishi | |
| 10016956-P | Explainability of predictive uncertainty models under drift in the telecom domain | Alberto Hata | |
| 10016976-P | Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling | Natalia Frumkin | |
| 10017135-P | SingLoRA: Low Rank Adaptation Using a Single Matrix | David Bensaid | |
| 10017173-P | SYNTHONY: A Stress-Aware, Intent-Conditioned Agent for Deep Tabular Generative Models Selection | Hochan Son | |
| 10017197-P | CATS: Inference-aligned SFT for Diffusion LLMs via Context-sensitivity Aware Trajectory Sampling | Seunghyuk Oh | |
| 10017199-P | BSTabDiff: Block-Subunit Diffusion Priors for High-Dimensional Tabular Data Generation | Al Zadid Sultan Bin Habib | |
| 10017204-P | A Complete Decomposition of Stochastic Differential Equations | Sam Duffield | |
| 10017211-P | IDLM: Inverse-distilled Diffusion Language Models | David Li | |
| 10017221-P | Time-Correlated Video Bridge Matching | Viacheslav Vasilev | |
| 10017246-P | On the "Induction Bias" in Sequence Models | Roland Memisevic | |
| 10017259-P | One-Step Residual Shifting Diffusion for Image Super-Resolution via Distillation | Nikita Gushchin | |
| 10017267-P | Agents in the Wild: Safety, Society, and the Illusion of Sociality on Moltbook | Yunbei Zhang | |
| 10017268-P | CR-Bench: Evaluating the Real-World Utility of AI Code Review Agents | Kristen Pereira | |
| 10017424-P | TopoBench: Benchmarking LLMs on hard topological reasoning | Nils Hoehing | |
| 10017442-P | An Investigation of Robustness of LLMs in Mathematical Reasoning: Benchmarking with Mathematically-Equivalent Transformation of Advanced Mathematical Problems | Yuren Hao | |
| 10017457-P | Surrogate Signals from Format and Length: Reinforcement Learning for Solving Mathematical Problems without Ground Truth Answers | xin rihui | |
| 10017503-P | AGM-Bench: Do Large Language Models Revise Beliefs Rationally? | Ben Jenkins | |
| 10017507-P | Finny: A Multi-Agent System for Structured Decision-Making with LLMs | Harshitha Ravindra | |
| 10017641-P | Exploring Perturbation Effects on Transcriptional Dynamics with ContrastiveBiVI | Ashenafee Mandefro | |
| 10017647-P | Physics-Constrained Correlation-Aware Attention for Collective Cell Dynamics | Andrei Zakharov | |
| 10017657-P | Converting diffusions to flows accelerates sampling and suggests over-conditioning of co-folding models on sequence | Nele Quast | |
| 10017673-P | Entropy, Disagreement, and the Limits of Foundation Models in Genomics | Maxime Rochkoulets | |
| 10017739-P | Methylation-Aware Embedding Geometry Emerges from Bisulfite Pretraining in DNA Language Models | Salwan Butrus | |
| 10017741-P | Are Vision Foundation Models foundational for electron microscopy image segmentation? | Caterina Fuster Barcelo | |
| 10017747-P | Incorporating contextual information into KGWAS for interpretable GWAS discovery | Heming Yao | |
| 10017759-P | A Geometric Perspective on Zero-Shot Variant Effect Prediction Across the Central Dogma | César Miguel Valdez Córdova | |
| 10018004-P | Tree of Options: Temporally Extended World Modeling, Planning, and Execution with Large Language Models | Xiaoling Zeng | |
| 10018007-P | Grounding Generated Videos in Feasible Plans via World Models | Christos Ziakas | |
| 10018036-P | A Lightweight Library for Energy-Based Joint-Embedding Predictive Architectures | Basile Terver | |
| 10018043-P | WestWorld: A Knowledge-Encoded Scalable Trajectory World Model for Diverse Robotics | Huajie Shao | |
| 10018060-P | Structure from Diffusion: Taming Video Diffusion Models for Camera Pose Estimation in Dynamic Videos | Sihan Liu | |
| 10018077-P | Action Shapley: A training data selection metric for Training World Models for Reinforcement Learning | Rajat Ghosh | |
| 10018082-P | Active World-Model with 4D-informed Re- trieval for Exploration and Awareness | Tara Javidi | |
| 10018089-P | Environment Maps: Structured Environmental Representations for Long-Horizon Agents | Chirag Sharma | |
| 10018201-P | DIRECTING THE UNSCRIPTED: ALT-MIRAGE FOR EMERGENT SOCIAL DECEPTION DRAMA | Yan Liu | |
| 10018220-P | Prompt Optimization Enables Stable Algorithmic Collusion in LLM Agents | Yingtao Tian | |
| 10018221-P | Performative Personalization Incentivizes Truthfulness in Federated Learning | Kumar Kshitij Patel | |
| 10018233-P | Do LLMs Act Like Rational Agents? Measuring Belief Coherence in Probabilistic Decision Making | Khurram Yamin | |
| 10018378-P | Evaluating LLM Agents as Human Simulators in Climate Social Dilemmas | Kaiyuan Liu | |
| 10018398-P | Team of Thoughts: Efficient Test-time Scaling of Agentic Systems through Orchestrated Tool Calling | Jeffrey Wong | |
| 10018406-P | MAGIC: Multi-Agent Generative Intention Coordination | David Huk | |
| 10018408-P | UT-Evolve: AN EVOLUTIONARY AGENT FOR UNIT TEST WRITING | Rajat Ghosh | |
| 10018422-P | Can Small Agents Collaborate to Beat a Single Large Language Model? | Xinyi Chen | |
| 10018434-P | Federation over Text | Dixi Yao | |
