Joints, Camera, Action!
Co-Generating 3D Motion and Video for Arbitrary Rigs
View project →CodeTriage
Make Every Expansion Count: Learning to Search Efficiently in LLM Code Repair
View project →Self-Saliency
Look Where You Say You're Looking: Self-Grounded Attention for Visual Reasoning
View project →Bootstrap Your Generator
Unpaired Visual Editing with Flow Matching
View project →LoRWeB
Spanning the Visual Analogy Space with a Weight Basis of LoRAs
View project →UniProbe
A Learnable Token-Level Hallucination Detector for Large VLMs using Multi-Structural Internal Representations
View project →Fast 4D Mesh
Fast 4D Mesh Generation by Spatio-Temporal Attention Chains
View project →MaskedManipulator
Versatile Whole-Body Manipulation
View project →Video Storyboarding
Multi-Shot Character Consistency for Text-to-Video Generation
View project →Motion by Queries
Identity-Motion Trade-offs in Text-to-Video Generation
View project →Add-it
Training-Free Object Insertion in Images With Pretrained Diffusion Models
View project →MaskedMimic
Unified Physics-Based Character Control Through Masked Motion Inpainting
View project →ConsiStory
Training-Free Consistent Text-to-Image Generation
View project →PlaMo
Plan and Move in Rich 3D Physical Environments
View project →Perfusion
Key-Locked Rank One Editing for Text-to-Image Personalization
View project →CALM
Conditional Adversarial Latent Models for Directable Virtual Characters
View project →