Jaulaucoeng

LIBERO-plus. Official repository of LIBERO-plus, a generalized benchmark for in-depth robustness analysis of vision-language-action models.

Penguin-VL. Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders [Technical Report]

MergeVLA. [CVPR 2026] MergeVLA: Cross-Skill Model Merging Toward a Generalist Vision-Language-Action Agent

LangForce. [ICML 2026] This repo is the official implementation of "LangForce : Bayesian Decomposition of Vision Language Action Models via Latent Action Queries"

PromptTA. Source-free Domain Generalization

VLA-ADP. Action aware Dynamic Pruning for Efficient Vision Language Action Manipulation

le-wm. Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

FluxVLA. An all-in-one VLA engineering platform for embodied AI — from data to real-robot deployment.

VLD. Python

SVIP. Learning Source-free Domain Adaptation for Visible-Infrared Person Re-Identification (NeruIPS, 2025, Code)-SVIP

TTAC2. [TPAMI 2024] The official implementation of "Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering Regularized Self-Training"

NeurIPS25-CogVLA. [NeurIPS 2025] CogVLA: Cognition-Aligned Vision-Language-Action Models via Instruction-Driven Routing & Sparsification

starVLA. StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing

X-VLA. [ICLR 2026] The offical Implementation of "Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model"

TGA-ZSR. (TPAMI 2026) Complementary Text-Guided Attention for Zero-Shot Adversarial Robustness & & (NeurIPS 2024) Text-Guided Attention is All You Need for Zero-Shot Robustness in Vision-Language Models

VLA-Adapter-Real. The real-world system implementation of VLA-Adapter.

AnyTouch2. [ICLR 2026] AnyTouch 2: General Optical Tactile Representation Learning For Dynamic Tactile Perception

RLinf. RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI

CorrWiseLosses. Code for CVPR 2022 paper "Comparing Correspondences: Video Prediction with Correspondence-wise Losses"

F2BA. A tale of works on the complexity of first-order bilevel optimization.

SimpleVLA-RL. [ICLR 2026] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

LanguageBind. 【ICLR 2024🔥】 Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment

LLaMA2-Accessory. An Open-source Toolkit for LLM Development

LLaMA-Adapter. [ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

ImageBind-LoRA. Fine-tuning "ImageBind One Embedding Space to Bind Them All" with LoRA

VLA-Adapter. VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model

hand-on-rl. Python

AI-Notes. Bilibili东川路第一可爱猫猫虫的AI笔记

SpeechCLIP. SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model, Accepted to IEEE SLT 2022

Generalization-Causality. 关于domain generalization，domain adaptation，causality，robutness，prompt，optimization，generative model各式各样研究的阅读笔记

imagecorruptions. Python package to corrupt arbitrary images.

CBSA. [NeurIPS25 Spotlight] Official Implementation for CBSA (Contract-and-Broadcast Self-Attention)

GAMP.

HOS-Net. [AAAI-2024] High-Order Structure Based Middle-Feature Learning for Visible-Infrared Person Re-Identification

2024-ICML-TAC. Code for the paper "Image Clustering with External Guidance" (ICML 2024)

Awesome-Touch. Tactile Sensing • Data Collection • IL/RL/VLA/WM • Manipulation • Simulation • Open Source

Awesome-Robotics-Foundation-Models.

tvl. [ICML 2024] A Touch, Vision, and Language Dataset for Multimodal Alignment

VHKOR. Visual-Haptic-Kinesthetic Object Recognition with Multimodal Transformer

mvitac. Self-Supervised Visual-Tactile Representation Learning via Multimodal Contrastive Training

DGTR. Official Code for Dexterous Grasp Transformer (CVPR 2024)

TTST. [IEEE TIP 2024] TTST: A Top-k Token Selective Transformer for Remote Sensing Image Super-Resolution

pytorch-CycleGAN-and-pix2pix. Image-to-Image Translation in PyTorch

SGPA. Example code of Sparse Gaussian Process Attention (ICLR 2023)

Non-Local-Sparse-Attention. PyTorch code for our paper "Image Super-Resolution with Non-Local Sparse Attention" (CVPR2021).

LVM. Python

rebiber. A simple tool to update bib entries with their official information (e.g., DBLP or the ACL anthology).

LReID-KRKC. The official implementation of AAAI2023 Oral paper "Lifelong Person Re-Identification via Knowledge Refreshing and Knowledge Consolidation"

LifelongReID. offical implement of our Lifelong Person Re-Identification via Adaptive Knowledge Accumulation in CVPR2021

PythonGuide. 「Python学习+面试指南」一份涵盖大部分Python相关行业的程序员所需要掌握的核心知识。准备Python面试，来看PythonGuide!

awesome-machine-learning-1. Learning Resources And Links Of Machine Learning（updating）

research-method. 论文写作与资料分享

MFH. [ICLR 23 oral] The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge Distillation

DDPM. PyTorch DDPM implementation

SegDiff. Python

MedSegDiff. Using Diffusion Models to Segment/Reconstruct Organs from Medical Images [AAAI Most influential Paper]

