Jiajun Deng's starred repositories
Segment-Everything-Everywhere-All-At-Once
[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"
YOLO-World
[CVPR 2024] Real-Time Open-Vocabulary Object Detection
Video-ChatGPT
[ACL 2024 š„] Video-ChatGPT is a video conversation model capable of generating meaningful conversation about videos. It combines the capabilities of LLMs with a pretrained visual encoder adapted for spatiotemporal video representation. We also introduce a rigorous 'Quantitative Evaluation Benchmarking' for video-based conversational models.
home-robot
Mobile manipulation research tools for roboticists
Deformable-3D-Gaussians
[CVPR 2024] Official implementation of "Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction"
Neural-Network-Parameter-Diffusion
We introduce a novel approach for parameter generation, named neural network parameter diffusion (p-diff), which employs a standard latent diffusion model to synthesize a new set of parameters
Grounding-DINO-1.5-API
API for Grounding DINO 1.5: IDEA Research's Most Capable Open-World Object Detection Model Series
video2game
Code release of Video2Game
Agent-Driver
A Language Agent for Autonomous Driving
BunnyVisionPro
Bimanual Dexterous Teleoperation with Real-Time Retargeting using VisionPro
spoc-robot-training
SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real World
DeepEraser
The official code for āDeepEraser: Deep Iterative Context Mining for Generic Text Eraserā.