Stars
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)
🌟100+ 原创 LLM / RL 原理图📚，《大模型算法》作者巨献！💥（100+ LLM/RL Algorithm Maps ）
verl: Volcano Engine Reinforcement Learning for LLMs
SeCap: Self-Calibrating and Adaptive Prompts for Cross-view Person Re-Identification in Aerial-Ground Networks (CVPR'25)
Pytorch implementation of 'Clothes-Changing Person Re-identification with RGB Modality Only. In CVPR, 2022.'
[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model
强化学习中文教程（蘑菇书🍄），在线阅读地址：https://datawhalechina.github.io/easy-rl/
from MHA, MQA, GQA to MLA by 苏剑林, with code
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
RAG兴趣小组，全手写的一个RAG应用。Langchain的大部分库会很方便，但是你不一定理解其中原理，所以代码尽可能展现基本算法，主打理解RAG的原理
A collection of AWESOME things about mixture-of-experts
PyTorch Re-Implementation of "The Sparsely-Gated Mixture-of-Experts Layer" by Noam Shazeer et al. https://arxiv.org/abs/1701.06538
[NeurIPS 2022] “M³ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design”, Hanxue Liang*, Zhiwen Fan*, Rishov Sarkar, Ziyu Jiang, Tianlong Che…
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
From scratch implementation of a sparse mixture of experts language model inspired by Andrej Karpathy's makemore :)
【IEEE TITS2025】Unity is Strength: Unifying Convolutional and Transformeral Features for Better Person Re-Identification
【AAAI2025】MambaPro: Multi-Modal Object Re-Identification with Mamba Aggregation and Synergistic Prompt
[CVPR 2023] Official repository of paper titled "MaPLe: Multi-modal Prompt Learning".
Implementation of Patch-wise Adversarial Regularization from "Learning Robust Global Representations by Penalizing Local Predictive Power"
Official Implementation for Flare-Aware Cross-modal Enhancement for Multi-spectral Vehicle ReID
[NeruIPS2024] RLE: A Unified Perspective of Data Augmentation for Cross-Spectral Re-identification
Welcome to the Awesome Multi-Modal Object Re-Identification Repository! This repository is dedicated to curating and sharing the latest methods, datasets, and resources focused specifically on the …
[CVPR 2023] Diverse Embedding Expansion Network and Low-Light Cross-Modality Benchmark for Visible-Infrared Person Re-identification
[CVPR2024]Day-Night Cross-domain Vehicle Re-identification