Weijie Wang
3 papers · Latest:
Computer Vision
World-R1: Reinforcing 3D Constraints for Text-to-Video Generation
World-R1 uses reinforcement learning to enforce 3D constraints in text-to-video generation, improving geometric consistency without architectural changes.
2604.24764
Computer VisionDiffusion Model as a Generalist Segmentation Learner
DiGSeg repurposes diffusion models for versatile, text-conditioned segmentation across diverse domains without custom architectures.
2604.24575
Computer VisionFeed-Forward 3D Scene Modeling: A Problem-Driven Perspective
This survey introduces a problem-driven taxonomy for feed-forward 3D scene modeling, focusing on model design strategies over output representations.
2604.14025
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.