HALO: Human-Grounded Granular Evaluation of Proactive Agents Paper • 2610.39086 • Published 19 days ago • 12
The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents Paper • 2610.36077 • Published 22 days ago • 161
SepGen: Multi-Stem Audio-Video Separation and Generation in a Single Model Paper • 2610.11361 • Published Oct 8 • 36
Post-Training Frontier Text-to-Image Models by Composing Preference and Rubric Rewards Paper • 2610.02967 • Published Oct 2 • 30
MetaRubric: Learning to Reward for Rubric-Based Reinforcement Learning Paper • 2610.02824 • Published Oct 2 • 12
Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs Paper • 2609.32259 • Published Sep 29 • 20
RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning Paper • 2609.20784 • Published Sep 17 • 24
VidaForge: Open Research Infrastructure for Video Pretraining Data Recipes Paper • 2609.06652 • Published Sep 6 • 6
Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstruction Paper • 2609.04201 • Published Sep 3 • 39
Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training Paper • 2608.26730 • Published Aug 27 • 26
LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes Paper • 2609.03796 • Published Sep 3 • 59