| 10018474-P | Agent-as-a-Coach: Towards Fully Agentic, Stateful, and Tool-Augmented Process Rewards | Junyu Ren | |
| 10018646-P | Just Enough Learning: GRPO-Guided Controllers for Hyperparameter Sweeps | Justin Lee | |
| 10018661-P | A Framework for Prompt Optimization and Translation Across Foundation Models | Abhinav Shankaranarayanan Venkataraman | |
| 10018664-P | AUTOHARNESS: IMPROVING LLM AGENTS BY AUTOMATICALLY SYNTHESIZING A CODE HARNESS | Carter Wendelken | |
| 10018688-P | Soft Mellowmax Monte Carlo Planning | Danilo Vucetic | |
| 10018689-P | Aligned but Stereotypical? Understanding and Mitigating Social Bias in LLM-Driven Text-to-Image Models | NaHyeon Park | |
| 10018733-P | Adaptive Decoding via Test-Time Policy Learning for Self-Improving Generation | Eelaaf Zahid | |
| 10019066-P | Secure Code Generation via Online Reinforcement Learning with Vulnerability Reward Model | Tianyi Wu | |
| 10019084-P | A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior | Harry Mayne | |
| 10019128-P | SureFED: Robust Federated Learning via Uncertainty-Aware Inward and Outward Inspection | Ruisi Zhang | |
| 10019130-P | Watermarking Discrete Diffusion Language Models | Avi Bagchi | |
| 10019164-P | VisualScratchpad: Inference-time Visual Concepts Analysis in Vision Language Models | Hyesu Lim | |
| 10019166-P | MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Knowledge Poisoning Attacks | Hyeonjeong Ha | |
| 10019176-P | Sycophantic Anchors: Localizing and Quantifying User Agreement in Reasoning Models | Jacek Duszenko | |
| 10019180-P | Latent Personality Alignment: Improving Harmlessness Without Mentioning Harms | Linh Le | |
| 10019202-P | Understanding Empirical Unlearning with Combinatorial Interpretability | Shingo Kodama | |
| 10019208-P | TIGHTENING OPTIMALITY GAP WITH CONFIDENCE THROUGH CONFORMAL PREDICTION | Michael Klamkin | |
| 10019214-P | Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment | Leon Gatys | |
| 10019218-P | Hierarchical Retrieval at Scale: Bridging Transparency and Efficiency | Perouz Taslakian | |
| 10019228-P | Investigating Data Interventions for Subgroup Fairness: An ICU Case Study | Erin Tan | |
| 10019252-P | Inference-Time Backdoors via Hidden Instructions in LLM Chat Templates | Omer Hofman | |
| 10019288-P | Backdoor Attacks on Decentralised Post-Training | Oguzhan Ersoy | |
| 10019310-P | Expert Selections In MoE Models Reveal (Almost) As Much As Text | Amir Nuriyev | |
| 10019326-P | Uncertainty Drives Social Bias Changes in Quantized Large Language Models | Stanley Bryan Hua | |
| 10019340-P | Mitigating Reward Hacking with RL Training Interventions | Aria wong | |
| 10019350-P | Verbosity Tradeoffs and the Impact of Scale on the Faithfulness of LLM Self-Explanations | Noah Siegel | |
| 10019674-P | GraphPFN: A Prior-Data Fitted Network for Graph Node-Level Tasks | Liudmila Prokhorenkova | |
| 10019680-P | Unified Evaluation of Table Embedding Methods Across Multiple Benchmark Scenarios | Saeed Ghoorchian | |
| 10019682-P | RelBench v2: A Large-Scale Benchmark and Relational Data Repository | Justin Gu | |
| 10019688-P | When do Score-Based Data Valuation Methods Work, and Why? | Kumar Kshitij Patel | |
| 10019690-P | PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation Models | Vignesh Kothapalli | |
| 10019709-P | jina-vlm: Small Multilingual Vision Language Model | Georgios Mastrapas | |
| 10019710-P | Less is More: Adaptive Coverage Sampling for Synthetic Training Data | Sasan Tavakkol | |
| 10019730-P | Multimodal Data Curation Through Ranked Retrieval | Pratyush Muthukumar | |
| 10019733-P | On the Strengths and Weaknesses of Data for Open-Set Embodied Assistance | Pradyumna Tambwekar | |
| 10019740-P | Positive Mining from LLM Seeds: A Semi-Supervised Graph Based Approach to Train Rare Event Classifiers | Abby Schantz | |
| 10019757-P | [Short] Where Does Olmo Get Its Values? | Xiaoqing Sun | |
| 10019758-P | [Short] Max It or Miss It: Benchmarking LLM On Solving Extremal Problems | Binxin Gao | |
| 10019948-P | Topology-Aware Neural Graph Operator (TANGO) for Material Constitutive Laws | Arman Moussavi | |
| 10020025-P | Cross-Linguistic Failures and Disparities in LLM Medical Reasoning: Analyzing XMedBench and CrossMMLU Across Western and Non-Western Languages | Akira Hoque | |
| 10020030-P | OC-PRM: Overcredit-Contrastive Training for Precision-First Process Reward Models | Aakriti Agrawal | |
| 10020032-P | Differential Adjusted Parity for Learning Fair Representations | Bucher Sahyouni | |
| 10020045-P | Scalable Intersectional Bias Auditing in Vision-Language Models through Combinatorial Interaction Testing | Heejin Bin | |
| 10020394-P | Time-to-Move: Training-Free Motion-Controlled Video Generation via Dual-Clock Denoising | Assaf Singer | |
| 10020406-P | Variational Entropic Optimal Transport | Nikita Gushchin | |
| 10020421-P | Hamiltonian-Guided Diffusion Fields for Variable-Length Rigid-Arm Trajectory Generation | Pedram Rooshenas | |
April 26 and 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. |
||||
|
|