"OpenPhone: Mobile Agentic Foundation Models for AI Phone"

✔（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】

"MiniRAG: Making RAG Simpler with Small and Open-Sourced Language Models"

Efficient Track Anything

[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

Official implementation for "DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusion".

OmniRefiner: Reinforcement-Guided Local Diffusion Refinement

UltraFlux: Data-Model Co-Design for High-quality Native 4K Text-to-Image Generation across Diverse Aspect Ratios

Official inference repo for FLUX.2 models

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…

Code release for "UnSAMv2: Self-Supervised Learning Enables Segment Anything at Any Granularity"

UniWorld: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation

RepNeXt: A Fast Multi-Scale CNN using Structural Reparameterization

An extremely fast Python package and project manager, written in Rust.

Code for MIRO: MultI-Reward cOnditioned pretraining improves T2I quality and efficiency

Native Multimodal Models are World Learners

Edit-R1: Reinforce Image Editing with Diffusion Negative-Aware Finetuning and MLLM Implicit Feedback

Repo for SeedVR2 & SeedVR (CVPR2025 Highlight)

[Preprint 2025] Ditto: Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset

This project is the official implementation of 'DreamOmni2: Multimodal Instruction-based Editing and Generation''

Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

A minimal PyTorch re-implementation of Qwen3 VL with a fancy CLI

Echo-4o

我的 nano-banana 创意玩法大合集！ 持续更新中！

Official code for our ICCV2025 paper "SDMatte: Grafting Diffusion Models for Interactive Matting"

[AAAI2026] X-SAM: From Segment Anything to Any Segmentation