Thinking Inertia: LLMs Keep Thinking When Told Not To Paper • 2610.11765 • Published 13 days ago • 243
Can MiniMax-H3 Reason About the Physical World? An Evaluation of Omni-Modal Generative Model Paper • 2609.18323 • Published Sep 16 • 116
Where Success Breaks: Failure-Boundary Learning for Robust Vision-Language-Action Models Paper • 2609.06114 • Published Sep 5
Kiwi-Edit: Versatile Video Editing via Instruction and Reference Guidance Paper • 2603.02175 • Published Mar 2 • 24
UniAPO: Unified Multimodal Automated Prompt Optimization Paper • 2508.17890 • Published Aug 25, 2025
JarvisHub: An Open Harness for Canvas-Native Multimodal Creative Agents Paper • 2607.23588 • Published Jul 26 • 87
Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories Paper • 2606.11176 • Published Jun 9 • 134
Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories Paper • 2606.11176 • Published Jun 9 • 134
Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories Paper • 2606.11176 • Published Jun 9 • 134
Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration Paper • 2605.17423 • Published May 17 • 31
Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration Paper • 2605.17423 • Published May 17 • 31