Highlights
- Pro
Stars
HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency
Fast file synchronization and network forwarding for remote development
Paper Debugger is the best overleaf companion
Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interact with the model while enjoying updates from Anthropic.
A curated collection of papers, tutorials, videos, and other valuable resources related to Mamba.
Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference
Hydra is a framework for elegantly configuring complex applications
Code for the Interspeech 2021 paper "AST: Audio Spectrogram Transformer".
Extract video features from raw videos using multiple GPUs. We support RAFT flow frames as well as S3D, I3D, R(2+1)D, VGGish, CLIP, and TIMM models.
[CVPR 2023] Official repository of paper titled "Fine-tuned CLIP models are efficient video learners".
[CVPR'25] Code for ''Language-Guided Audio-Visual Learning for Long-Term Sports Assessment''
pytorch distribute tutorials
Open Source DeepWiki: AI-Powered Wiki Generator for GitHub/Gitlab/Bitbucket Repositories. Join the discord: https://discord.gg/gMwThUMeme
verl: Volcano Engine Reinforcement Learning for LLMs
Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.
DDPO for finetuning diffusion models, implemented in PyTorch with LoRA support
A cute running cat animation on your windows taskbar.
An official implementation of DanceGRPO: Unleashing GRPO on Visual Generation
Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis
one based on personal blog developed, specially for computer students to learn the blog search website, providing a variety of knowledge courses
Code release for ActionFormer (ECCV 2022)
Implementation of Non-local Block.
🚀MCP server for accessing RedNote(XiaoHongShu, xhs).