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770 results for “keyword:"post train"” in ICLR 2027. 139 withdrawn or desk rejected listed apart.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]On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators▲6.6k3.33
[PDF]AlphaDiverse: Post-Training Local Quantitative Research Agents for Diverse Exploration in Alpha Factor Mining▼4.3k2.00
[PDF]IterLab: Training Agents to Experiment and Improve over Long Horizons with Calibrated Synthetic Tasks▼4.3k2.00
[PDF]Rethinking Floorplan Generation with Space Syntax: From Design Theory to Model Improvement▲5.4k3.00
[PDF]PortraitGen: Anchoring GRPO with Real-Image Trajectories for Photorealistic Portrait Generation▼4.5k2.67
[PDF]Corruption Robustness in Post-Training Quantization of Vision Transformers: A Calibration Perspective▼4.3k2.00
[PDF]FAME: Multi-Level Focus-Aware Mixture-of-Experts with Auxiliary Correctness Supervision for Audio Reasoning▲20k2.67
[PDF]SimpleOPD: Simple Tokenizer-Agnostic On-Policy Distillation for Long-Context Reasoning▼4.3k2.00
[PDF]Beyond Retrieval and Fine-tuning: Learning from Scientific Execution Experience for Self-Improving Agents▼4.5k2.25
[PDF]FSPO: Policy-Consistent Risk and Pareto-Feasible Control for Budgeted LLM RL Post-Training▼4.3k2.00
[PDF]Understanding Evolution Strategies for LLM Reasoning: Broader Reasoning Coverage than GRPO▲25k3.00
[PDF]Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation▲5.4k3.00
Withdrawn or desk rejected (139)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