Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning

本人的科研经验

Apply the pruning strategy for MobileNet_v2

[CVPR 2025] DEIM: DETR with Improved Matching for Fast Convergence

一些关于目标检测的脚本的改进思路代码，详细请看readme.md

The official implementation of "MoCaE: Mixture of Calibrated Experts Significantly Improves Accuracy in Object Detection"

DN-TOD

[TITS 2024] You Only Look Clusters for Tiny Object Detection in Aerial Images

Deep Learning for Person Re-identification: A Survey and Outlook

Implementation of the new SOTA for model based RL, from the paper "Improving Transformer World Models for Data-Efficient RL", in Pytorch

The implementation of various lightweight networks by using PyTorch. such as：MobileNetV2，MobileNeXt，GhostNet，ParNet，MobileViT、AdderNet，ShuffleNetV1-V2，LCNet，ConvNeXt，etc. ⭐⭐⭐⭐⭐

Tools to Design or Visualize Architecture of Neural Network

Bringing together outstanding artificial intelligence (AI) open source projects from around the world.

The official repo for [TGRS'22] "An Empirical Study of Remote Sensing Pretraining"

Yolo X, v3 ~ v12 and several Multi-Object Tracker(SORT, DeepSORT, ByteTrack, BoT-SORT, etc.) in MOT17 and VisDrone2019 Dataset. It uses a unified style and integrated tracker for easy embedding in …

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

PyTorch native quantization and sparsity for training and inference

YOLOE: Real-Time Seeing Anything [ICCV 2025]

(2020-2022)The PyTorch version of SiamFC，SiamRPN，DaSiamRPN, UpdateNet , SiamDW, SiamRPN++, SiamMask, SiamFC++, SiamCAR, SiamBAN, Ocean, LightTrack , TrTr, NanoTrack; Visual object tracking based on…

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

[IGARSS 2025 Oral] A Simple Aerial Detection Baseline of Multimodal Language Models.

Enjoy the magic of Diffusion models!

Simple Online Realtime Tracking with a Deep Association Metric

强化学习中文教程（蘑菇书🍄），在线阅读地址：https://datawhalechina.github.io/easy-rl/

[ISPRS 2024] Satellite Video Single Object Tracking: A Systematic Review and An Oriented Object Tracking Benchmark

A series of basic algorithms that are useful for video understanding, including Single Object Tracking (SOT), Video Object Segmentation (VOS) and so on.

This is the official code for the paper Visible and Clear: Finding Tiny Objects in Difference Map.

[CVPR 2025] "A Distractor-Aware Memory for Visual Object Tracking with SAM2"

🔥 Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos