Bee: A High-Quality Corpus and Full-Stack Suite to Unlock Advanced Fully Open MLLMs
Paper • 2510.13795 • Published • 60
MenghaoGuo
MenghaoGuo
AI & ML interests
Computer Vision, Visual Attention.
Recent Activity
upvoted a paper 9 days ago
Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction upvoted a paper 29 days ago
EEVEE: Towards Test-time Prompt Learning in the Real World for Self-Improving Agents liked a Space about 2 months ago
victor/pixal3d-studioOrganizations
authored a
paper 9 months ago
authored 3
papers about 1 year ago
CharacterGen: Efficient 3D Character Generation from Single Images with Multi-View Pose Canonicalization
Paper • 2402.17214 • Published • 2
Visual Attention Network
Paper • 2202.09741 • Published • 1
RBench-V: A Primary Assessment for Visual Reasoning Models with Multi-modal Outputs
Paper • 2505.16770 • Published • 12