RAGU: A Multi-Step GraphRAG Engine with a Compact Domain-Adapted LLM Paper • 2607.11683 • Published 9 days ago • 132
RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources Paper • 2606.29538 • Published 6 days ago • 132
BadWAM: When World-Action Models Dream Right but Act Wrong Paper • 2607.15207 • Published 6 days ago • 52
SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration Paper • 2607.15257 • Published 6 days ago • 67
SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning Paper • 2607.14777 • Published 6 days ago • 95
VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Paper • 2607.14935 • Published 6 days ago • 162
LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget Paper • 2607.14952 • Published 6 days ago • 188
CyberHarem/shiina_mahiru_otonarinotenshisamaniitsunomanikadameningennisareteitaken Viewer • Updated Apr 9, 2024 • 1.84k • 42 • 1
Blind-Spots-Bench: Evaluating Blind Spots in Multimodal Models Paper • 2607.08317 • Published 13 days ago • 35
Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation Paper • 2607.11886 • Published 9 days ago • 83
Scalable Visual Pretraining for Language Intelligence Paper • 2607.09657 • Published 12 days ago • 56