USL-VI-ReID. The implementation of cvpr 2023 paper "Unsupervised Visible-Infrared Person Re-Identification via Progressive Graph Matching and Alternate Learning"

UNIReID. Towards Modality-Agnostic Person Re-identification with Descriptive Query CVPR2023

visual_prompting. Exploring Visual Prompts for Adapting Large-Scale Models

Visualizer. assistant tools for attention visualization in deep learning

PythonExercise. Python 编程练习题 100 例（源码），实例在 Python 3.6 环境下测试通过。

AISystem. AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

VehicleX. VehicleX: Simulating Content Consistent Vehicle Datasets with Attribute Descent (ECCV 2020, TPAMI 2023)

VVeRi-901-Trial. Python

PhD-Learning. Jianan Zhao, Fengliang Qi, GuangYu Ren, Lin Xu*. PhD Learning: Learning with Pompeiu-hausdorff Distances for Video-based Person Re-Identification. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2021.

CF-AAN. Video-based Person Re-identification without Bells and Whistles (CVPRw 2021)

CAViT. Python

awesome-reid-dataset. Collection of public available person re-identification datasets

multi-modal-vehicle-Re-ID. The multi-modal datasets and the codes of HAMNet.

Diffusion-based-Segmentation. This is the official Pytorch implementation of the paper "Diffusion Models for Implicit Image Segmentation Ensembles".

LLCM. [CVPR 2023] Diverse Embedding Expansion Network and Low-Light Cross-Modality Benchmark for Visible-Infrared Person Re-identification

FloW-Dataset. A dataset for floating waste detection in inland waters.

BTRDA. Python

Hypergraphs-Image-Inpainting. (WACV 2021) Hyperrealistic Image Inpainting with Hypergraphs

PyGCL. PyGCL: A PyTorch Library for Graph Contrastive Learning

LCCRF. Pytorch code for "Leaning Compact and Representative Features for Cross-Modality Person Re-Identification"(World Wide Web,CCF-B).

DCRN. [AAAI 2022] An official source code for paper Deep Graph Clustering via Dual Correlation Reduction.

Hetero-center-triplet-loss-for-VT-Re-ID. Python

SPConv.pytorch. [ IJCAI-20 ] Split to Be Slim: An Overlooked Redundancy in Vanilla Convolution

MITML. Python

GroupWhitening. This project is the PyTorch implementation of our accepted CVPR 2021 paper, Group Whitening: Balancing Learning Efficiency and Representational Capacity

dwt-domain-adaptation. Code for paper "Unsupervised Domain Adaptation using Feature-Whitening and Consensus Loss" (CVPR 2019)

PytorchWCT. This is the Pytorch implementation of Universal Style Transfer via Feature Transforms.

MSG-Transformer. MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokens (CVPR 2022)

MixMatch-pytorch. Code for "MixMatch - A Holistic Approach to Semi-Supervised Learning"

TBH. Auto-Encoding Twin-Bottleneck Hashing for CVPR2020

deep-cross-modal-hashing. Deep learning cross modal hashing in PyTorch

MyReidProject. Python

SAT. Official Pytorch code for Structure-Aware Transformer.

PMT. Code for paper (Lu, H., Zou, X., & Zhang, P. Learning progressive modality-shared transformers for effective visible-infrared person re-identification. In Proceedings of the AAAI conference on artificial intelligence (Vol. 37, No. 2, pp. 1835-1843).)

DCR-ReID_TCSVT2023. Python

pytorch_ConvUnitOptimization. This is the official repository of "Improving generalization of Batch Whitening by Convolutional Unit Optimization", ICCV 2021.

IterNorm-pytorch. This is the pytorch re-implementation of the IterNorm

Switchable-Whitening. Code for Switchable Whitening (ICCV2019)

Deep-Feature-Consistent-VAE. Pytorch Implementation of Hou, Shen, Sun, Qiu, "Deep Feature Consistent Variational Autoencoder", 2016

11785-Flow-VAE-dientanglement. Large-scale image generation on ImageNet

VQ-VAE. This is my implementation of Vector Quantized VAE trained on ImageNet data

ResNetVAE. Variational AutoEncoder + ResNet Transfer Learning

rq-vae-transformer. The official implementation of Autoregressive Image Generation using Residual Quantization (CVPR '22)

enhancing-transformers. An unofficial implementation of both ViT-VQGAN and RQ-VAE in Pytorch

transformer-vae. A library for making Transformer Variational Autoencoders. (Extends the Huggingface/transformers library.)

Machine-Learning-with-Graphs.

ADCA.

GCMT. Graph Consistency based Mean-Teaching for Unsupervised Domain Adaptive Person Re-Identification

SYSU-MM01. Introduction and evaluation code for RGB-IR re-id dataset SYSU-MM01.

Cross-Modal-Re-ID-baseline. Pytorch Code for Cross-Modality Person Re-Identification (Visible Thermal/Infrared Re-ID)

HiCMD. [CVPR2020] Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification

CutMix-PyTorch. Official Pytorch implementation of CutMix regularizer

simpleHRNET. Pose Detection (Simple HRNET)

hrnet. Python

HRNet. Implementation of HRNet

hrnet. Python

HRNet. A compact HRNet implementation in PyTorch