Starred repositories
63
stars
written in Python
Clear filter
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
Hierarchical Reasoning Model Official Release
Klavis AI (YC X25): MCP integration platforms that let AI agents use tools reliably at any scale
The open source platform for AI-native application development.
Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI (Kunlun Inc.), specializing in vision-language reasoning.
🔥 [ICCV 2025 Highlight] InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity
SDG is a specialized framework designed to generate high-quality structured tabular data.
PromptEnhancer is a prompt-rewriting tool, refining prompts into clearer, structured versions for better image generation.
[ICLR 2024] Official implementation of "TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting"
VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
( TPAMI2022 / CVPR2019 Oral ) Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation
Unified KV Cache Compression Methods for Auto-Regressive Models
[Neurips 2025] R-KV: Redundancy-aware KV Cache Compression for Reasoning Models
[NeurIPS 2025] PyTorch implementation of [ThinkSound], a unified framework for generating audio from any modality, guided by Chain-of-Thought (CoT) reasoning.
RLinf is a flexible and scalable open-source infrastructure designed for post-training foundation models (LLMs, VLMs, VLAs) via reinforcement learning.
llms 大模型 笔记50篇 此仓库包含关于机器学习、深度学习、计算机视觉、自然语言处理、大模型 爬虫等领域 项目实战
[CVPR 2025 Highlight] 3DTopia-XL: High-Quality 3D PBR Asset Generation via Primitive Diffusion
Lumina-DiMOO - An Open-Sourced Multi-Modal Large Diffusion Language Model
4DNeX: Feed-Forward 4D Generative Modeling Made Easy
[EMNLP'25] s3 - ⚡ Efficient & Effective Search Agent Training via RL for RAG (RLVR for Search with Minimal Data)
🛠️ DeepAgent: A General Reasoning Agent with Scalable Toolsets
Multi-Agent System Framework For Complex Tasks
The official implementation of Self-Play Preference Optimization (SPPO)
🏆 #1 Multi-LLM consensus framework | 550+ stars | 95% accuracy | 10+ LLM providers | Leading cell annotation tool