HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videos

A generative world for general-purpose robotics & embodied AI learning.

[ICLR 2025] MLLM for On-Demand Spatial-Temporal Understanding at Arbitrary Resolution

[NeurIPS 2024] Generalizable and Animatable Gaussian Head Avatar

[CVPR 2024] Official implementation of Morphable Diffusion: 3D-Consistent Diffusion for Single-image Avatar Creation

WiLoR: End-to-end 3D hand localization and reconstruction in-the-wild

A beautiful, simple, clean, and responsive Jekyll theme for academics

MiniCPM-o 2.6: A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone

Transformer Explained Visually: Learn How LLM Transformer Models Work with Interactive Visualization

[CVPR 2024] ID2Reflectance: Monocular Identity-Conditioned Facial Reflectance Reconstruction

Bring portraits to life!

InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥

[ECCV2024 - Oral] Adaptive Parametric Activation

[3DV'24] GAN-Avatar: Controllable Personalized GAN-based Human Head Avatar

[ECCV 2024 Oral🔥] Arc2Face: A Foundation Model for ID-Consistent Human Faces

The official implementatation of paper "BOTH2Hands: Inferring 3D Hands from Both Text Prompts and Body Dynamics".

[CVPR 2024 Highlight] Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis

The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.

GPT4V-level open-source multi-modal model based on Llama3-8B

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

(SIGGRAPH 2024) Portrait3D: Text-Guided High-Quality 3D Portrait Generation Using Pyramid Representation and GANs Prior

[EMNLP 2024] RWKV-CLIP: A Robust Vision-Language Representation Learner

[AAAI 2023 Oral] Domain-General Crowd Counting in Unseen Scenarios

[ICCV 2023] Controllable Person Image Synthesis with Pose‑Constrained Latent Diffusion

Official code for "Complementary Experts for Long-tailed Semi-Supervised Learning" (AAAI'2024)

[CVPR 2024] VkD : Improving Knowledge Distillation using Orthogonal Projections