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
770 results for “keyword:"post train"” in ICLR 2027. 139 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Euterpe: Efficient Multi-Level Preservation of Pretrained Performance during Preference Alignment for Protein Inverse Folding▼4.3k2.00
[PDF]What Should a Self-Teacher See? Privileged Context Design for On-Policy Self-Distillation▼1.2k1.67
[PDF]From Measured Biology to Analysis Decisions: How Far Does Post-Trained Knowledge Travel?▲3.0k2.33
[PDF]Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agents▼2.0k1.00
[PDF]Not All Privilege Is Distillable: Calibrating Teacher Corrections for Few-Step Video Generation▲5103.00
[PDF]Rethinking What LLMs Transfer to Recommendation: Localizing and Recombining Pretrained Computation▼4.3k2.00
[PDF]CCL: Counterfactual Contract Learning for Local Execution Recovery in Embodied Multi-Agent Collaboration▼4.5k2.67
Withdrawn or desk rejected (139)
[PDF]Everything in Moderation: Interior Per-Domain Coverage Optima and Gap-Preserving Fixed-Budget Alignment in Multi-Domain Mid-TrainingDesk rejected
[PDF]Why Benign Post-Training Induces Safety Gate Collapse: Changes in Harmful Activation Geometry Relative to the Inherited Refusal GateWithdrawn1.67
[PDF]Hierarchical Safety-Oriented Dense RL with Refined Credit Assignment for Tokenized Multi-Agent Traffic SimulationWithdrawn1.75
[PDF]Decoupling KL and Trajectories: A Unified Perspective for SFT, DAgger, Offline RL, and OPD in LLM DistillationDesk rejected1.50