MVTrack4Gen: Multi-View Point Tracking as Geometric Supervision for 4D Video Generation
Paper • 2606.26087 • Published • 29
JeonSeongHu
JeonSeongHu
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 5 months ago
CAMEO: Correspondence-Attention Alignment for Multi-View Diffusion Models upvoted a paper 5 months ago
CANVAS: A Benchmark for Vision-Language Models on Tool-Based User Interface DesignOrganizations
None yet
upvoted a paper 1 day ago
upvoted 3
papers 5 months ago
CAMEO: Correspondence-Attention Alignment for Multi-View Diffusion Models
Paper • 2512.03045 • Published • 3
CANVAS: A Benchmark for Vision-Language Models on Tool-Based User Interface Design
Paper • 2511.20737 • Published • 3
Vision-aligned Latent Reasoning for Multi-modal Large Language Model
Paper • 2602.04476 • Published • 14
updated 2
models over 2 years ago
updated a
Space almost 3 years ago