Open-source implementation of AlphaEvolve

AgentCompass is an extensible open-source evaluation infrastructure for systematically assessing LLM/VLM agent capabilities.

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Our library for RL environments + evals

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

reasoning-guided spatial visual token augmentation

主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

Entropy Based Sampling and Parallel CoT Decoding

🏞 A content-based image retrieval (CBIR) system

Large Reasoning Models

ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)

O1 Replication Journey

An extensible benchmark for evaluating large language models on planning

A collection of papers on the topic of ``Computer Vision in the Wild (CVinW)''

VisionLLaMA: A Unified LLaMA Backbone for Vision Tasks

[ECCV2024] Video Foundation Models & Data for Multimodal Understanding

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

[CVPR 2023 Highlight] InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions

Research Trends in LLM-guided Multimodal Learning.

CUDA programs for our training session.

📚 计算机经典编程书籍、大黑书、编程电子书、电子书、编程书籍，包括计算机基础、C/C++、Java、Python、面试题、架构设计、算法系列等经典电子书。

Deep Reinforcement Learning

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Pure Pytorch Docker Images.

Repo for counting stars and contributing. Press F to pay respect to glorious developers.