AI agents running research on single-GPU nanochat training automatically

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, …

Fully Open Framework for Democratized Multimodal Training

NEO Series: Native Vision-Language Models from First Principles

Hybrid Mamba-Attention for Efficient Entity Segmentation

[COLM 2025] Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources

🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!

real time face swap and one-click video deepfake with only a single image

[AAAI 2025]👔IMAGDressing👔: Interactive Modular Apparel Generation for Virtual Dressing. It enables customizable human image generation with flexible garment, pose, and scene control, ensuring high …

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

Project Page for "LISA: Reasoning Segmentation via Large Language Model"

[ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

Adblock Plus extension for Google Chrome

Apache ECharts is a powerful, interactive charting and data visualization library for browser

Collaborative JavaScript Debugging App

Enterprise Charts 【Baidu Hi : 1379172 | Email : echarts@baidu.com】