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760 results for “keyword:"post training"” in ICLR 2027. 135 withdrawn or desk rejected listed apart.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]BranchWise: A Path Is Not a Policy — Unfolding Successful Trajectories into Model-Tailored Decision Boundaries▲9.2k2.67
[PDF]PostTrainBench-Pro: How Well Can AI Agents Post-Train Domain-Level Capabilities under Controlled Compute?▲5.4k3.00
[PDF]Better Fixed-State Fidelity Need Not Improve Closed-Loop Performance in Quantized Neural Policies▼1361.33
[PDF]Rethinking RL for LLM Reasoning: It’s Sparse Policy Selection, Not Capability Learning▼4.5k2.67
[PDF]Balancing Specialists with Safety: Lagrangian Anchored Multi-Teacher On-Policy Distillation for Large Language Models▼1361.33
[PDF]Not Which Path, but What Happens Before You Would Stop: What Reasoning Post-Training Changes▼1361.33
[PDF]MDMixQ: Modality-Decoupled Mixed-Precision Quantization for Multimodal MoE Compression▼4.3k2.00
[PDF]Who Teaches Which Token? Verifier-Gated Multi-Expert On-Policy Distillation for Scientific Reasoning▲3.0k2.33
[PDF]Thinking in Trajectories: Structured Exploration for Vision-Language-Action Reinforcement Learning▲3952.67
[PDF]From Storage to Access: Verifiable Activation of Parametric Knowledge in LLMs via Explicit Priming and Implicit Reasoning▲5.4k3.00
[PDF]SteerQuant: Steering Quantization Error with Action-Guided Scaling in World–Action Models▲3.0k2.33
[PDF]Distilling Structure, Not Solutions: Structural Bottlenecks for On-Policy Self-Distillation▼4.3k2.00
[PDF]COSP: Consumer Oriented Second-order Pruning for Compact Implicit Neural Representations▼5.8k2.33
[PDF]Density-Matched Power-of-Two Quantization: Allocating Logarithmic Levels for Multiplier-Free LLM Inference▼1.2k1.67
[PDF]The Denoising Estimate Is a State Variable: Joint Refinement for Few-Step Flow Language Models▲5.4k3.00
[PDF]MxQBound: Efficient Mixed-Precision Quantization for MoE-LLMs Guided by Expert Importance and Error Bound Guarantees▲6.1k2.00
[PDF]RLVR Training of LLMs Does Not Improve Thinking Ability for General QA: Evaluation Method and a Simple Solution▼4.3k2.00
[PDF]SAR-LCRT: RISK-GATED RESIDUAL TRANSPORT FOR FROZEN TIME-SERIES FORECASTERS UNDER DELAYED FEEDBACK▼1.2k1.67
Withdrawn or desk rejected (135)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