SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Paper • 2608.03573 • Published 7 days ago • 50
Beyond Simply Environment Scaling: Designing Effective Environment Distributions for Multimodal Agent Learning Paper • 2608.03571 • Published 7 days ago • 42
Weak-to-Strong Generalization via Direct On-Policy Distillation Paper • 2607.05394 • Published Jul 8 • 142
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published May 28 • 253
TAD: Temporal-Aware Trajectory Self-Distillation for Fast and Accurate Diffusion LLM Paper • 2605.09536 • Published May 10 • 2
TAD Collection Temporal-Aware Trajectory Self-Distillation for Fast and Accurate Diffusion LLMs • 4 items • Updated May 10 • 1
Establishing Trustworthy LLM Evaluation via Shortcut Neuron Analysis Paper • 2506.04142 • Published Jun 4, 2025 • 28
MMR-V: What's Left Unsaid? A Benchmark for Multimodal Deep Reasoning in Videos Paper • 2506.04141 • Published Jun 4, 2025 • 31