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760 results for “keyword:"post training"” in ICLR 2027. 135 withdrawn or desk rejected listed apart.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]REGEN: Replay-recycling for Expert-to-Generalist distillation with Offline Reinforcement Learning▼5.8k2.33
[PDF]GOJO: Geometry-preserving Joint Optimization for On-policy Distillation in Diffusion Models▼4.5k2.25
[PDF]When Lower Reconstruction Loss Hurts: Distributionally Robust Refinement for Low-Bit LLM Quantization▼5.8k2.33
[PDF]Concordance-Guided Rollout Reweighting and Resampling for Multi-Reward Image Generation Post-Training▼5.8k2.33
[PDF]Mitigating Capability Degradation in LLM Self-Improvement via Representation Geometry Regularization▼4.3k2.00
[PDF]ARSO: Reconstruction-Aware Rounding with Joint Scale Optimization for Weight-Only LLM Quantization▼1.3k1.75
[PDF]A General Model Diffing Framework for Understanding Post-Training: Attributing Behavioral Differences to Parameter Updates▼1.2k1.67
[PDF]SignRoundV2: Toward Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs▲3.0k2.33
[PDF]HSA: Hierarchical Sensitivity-Aware Quantization for Resource-Constrained Embodied Models▼1.2k1.67
[PDF]Pinpoint Quantization: A Mechanistic Account of Tail-Capability Failures in Quantized LLMs▲5103.00
[PDF]Reducing Hallucination in Multimodal Large Language Models through Hard Grounding Preference Supervision▼1.2k1.67
[PDF]BiTFlow: Efficient Coreset Selection for Instruction Tuning via Balanced Token Flow Matching▲143.33
[PDF]XOR-Trellis: Ultra-Low-Complexity Dequantization and Curvature-Aware Hadamard-Free LLM Quantization▲6.6k3.33
[PDF]SeisAgentBench: Benchmarking and Reinforcement Learning for Seismic Data-Processing Agents▲5.4k3.00
[PDF]What Generation Knows: Unlocking Fine-Grained Understanding in Unified Multimodal Models▼5.9k2.50
Withdrawn or desk rejected (135)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