VLM3: Vision Language Models Are Native 3D Learners
Paper • 2605.30561 • Published • 20
Hongje Seong
hongjeseong
AI & ML interests
None yet
Recent Activity
upvoted a paper 1 day ago
VLM3: Vision Language Models Are Native 3D Learners upvoted a paper 6 days ago
Geometry-Aware Representation Denoising for Robust Multi-view 3D ReconstructionOrganizations
None yet
upvoted 2
papers 1 day ago
upvoted 6
papers 6 days ago
Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction
Paper • 2605.26230 • Published • 41
SpatialBench: Is Your Spatial Foundation Model an All-Round Player?
Paper • 2605.27367 • Published • 70
LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding
Paper • 2605.27365 • Published • 135
CubePart: An Open-Vocabulary Part-Controllable 3D Generator
Paper • 2605.28763 • Published • 14
Fast-dDrive: Efficient Block-Diffusion VLM for Autonomous Driving
Paper • 2605.23163 • Published • 17
GEM: Generative Supervision Helps Embodied Intelligence
Paper • 2605.28548 • Published • 40
upvoted a paper 8 days ago
upvoted a paper 13 days ago
upvoted a paper 20 days ago
upvoted a paper 23 days ago
upvoted 4
papers about 1 month ago
Image Generators are Generalist Vision Learners
Paper • 2604.20329 • Published • 21
Vista4D: Video Reshooting with 4D Point Clouds
Paper • 2604.21915 • Published • 12
Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation
Paper • 2604.18168 • Published • 96
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
Paper • 2604.14268 • Published • 122