YangJiao

judgeval. The Continuous-Improvement Stack for Agents. Our environment data and evals power agent improvement and monitoring.

OpenART. Python

OSWorld-V2. OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks

RepWAM. Code for RepWAM: World Action Modeling with Representation Visual-Action Tokenizers

VeriLatent. Official code for Adaptive Inference-Time Scaling via Early-Step Latent Verification for Image Editing

CUA-Gym. Scalable pipeline for synthesizing verifiable RLVR training data for computer-use agents

Awesome-RL-GUI-Agents. A curated list of awesome RL in GUI Agent papers

AgentsMeetRL. Awesome List for Agentic RL

AwesomeOPD. Awesome List for On-Policy Distillation

gym-anything. Gym-Anything: Turn any Software into an Agent Environment

andrej-karpathy-skills. A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

hermes-agent. The agent that grows with you

molmoweb. Python

claw-eval. Claw-Eval is an evaluation harness for evaluating LLM as agents. All tasks verified by humans.

arxiv-monitor. HTML

GUI-Libra. Official code for paper "GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL"

skills. Public repository for Agent Skills

OpenRT. Open-source red teaming framework for MLLMs with 42+ attack methods

ml-unigen. UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and Generation

FreeInpaint. [AAAI 2026] FreeInpaint: Tuning-free Prompt Alignment and Visual Rationality Enhancement in Image Inpainting

UniREditBench. [ECCV 2026] Offline implementation of UniREditBench: A Unified Reasoning-based Image Editing Benchmark.

SCOPE. An implementation of SCOPE: Saliency-Coverage Oriented Token Pruning for Efficient Multimodel LLMs (NeurIPS 2025)

Metis-RISE. Metis-RISE: RL Incentivizes and SFT Enhances Multimodal Reasoning Model Learning

OpenCUA. [NeurIPS 2025 Spotlight] OpenCUA: Open Foundations for Computer-Use Agents

GLM-V. GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

CL4R1T4S. LEAKED SYSTEM PROMPTS FOR CHATGPT, CLAUDE, GEMINI, GROK, PERPLEXITY, CURSOR, LOVABLE, REPLIT, AND MORE! - AI SYSTEMS TRANSPARENCY FOR ALL! 👐

umt. A Pytorch Implementation of Unbiased Mean Teacher for Cross-domain Object Detection (CVPR 2021)

reka-vibe-eval. Multimodal language model benchmark, featuring challenging examples

Awesome_Think_With_Images. Resources and paper list for "Thinking with Images for LVLMs". This repository accompanies our survey on how LVLMs can leverage visual information for complex reasoning, planning, and generation.

ControlThinker. ControlThinker: Unveiling Latent Semantics for Controllable Image Generation through Visual Reasoning

Qwen-AD. Official implementation of "Look Before You Decide: Prompting Active Deduction of MLLMs for Assumptive Reasoning"

OmniGenBench. Python

describe-anything. [ICCV 2025] Implementation for Describe Anything: Detailed Localized Image and Video Captioning

r1_reward. ✨✨ [ICLR 2026] R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning

Awesome-Unified-Multimodal-Models. Awesome Unified Multimodal Models

SimpleAR. Pytorch implementation for the paper titled "SimpleAR: Pushing the Frontier of Autoregressive Visual Generation"

FlexVAR. Python

multimodal_rewardbench. Multimodal RewardBench

Awesome-MCoT. Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey

Awesome-RL-based-Reasoning-MLLMs. This repository provides valuable reference for researchers in the field of multimodality, please start your exploratory travel in RL-based Reasoning MLLMs!

DuMo. [AAAI 2025] DuMo: Dual Encoder Modulation Network for Precise Concept Erasure

MMoP. Multimodal Mixture of Prompt for Vision-Language Models

RECE. [ECCV 2024] Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Models

UniToken. [CVPRW 2025] UniToken is an auto-regressive generation model that combines discrete and continuous representations to process visual inputs, making it easy to integrate both visual understanding and image generation tasks seamlessly.

open-r1. Fully open reproduction of DeepSeek-R1

Kimi-k1.5.

OpenTokenizer. Python

genesis-world. Simulation platform for general-purpose robotics & embodied AI learning.

TokenFlow. [CVPR 2025] 🔥 Official impl. of "TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation".

TimeMarker. A Versatile Video-LLM for Long and Short Video Understanding with Superior Temporal Localization Ability

Emu3. Next-Token Prediction is All You Need

OVRE. Python

ReToMe-VA. [ACM MM 2024] ReToMe-VA: Recursive Token Merging for Video Diffusion-based Unrestricted Adversarial Attack

AdvQDet. [ACM MM 2024] AdvQDet: Detecting Query-Based Adversarial Attacks with Adversarial Contrastive Prompt Tuning

EventHallusion. EventHallusion: Diagnosing Event Hallucinations in Video LLMs

LAVIS. LAVIS - A One-stop Library for Language-Vision Intelligence

Lumina-mGPT. Official Implementation of "Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining"

IDForge. [MM24 Oral] Identity-Driven Multimedia Forgery Detection via Reference Assistance

SEED-Voken. SEED-Voken: A Series of Powerful Visual Tokenizers

chameleon. Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.

