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
76 results for “keyword:"reward modeling"” in ICLR 2027. 17 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]STEAM: Self-Supervised Temporal Ensemble Advantage Modeling for Real-World Robot Learning▲5103.00
[PDF]When Preference Margins Hide Text-Only Shortcuts: Visual-Conditional Margin Learning for Multimodal Reward Models▲5103.00
[PDF]RoboValue: A Fine-Grained Sim-and-Real Benchmark for Unified Evaluation of Robotic Value Models▼5.8k2.33
Withdrawn or desk rejected (17)
[PDF]Auditing Reward-Model Selection on Tool Trajectories: Identification, Policy Utility, and Natural TransferWithdrawn1.67
[PDF]WHAT SHOULD A SELF-DISTILLATION TEACHER SEE? SOLVER FEEDBACK FOR LOGICAL REASONINGWithdrawn1.33
[PDF]The Horizon of Reward GuidanceDesk rejected