arxiv:2607.27380
🤝 Open to Collab
Juanxi Tian
Juanxi
AI & ML interests
Efficient AI & Gen AI
Recent Activity
upvoted a paper about 13 hours ago
Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes published a dataset 2 days ago
OpenEnvisionLab/WorldEngine authored a paper 6 days ago
VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System