Instruct-tune LLaMA on consumer hardware

此项目是机器学习(Machine Learning)、深度学习(Deep Learning)、NLP面试中常考到的知识点和代码实现，也是作为一个算法工程师必会的理论基础知识。

Get started with building Fullstack Agents using Gemini 2.5 and LangGraph

llama3 implementation one matrix multiplication at a time

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

MiniCPM4 & MiniCPM4.1: Ultra-Efficient LLMs on End Devices, achieving 3+ generation speedup on reasoning tasks

Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)

Democratizing Reinforcement Learning for LLMs

Acceptance rates for the major AI conferences

Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.

Official repository of 'Visual-RFT: Visual Reinforcement Fine-Tuning' & 'Visual-ARFT: Visual Agentic Reinforcement Fine-Tuning'’

Official implementation for "Automatic Chain of Thought Prompting in Large Language Models" (stay tuned & more will be updated)

maximal update parametrization (µP)

Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

Codebase for Aria - an Open Multimodal Native MoE

A collection of notebooks/recipes showcasing usecases of open-source models with Together AI.

OLMoE: Open Mixture-of-Experts Language Models

[CVPR 2024] Alpha-CLIP: A CLIP Model Focusing on Wherever You Want

[NeurIPS 2021] [T-PAMI] DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

Person Re-ranking (CVPR 2017)

🔦 A Pytorch implementation of GoogleBrain's SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition

🧀 Code and models for the ICML 2023 paper "Grounding Language Models to Images for Multimodal Inputs and Outputs".

Action recognition using soft attention based deep recurrent neural networks

欢迎来到 "LLM-travel" 仓库！探索大语言模型（LLM）的奥秘 🚀。致力于深入理解、探讨以及实现与大模型相关的各种技术、原理和应用。

An implementation of our CVPR 2018 work 'Domain Adaptive Faster R-CNN for Object Detection in the Wild'

OpenThinkIMG is an end-to-end open-source framework that empowers LVLMs to think with images.

Official implementation of the paper "Attentive Eraser: Unleashing Diffusion Model’s Object Removal Potential via Self-Attention Redirection Guidance" (AAAI 2025 Oral)