Zefeng He
- Papers
- 7
Cite
Notes
Only stored in your browser.
7papers
Authored papers
7GEMS: Agent-Native Multimodal Generation with Memory and Skills
arXiv 2026
Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs
arXiv 2026
LatentMem: Customizing Latent Memory for Multi-Agent Systems
arXiv 2026
DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models
arXiv 2025
VideoSSR: Video Self-Supervised Reinforcement Learning
arXiv 2025
FrameThinker: Learning to Think with Long Videos via Multi-Turn Frame Spotlighting
arXiv 2025
Spotlight on Token Perception for Multimodal Reinforcement Learning
arXiv 2025
Affiliations
No known affiliations.
Frequent co-authors
10from 7 papers