bohan zeng

zbhpku's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 6 days ago

MosaicMem: Hybrid Spatial Memory for Controllable Video World Models

Paper • 2603.17117 • Published 7 days ago • 85

commented a paper 6 days ago

MosaicMem: Hybrid Spatial Memory for Controllable Video World Models

Paper • 2603.17117 • Published 7 days ago • 85 •

5

upvoted a paper 7 days ago

AvatarForcing: One-Step Streaming Talking Avatars via Local-Future Sliding-Window Denoising

Paper • 2603.14331 • Published 9 days ago • 14

upvoted a paper 19 days ago

BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning

Paper • 2603.04918 • Published 19 days ago • 55

liked a dataset 21 days ago

peteromallet/dataclaw-peteromallet

Viewer • Updated 27 days ago • 549 • 10.1k • 297

liked a model 27 days ago

Qwen/Qwen3.5-35B-A3B-FP8

Image-Text-to-Text • 36B • Updated 27 days ago • 2.2M • 121

upvoted 2 papers about 1 month ago

TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions

Paper • 2602.08711 • Published Feb 9 • 28

GENIUS: Generative Fluid Intelligence Evaluation Suite

Paper • 2602.11144 • Published Feb 11 • 55

upvoted 2 papers about 2 months ago

Semantic Routing: Exploring Multi-Layer LLM Feature Weighting for Diffusion Transformers

Paper • 2602.03510 • Published Feb 3 • 27

OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models

Paper • 2602.04804 • Published Feb 4 • 48

authored a paper about 2 months ago

Research on World Models Is Not Merely Injecting World Knowledge into Specific Tasks

Paper • 2602.01630 • Published Feb 2 • 49

upvoted a paper about 2 months ago

3D-Aware Implicit Motion Control for View-Adaptive Human Video Generation

Paper • 2602.03796 • Published Feb 3 • 64

commented a paper about 2 months ago

Research on World Models Is Not Merely Injecting World Knowledge into Specific Tasks

Paper • 2602.01630 • Published Feb 2 • 49 •

4

upvoted a paper about 2 months ago

Research on World Models Is Not Merely Injecting World Knowledge into Specific Tasks

Paper • 2602.01630 • Published Feb 2 • 49

submitted a paper to Daily Papers about 2 months ago

Research on World Models Is Not Merely Injecting World Knowledge into Specific Tasks

Paper • 2602.01630 • Published Feb 2 • 49

authored a paper about 2 months ago

VABench: A Comprehensive Benchmark for Audio-Video Generation

Paper • 2512.09299 • Published Dec 10, 2025 • 8

authored a paper 2 months ago

CoF-T2I: Video Models as Pure Visual Reasoners for Text-to-Image Generation

Paper • 2601.10061 • Published Jan 15 • 32

upvoted a paper 2 months ago

CoF-T2I: Video Models as Pure Visual Reasoners for Text-to-Image Generation

Paper • 2601.10061 • Published Jan 15 • 32

submitted a paper to Daily Papers 2 months ago

CoF-T2I: Video Models as Pure Visual Reasoners for Text-to-Image Generation

Paper • 2601.10061 • Published Jan 15 • 32

upvoted a paper 3 months ago

GARDO: Reinforcing Diffusion Models without Reward Hacking

Paper • 2512.24138 • Published Dec 30, 2025 • 30