Stars
[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.
Tongyi Deep Research, the Leading Open-source Deep Research Agent
✔（已完结）最全面的 深度学习 笔记【土堆 Pytorch】【李沐 动手学深度学习】【吴恩达 深度学习】【大飞 大模型Agent】
[NeurIPS 2025] Image editing is worth a single LoRA! 0.1% training data for fantastic image editing! Surpasses GPT-4o in ID persistence~ MoE ckpt released! Only 4GB VRAM is enough to run!
Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling
[SIGGRAPH Asia 2025] DreamO: A Unified Framework for Image Customization
[TPAMI 2026 & ICML 2024 Oral] Official repository of the SparseTSF paper: "SparseTSF: Modeling Long-term Time Series Forecasting with 1k Parameters". This work is developed by the Lab of Professor …
Repository for "FreDF: Learning to Forecast in the Transformed Domain"
[NeurIPS 2025] CodeCrash: Exposing LLM Fragility to Misleading Natural Language in Code Reasoning
[ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing
[SIGGRAPH 2025] LAM: Large Avatar Model for One-shot Animatable Gaussian Head
[ICLR 2024] Official implementation of "TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting"
[TMLR 2025] Thera: Aliasing-Free Arbitrary-Scale Super-Resolution with Neural Heat Fields
[ICCV2025] LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds
[ICCV 25] OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
[ICCV 2025] Code Implementation of "ArtEditor: Learning Customized Instructional Image Editor from Few-Shot Examples"
Di♪♪Rhythm: Blazingly Fast and Embarrassingly Simple End-to-End Full-Length Song Generation with Latent Diffusion
✨ A synthetic dataset generation framework that produces diverse coding questions and verifiable solutions - all in one framwork
A research repo for experiments about Reinforcement Finetuning
Pippo: High-Resolution Multi-View Humans from a Single Image
YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open