NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
120 results for “keyword:"reward models"” in ICLR 2027. 25 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Can Cheap Failures Teach Good Rewards? Studying Counterfactual Sources for Reward Learning in Manipulation▲3.0k2.33
[PDF]DeltaPRM: Rollout-Free Automatic Process Rewards via Answer Likelihood Gain for Retrieval Agents▲5.4k3.00
[PDF]What Does a Failed Rollout Supervise? Separating Policy Failure from Recoverability in Tool Agents▼4.3k2.00
[PDF]Let the Weak Judge: Annotation-Free Process Rewards for Multimodal E-commerce Relevance▼1.2k1.67
[PDF]From Trajectories to Grounded Preferences: Process Preference Synthesis via Interaction Element Graphs for Web PRMs▲3.0k2.33
[PDF]RHContrast: A Matched-Control Benchmark for Evaluating Reward-Hacking Risks in Long-Form LLM Responses▲3.0k2.33
[PDF]Procedure or Format? Measuring What a Reasoning Trace Teaches with Format-Residualized Codelength▲3952.67
[PDF]Equal Ranking Quality, Different Decisions: Measuring and Reducing Order Dependence in LLM Scorers▼5.8k2.33
[PDF]CheckDistill: Adaptive Checklist Distillation for Efficient Distributional Reward Modeling in Image Editing▼1.2k3.00
[PDF]Mitigating Over-Optimization in PRM-Guided Search in Mathematical Reasoning by Optimizing the Guide▼5.8k2.33
[PDF]PNR-SR: Policy-Native Reward-Policy Co-Training for One-Step Real-World Image Super-Resolution▲5103.00
[PDF]RewardExplainer: Learning Reward Model Explanations from Counterfactual Preference Feedback▲5103.00
[PDF]DreamerAD: Efficient Reinforcement Learning via Latent World Model for Autonomous Driving▲5103.00
[PDF]Certified Interface Aliases: Exact Collisions in Vision-Language Preprocessing, and When They Exist▼5.8k2.33
[PDF]Judging in Latent Space: Efficient Generative Reward Modeling via Semantics-Preserving Compression▲6.1k2.00
[PDF]Rewarding the Graph Behind the Chain: Topology-Aware Process Supervision for RL and Reasoning Distillation▲3952.67
Withdrawn or desk rejected (25)
[PDF]Rewarding Reasoning, Not Answers: Fixing and Bounding Test-Time Reinforcement Learning on Medical QAWithdrawn1.67
[PDF]Risk Is Not Reward: Action-Relative Process Rewards for VLM Hallucination MitigationDesk rejected