zai-org/cogvlm2-llama3-caption
Video-Text-to-Text • 13B • Updated • 706 • 118
李佑軒
johnnyli1220
AI & ML interests
None yet
Recent Activity
upvoted a paper about 6 hours ago
JanusMesh: Fast and Zero-Shot 3D Visual Illusion Generation via Cross-Space Denoising upvoted a paper 3 days ago
BRDFusion: Physics Meets Generation for Urban Scene Inverse Rendering upvoted a paper 6 days ago
Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language ModelsOrganizations
None yet
liked a
model 4 months ago