ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model
Paper • 2603.22281 • Published • 17
Haichao Zhang
haichaozhang
AI & ML interests
Generative Models, Image&Video Synthesis, Trajectory Pred
Recent Activity
liked a Space 4 days ago
ssocean/Newborn_Article_Impact_Predict upvoted a paper 4 days ago
Demystifying When Pruning Works via Representation Hierarchies liked a model 5 days ago
Wan-AI/Wan2.1-VACE-1.3BOrganizations
None yet
submitted a
paper to Daily Papers 18 days ago
authored 4
papers 6 months ago
Camouflaged Image Synthesis Is All You Need to Boost Camouflaged Detection
Paper • 2308.06701 • Published • 1
OOSTraj: Out-of-Sight Trajectory Prediction With Vision-Positioning Denoising
Paper • 2404.02227 • Published
Dense Video Understanding with Gated Residual Tokenization
Paper • 2509.14199 • Published • 3
Neural Discrete Token Representation Learning for Extreme Token Reduction in Video Large Language Models
Paper • 2503.16980 • Published • 4