OmniTokenizer. [NeurIPS 2024]OmniTokenizer: one model and one weight for image-video joint tokenization.

FeatUp. Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024

DAC. [CVPR 2024] Official implementation of CVPR 2024 paper: "Doubly Abductive Counterfactual Inference for Text-based Image Editing"

DailyFood-172.

Lumen. [NeurIPS 2024] Lumen: a Large multimodal model with versatile vision-centric capabilities

InstaGen. InstaGen: Enhancing Object Detection by Training on Synthetic Dataset, CVPR2024

LLaVA-MoLE. Python

MDU_preprocess. Creating virtual 2D points via multi-depth projection

Griffon. Official repo of Griffon series including v1(ECCV 2024), v2(ICCV 2025), G, and R, and also the RL tool Vision-R1(CVPR 2026).

InternLM-XComposer. InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions

GCMA. [ACM MM2023] Code Release of GCMA: Generative Cross-Modal Transferable Adversarial Attacks from Images to Videos

Mapillary2COCO. Transfer Mapillary Vistas Dataset to Coco format

Qwen-VL. The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.

InstructDiffusion. PyTorch implementation of InstructDiffusion, a unifying and generic framework for aligning computer vision tasks with human instructions.

DriveAGI. [CVPR 2024 Highlight] GenAD: Generalized Predictive Model for Autonomous Driving

guidance. A guidance language for controlling large language models.

NuScenes-QA. [AAAI 2024] NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving Scenario.

SparseFusion. [ICCV 2023] SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection

BSC-Attack. [AAAI2022] Code Release of Attacking Video Recognition Models with Bullet-Screen Comments

Self-Universality. Enhancing the Self-Universality for Transferable Targeted Attacks [CVPR 2023 Paper]

segment-anything. The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

SurroundOcc. [ICCV 2023] SurroundOcc: Multi-camera 3D Occupancy Prediction for Autonomous Driving

3D-Dual-Fusion. [Arxiv 2022] This is the official implementation of 3D Dual-Fusion: Dual-Domain Dual-Query Camera-LiDAR Fusion for 3D Object Detection

SOLOFusion. Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection

GD-MAE. GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Clouds (CVPR 2023)

occupancy-for-nuscenes. 3D occupancy

ESOL_WSSS.

ProposalContrast. This repository contains the PyTorch implementation of the ECCV'2022 paper, ProposalContrast: Unsupervised Pre-training for LiDAR-based 3D Object Detection.

Occupancy-MAE. Official implementation of our TIV'23 paper: Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoders

BEV-MAE. [AAAI 2024] BEV-MAE: Bird's Eye View Masked Autoencoders for Point Cloud Pre-training in Autonomous Driving Scenarios

ViGA. "Video Moment Retrieval from Text Queries via Single Frame Annotation" in SIGIR 2022

AeDet. AeDet: Azimuth-invariant Multi-view 3D Object Detection, CVPR2023

PENet_ICRA2021. ICRA 2021 "Towards Precise and Efficient Image Guided Depth Completion"

MSMDFusion. [CVPR 2023] MSMDFusion: Fusing LiDAR and Camera at Multiple Scales with Multi-Depth Seeds for 3D Object Detection

MORE. [ECCV 2022] MORE: Multi-Order RElation Mining for Dense Captioning in 3D Scenes official implementation

MVP. Python

Transformer-backbone. The reproduce of Transformer architecture in paper "Attention is all your need"

sgmn. Graph-Structured Referring Expressions Reasoning in The Wild, In CVPR 2020, Oral.

Scan2Cap. [CVPR 2021] Scan2Cap: Context-aware Dense Captioning in RGB-D Scans

Heuristic_black_box_adversarial_attack_on_video_recognition_models. Python

TV-Net. The official code of MM 2021 paper "Two-stage Visual Cues Enhancement Network for Referring Image Segmentation"

Pointnet_Pointnet2_pytorch. PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.

CDistNet. Official Pytorch implementations of CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition（IJCV）

LBYLNet. [CVPR2021] Look before you leap: learning landmark features for one-stage visual grounding.

AugFPN. source code of AugFPN

Deformable-DETR. Deformable DETR: Deformable Transformers for End-to-End Object Detection.

vit-pytorch. Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

vision_transformer. Jupyter Notebook

Localization-VizDoom. C

attention-is-all-you-need-pytorch. A PyTorch implementation of the Transformer model in "Attention is All You Need".

UESTC_OS_experiment. 电子科技大学操作系统进程与资源管理实验代码（python）

fastNLP. fastNLP: A Modularized and Extensible NLP Framework. Currently still in incubation.

mcu_design. 三天三夜小组mcu设计