Chris

SWE-Vision. Python

jan. Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.

EgoMemo. Official Repo of Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos

Liger-Kernel. Efficient Triton Kernels for LLM Training

ViaRL. ViaRL: Adaptive Temporal Grounding via Visual Iterated Amplification Reinforcement Learning

Qwen-Agent. Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

ThinkingWithVideos. The official code of "Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning"

LongVT. [CVPR 2026] LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling

Video-o3. [ICML 2026] Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoning

Video-CoM. Video-CoM: Interactive Video Reasoning via Chain of Manipulations

WorldVQA. Python

EasyR1. EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

verl. verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

FlashPortrait. [CVPR2026]We present FlashPortrait, an end-to-end video diffusion transformer capable of synthesizing ID-preserving, infinite-length videos while achieving up to 6$\times$ acceleration in inference speed.

mllm-npu. mllm-npu: training multimodal large language models on Ascend NPUs

AISystem. AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

VLM-R1. Solve Visual Understanding with Reinforced VLMs

Logic-RL. Reproduce R1 Zero on Logic Puzzle

StableAnimator. [CVPR2025] We present StableAnimator, the first end-to-end ID-preserving video diffusion framework, which synthesizes high-quality videos without any post-processing, conditioned on a reference image and a sequence of poses.

llm.c. LLM training in simple, raw C/CUDA

MovieChat. [CVPR 2024] MovieChat: From Dense Token to Sparse Memory for Long Video Understanding

Awesome_Long_Form_Video_Understanding. Awesome papers & datasets specifically focused on long-term videos.

llm_interview_note. 主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

MotionFollower. [ICCV2025] MotionFollower: Editing Video Motion via Lightweight Score-Guided Diffusion

Open-Sora. Open-Sora: Democratizing Efficient Video Production for All