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
1,315 results for “keyword:"policy"” in ICLR 2027. 274 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]CheckDistill: Adaptive Checklist Distillation for Efficient Distributional Reward Modeling in Image Editing▼1.2k3.00
[PDF]When Visual Compression Breaks Control: Efficient Multi-View VLA Inference via Retaining Evidence for Control-Aligned Policy Recovery▼1.2k1.67
[PDF]Privileged Likelihood is not Automatically Value: Three Checks for Token Credit in On-Policy Self-Distillation▲6.6k3.33
[PDF]Matched Compute Is Not Matched Signal: Where the Gradient Goes in Group-Relative Reinforcement Learning▼1361.33
[PDF]HEIR: When the Student Inherits the Teacher's Seat Pareto-Competitive Reference Selection for On-Policy Self-Distillation of Reasoning LLMs▼5.3k1.33
[PDF]Pareto-GRPO: Prompt-Local Pareto Credit Assignment for Efficient Search-Augmented Reasoning▼1.2k1.67
[PDF]FedPRA: Policy-Residual Aggregation for Heterogeneous Differentially Private Federated Learning.▼4.3k2.00
[PDF]Guide the Tokens, Rank the Moments: Adaptive On-Policy Distillation for Temporal Video Grounding▲5.4k3.00
[PDF]Correct Code, Broken Contributions? SWE-CC: Benchmarking Repository Policy Compliance for Coding Agents▼5.8k2.33
[PDF]Structure Beyond Pixels: Aligning Video with Structural Preferences for Robust Policy Generation▼5.8k2.33
[PDF]OmniZPD: Token Compression via Policy Optimization and Self-Distillation for Omni-Modal Reasoning▼4.5k2.67
[PDF]Retrospection Makes a Better Learner: Retrospective On-Policy Self-Distillation for Reasoning Models▲6.1k2.00
[PDF]Cool the Sampler, Not the Learner: Sampling Temperature Moves the Staleness Cliff of Importance-Corrected GRPO▼4.3k2.00
[PDF]Minimax Optimality for Factored Optimal-Transport Distributionally-Robust Policy Learning in Contextual Bandits▼4.5k2.67
[PDF]LNPO-ATC: LENGTH-NORMALIZED POLICY OPTIMIZATION WITH ADAPTIVE TOKEN CREDIT FOR LONG-CONTEXT REASONING▼4.5k2.67
[PDF]ForkLeft: Entropy-First Rollouts for Prefix-Aligned Autoregressive-to-Diffusion Distillation▼1.2k1.67
[PDF]When Do We Need On-Policy Distillation? Distilling on Offline Student Rollouts Is Often Better▼4.5k2.67
Withdrawn or desk rejected (274)
[PDF]When Is a Policy Violation a Model Failure? Policy Observability and Failure Attribution in Agent-Safety EvaluationDesk rejected
[PDF]Beyond the Local View: Predicting Correction Gains for Sparse On-Policy DistillationWithdrawn1.33
[PDF]Correlation Does Not Certify a Policy Choice: What Benchmarks Should Publish InsteadWithdrawn2.33
[PDF]Implicit Strategic Optimization: Prediction-Aware Long-Horizon Learning for LLM AgentsDesk rejected1.67
[PDF]Learning What to Share: Latent Representations for FedRL with Observation DistractorsDesk rejected1.67
[PDF]Collaborative Specialist Knowledge Distillation for Federated Offline Reinforcement LearningWithdrawn2.00