Xin Wen
xwen99
AI & ML interests
self-supervised learning, object discovery
Recent Activity
upvoted a paper about 2 months ago
Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes upvoted a paper 4 months ago
SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents upvoted a paper 4 months ago
LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video GenerationOrganizations
