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770 results for “keyword:"post train"” in ICLR 2027. 139 withdrawn or desk rejected listed apart.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]Post-Calibration Topology Drift Reveals Operator-Dependent Numerical Sensitivity in Quantized Graph Neural Networks▲11.00
[PDF]Pinning Visual Paths:Preserving Visual Structure for Ultra-Low-Bit Vision Encoders with Task-Informed Reconstruction▼4.3k2.00
[PDF]Rethinking Anti-distillation of Large Language Models: An Unlearnable Examples Perspective▲5103.00
[PDF]Fixing the Errors That Flip Answers: Output-Weighted Low-Rank Correction for Quantized Vision-Language Models▲3952.67
[PDF]Training-State Shaping for Low-NFE Flow Matching: Gains Across Solvers and Better Couplings for Distillation▲6.1k2.00
[PDF]Fine-Tuning VLAs with Self-Demonstrated Generative Control for Multi-Task Manipulation▼1.2k3.00
[PDF]Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy▼5.8k2.33
[PDF]Context-Robust: Context-Informed Activation Calibration for Mixture-of-Experts Language Models▲14k3.00
[PDF]One Task, Many Interfaces: Simple Cross-Interface Consistency Training Improves LLM Agent Robustness▲3.0k2.33
[PDF]Finale: Reconstructing Local Supervision with Terminal-Anchored Replay for End-to-End Web Agents▲5.4k3.00
[PDF]Accuracy Is Not Enough: Measuring Instruction-Following Stability Under Post-Training Quantization▲11.00
[PDF]QGATE: Counterexample-Guided Precision Patching of Quantized LLMs with Fail-Closed Slice Reporting▲11.00
[PDF]biCurriculum: Crediting Executable Task and Environment Rewrites by Their Learning Utility▼1361.33
[PDF]PRIMO: Pareto-Optimal Information-Constrained Compression for Mixture-of-Experts Language Models▲6.1k2.00
[PDF]Distilling Strong Teachers into Small Models: Teacher-Preferred Distribution Alignment Matters▼5.8k2.33
[PDF]Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubrics▲5103.00
[PDF]HEPH: 3-Bit Grid-Aligned Trellis Quantization of MXFP4 Mixture-of-Experts for Accurate, Hadamard-Free Serving▲20k2.67
Withdrawn or desk rejected (139)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