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
760 results for “keyword:"post training"” in ICLR 2027. 135 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Sequential Functional Structured Tucker Compression for Large Language Model Attentions▼5.8k2.33
[PDF]Reasoning Geometry of Language Models: How Prompting, Training, and Scale Shape Judgment Trajectories▲11.00
[PDF]Rewards for budget-aware multi-turn agents that dynamically adapt to arbitrary test-time constraints▲3952.67
[PDF]ReaLogic-FT: Progressive Neuro-Symbolic Post-Training for Reasoner-Verifiable Logical Reasoning▲3.0k2.33
[PDF]Exact Posterior Distillation: Teaching Language Models What To Believe And Whom To Trust▲3.0k2.33
[PDF]RILO: Feeding Implicit Process Rewards Back into Visual Reasoning for Industrial Anomaly Understanding▼1.3k1.75
[PDF]Less Data, Better Timing: Student–Curriculum Coupling for VLM On-Policy Distillation in Temporal Video Grounding▲9.2k2.67
[PDF]QuantaMind: A Large Chemistry Language Model for Structured Molecular Screening and Discovery▼1361.33
[PDF]Where Does Staleness Accumulate? Pool Aware Effective Staleness Control for Asynchronous RL in LLM Post Training▼5.8k2.33
[PDF]On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators▲6.6k3.33
Withdrawn or desk rejected (135)
[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