Evaluation code and datasets for the ACL 2024 paper, VISTA: Visualized Text Embedding for Universal Multi-Modal Retrieval. The original code and model can be accessed at FlagEmbedding.

Official implement of CIKM2025: 《UniECS: Unified Multimodal E-Commerce Search Framework with Gated Cross-modal Fusion》

(CVPR 2025 highlight✨) Official repository of paper "LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models"

LLM inference in C/C++

Official PyTorch Implementation of Correlation Verification for Image Retrieval, CVPR 2022 (Oral Presentation)

Effortless data labeling with AI support from Segment Anything and other awesome models.

[DEIMv2] Real Time Object Detection Meets DINOv3

Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

gguf (GPT-Generated Unified Format) connector

RepVGG: Making VGG-style ConvNets Great Again

Nano vLLM

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

Detect Anything via Next Point Prediction (Based on Qwen2.5-VL-3B)

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.

OCR, layout analysis, reading order, table recognition in 90+ languages

Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning, achieving state-of-the-art performance on 38 out of 60 public benchmarks.

ClashX 是一个以Clash为内核的MAC系统翻墙工具。

OpenMMLab Model Deployment Framework

PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT

This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025

[Preprint] On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification.

Recipes for shrinking, optimizing, customizing cutting edge vision models. 💜

将SmolVLM2的视觉头与Qwen3-0.6B模型进行了拼接微调

An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models

Some out-of-the-box hooks for pre-commit

A PyTorch-based knowledge distillation toolkit for natural language processing

Text-audio foundation model from Boson AI

verl: Volcano Engine Reinforcement Learning for LLMs