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760 results for “keyword:"post training"” in ICLR 2027. 135 withdrawn or desk rejected listed apart.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]Behavior Amplification: Discovering and Steering Model-Specific Reasoning Strengths in LLMs▲9.2k2.67
[PDF]Learning to Stop without Learning to Stop: Self-Supervised Confidence Training Improves Reasoning Efficiency▲3952.67
[PDF]How Does "English (US)” Become the Default? Triangulating Structural Bias Towards American English Across the LLM Pipeline▲5.4k3.00
[PDF]Noise-Robust Reinforcement Learning with Verifiable Rewards for Open-ended Medical Multimodal Reasoning▲3.0k2.33
[PDF]The Shape of Flows: Topological Regularization of Vector Fields in Flow Matching for Better Diversity and Fidelity.▲3952.67
[PDF]Quantized Keys Steal Attention: Bias Correction for KV-Cache Compression in Video Diffusion▲5103.00
[PDF]LRSR: Hardware-Friendly Approximation of Per-Element Quantization via Low-Rank Scale Reconstruction▲3.9k1.67
[PDF]Dual Tuning: Joint Screening of Data Utility and Supervision Modes for Multimodal Fine-Tuning▼4.3k2.00
[PDF]HeteroQuant: Resolving Expert Heterogeneity in MoE Quantization via Targeted Calibration▼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Withdrawn or desk rejected (135)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