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
40 results for “keyword:"model post training"” in ICLR 2027. 5 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Training-State Shaping for Low-NFE Flow Matching: Gains Across Solvers and Better Couplings for Distillation▲6.1k2.00
[PDF]Rethinking Training–Inference Mismatch in LLM Reinforcement Learning: Where It Arises and How to Correct It▲4002.67
[PDF]The Shape of the DPO Hyperparameter Landscape: What to Measure, How It Moves with Scale, and When Not to Transfer It▼5.8k2.33
[PDF]TangentMix: Recovering Specialized Language Models through State-Conditioned Data Allocation▲6.1k2.00
[PDF]A Good Self-Teacher Meets the Student Where They Are: Joint On-Policy Learning and Teaching▲5103.00
[PDF]RL Does Not Always Forget Less: Understanding Retention through Target Learning in LLM Post-Training▲4002.67
[PDF]Learn What’s Left, Not What’s Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization▼5.8k2.33
[PDF]Beyond Policy Rollouts: Embedding-Space Directional Exploration with Anchored Noise for LLM RLVR▼4.5k2.67
[PDF]Dual-Channel Robust Group-Relative Policy Optimization via Advantage and Sequence-Weight Estimation▼1.2k1.67
[PDF]What Is Lost in Post-Training? Default Collapse and the Loss of In-Context Steerability Across Diverse Perspectives▼4.3k2.00
[PDF]When Sparse Reward Meets Dense Distillation: Training Dynamics of On-Policy Distillation▲3.0k2.33
[PDF]Balancing Specialists with Safety: Lagrangian Anchored Multi-Teacher On-Policy Distillation for Large Language Models▼1351.33
[PDF]Distilling Structure, Not Solutions: Structural Bottlenecks for On-Policy Self-Distillation▼4.3k2.00
[PDF]The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation▼5.8k2.33
Withdrawn or desk rejected (5)
[PDF]TGPO: Tracked-Gradient Policy Optimization for Multi-Reward Reinforcement LearningDesk rejected