VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Paper • 2607.14935 • Published 3 days ago • 120
SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration Paper • 2607.15257 • Published 3 days ago • 58
Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable Paper • 2607.13285 • Published 5 days ago • 196
SynthDocBench: Controlled Benchmark for Long-Context Visual Document Understanding Paper • 2607.10400 • Published 8 days ago • 69
4D Human-Scene Reconstruction from Low-Overlap Captures Paper • 2607.09125 • Published 9 days ago • 52
Motion4Motion: Motion Transfer Across Subjects at Inference Paper • 2607.11644 • Published 6 days ago • 10
ABot-N1: Toward a General Visual Language Navigation Foundation Model Paper • 2607.10383 • Published 5 days ago • 98
ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory Paper • 2607.10350 • Published 4 days ago • 82
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading Paper • 2607.08964 • Published 10 days ago • 74
Video Generation Models are General-Purpose Vision Learners Paper • 2607.09024 • Published 9 days ago • 79
Vidu S1: A Real-Time Interactive Video Generation Model Paper • 2607.03118 • Published 16 days ago • 138
Jet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPE Paper • 2607.07740 • Published 11 days ago • 23
Automating the Design of Embodied Agent Architectures Paper • 2606.30111 • Published 16 days ago • 13
Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning Paper • 2607.07508 • Published 11 days ago • 24