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
819 results for “keyword:"reward"” in ICLR 2027. 154 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Verifiable ≠ Valid: What Programmatic Physics Rewards for Video Generation Actually Optimize▲6.1k2.00
[PDF]RewardWeaver: Long-Horizon Interactive Learning for Language Agents via Self-Evolving Reward Adaptation▼1.2k1.67
[PDF]DreOPD: Degraded-Reference Extrapolative On-Policy Distillation for Flow-matching Models▲5103.00
[PDF]Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack▼4.3k2.00
[PDF]OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models▲444.00
[PDF]Normal Fréchet Drift: Measuring Post-Training Departure from Pretrained Reference Manifold▲13k2.33
[PDF]Skip What You Can Predict: Predictive Repositioning for Policy Optimization for Efficient LLM Training▲5.4k3.00
[PDF]VGAS: Variance-Reduced Guidance and Adaptive Selection for Training-Free Reward Alignment in Discrete Diffusion▲3952.67
[PDF]Trajectory-Aware Policy Optimization: Closing the State Distribution Gap in Long-Horizon LLM RL▲3952.67
[PDF]Generalized Proximal Policy Optimization: Unifying LLM RL Algorithms from the Perspective of Divergence▲3.0k2.33
[PDF]When Reward Doesn't See Everything: Modality-Blind Credit Assignment for Simultaneous Speech-To-Speech Translation▲3.9k1.67
[PDF]Neuromodulated Equilibrium Learning: Reward-Driven Learning from a Single Free Equilibrium▼4.3k2.00
[PDF]Conjunctive Amplification of Reward-Scale Miscalibration in Cooperative Multi-Event Reinforcement Learning▼5.8k2.33
[PDF]RL-Trained Crop-and-Zoom Is Often Decorative: Pixel Budgets, Protocol Costs, and Causal Credit▼4.5k2.67
[PDF]All Work And No Play Makes Jack a Dull Boy: Understanding and Preventing Catastrophic Strategy Collapse in RLVR▲6.1k2.00
Withdrawn or desk rejected (154)
[PDF]Auditing Reward-Model Selection on Tool Trajectories: Identification, Policy Utility, and Natural TransferWithdrawn1.67
[PDF]Verifier-Induced Strategy Collapse: Family-Correlated False Negatives Eliminate Valid Strategies While Capability Metrics ImproveDesk rejected
[PDF]Reflection Rewards Pay for Deferral: Capability-Aware Rewards for Reflective RLDesk rejected3.00