VGI-Bench: Probing Visual Intelligence in Video Generation Models Paper • 2608.19583 • Published 21 days ago • 179
EnvHarness: Awakening Static Worlds for Agent Learning Paper • 2608.19880 • Published 27 days ago • 275
Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA Paper • 2608.09819 • Published Aug 10 • 344
Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents Paper • 2607.28227 • Published Jul 30 • 312
CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agents Paper • 2607.25431 • Published Jul 28 • 114
laion/1.7b-MixtureVitae-300BT-v1-decontaminated-16k-DPO-Tulu3-decontaminated-masked Text Generation • 2B • Updated Jul 18 • 7 • 1
LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget Paper • 2607.14952 • Published Jul 16 • 214
Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-Language Retrieval Paper • 2607.04605 • Published Jul 6 • 24