Stars
An open-source agent harness powered by the Qwen Omni Realtime API—see, hear, and act, with built-in memory.
DingTalk Workspace is an officially open-sourced cross-platform CLI tool from DingTalk. It unifies DingTalk’s full suite of product capabilities into a single package, is designed for both human us…
Resources and paper list for "Thinking with Images for LVLMs". This repository accompanies our survey on how LVLMs can leverage visual information for complex reasoning, planning, and generation.
[CVPR 2026] LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling
Interleaving Reasoning: Next-Generation Reasoning Systems for AGI
Official OpenClaw DingTalk channel plugin | 钉钉官方 OpenClaw 插件
Official Code for ICCV 2025 paper — Beyond Isolated Words: Diffusion Brush for Handwritten Text-Line Generation
Official code for NeurIPS 2025 paper "GRIT: Teaching MLLMs to Think with Images"
Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.
Python SDK for DingTalk Stream Mode API, Compared with the webhook mode, it is easier to access the DingTalk chatbot
OpenOCR: An Open-Source Toolkit for General-OCR Research and Applications, integrates a unified training and evaluation benchmark, commercial-grade OCR and Document Parsing systems, and faithful re…
CosyVoice_DPO_NOTES: Supercharge Your Cosyvoice model with Cutting-Edge DPO Fine-Tuning!
Everything about the SmolLM and SmolVLM family of models
📄 Awesome OCR multiple programing languages toolkits based on ONNX Runtime, OpenVINO, MNN, PaddlePaddle, TensorRT and PyTorch.
Summarize existing representative LLMs text datasets.
Monkey (LMM): Image Resolution and Text Label Are Important Things for Large Multi-modal Models (CVPR 2024 Highlight)
Python tutorial for DingTalk Open Platform 钉钉开放平台的 Python 教程
Awesome LLM compression research papers and tools.
[NeurIPS 2024 Datasets and Benchmarks Track] Closed-Loop E2E-AD Benchmark Enhanced by World Model RL Expert
A curated list of world models for autonomous driving.
Common used path planning algorithms with animations.
NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.
[CVPR 2025] Prompt Depth Anything
[NeurIPS'24] Official implementation of "HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priors"
[ICCV 2025] Official implementation of the paper “MagicDrive-V2: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control”