Starred repositories
🤟 Visual Alignment Constraint for Continuous Sign Language Recognition. ( ICCV 2021)
💡 Resources about Sign Language Processing (e.g., Sign Language Recognition / Translation / Production)
Fast SAM 3D Body: Accelerating SAM 3D Body for Real-Time Full-Body Human Mesh Recovery
A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.
Predicting the generation FID of latent diffusion, with a variant of reconstruction FID of Variational Auto-encoder.
HY-Motion model for 3D human motion or 3D character animation generation.
Official implementation of GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
Helios: Real Real-Time Long Video Generation Model
[CVPR 2026🔥] 🧑🎨 OmniLottie, an open-sourced multi-modal instructed vector animation generator that produces Lottie JSONs.
[ICLR 26 Oral] Stable Video Infinity: Infinite-Length Video Generation with Error Recycling
Qwen3.5 is the large language model series developed by Qwen team, Alibaba Cloud.
SteadyDancer: Harmonized and Coherent Human Image Animation with First-Frame Preservation
Official Implementation of iMF https://arxiv.org/abs/2512.02012
Official Implementation of pMF https://arxiv.org/abs/2601.22158
A tool for creating and sharing Code Vein builds.
Fast, Sharp & Reliable Agentic Intelligence
Official repository for “PixelGen: Pixel Diffusion Beats Latent Diffusion with Perceptual Loss”
NVIDIA FastGen: Fast Generation from Diffusion Models
Momentum Human Rig is an anatomically-inspired parametric full-body digital human model developed at Meta. It includes: A parametric body skeletal model; A realistic 3D mesh skinned to the skeleton…
Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders
[ ECCV 2024 ] MotionLCM: This repo is the official implementation of "MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model"
Attempt to make multiple residual streams from Bytedance's Hyper-Connections paper accessible to the public
implementations and experimentation on mHC by deepseek - https://arxiv.org/abs/2512.24880
OmniControl: Control Any Joint at Any Time for Human Motion Generation, ICLR 2024
HumanML3D: A large and diverse 3d human motion-language dataset.
The official PyTorch implementation of the paper "Human Motion Diffusion Model"