🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

OS-Sentinel

JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence

[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

[NeurIPS'25] GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents

JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence

GUI Grounding for Professional High-Resolution Computer Use

AndroidWorld is an environment and benchmark for autonomous agents

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

Building a comprehensive and handy list of papers for GUI agents

[ACL 2025] Code and data for OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis

[CVPR 2025] Magma: A Foundation Model for Multimodal AI Agents

Code repo for "WebArena: A Realistic Web Environment for Building Autonomous Agents"

ScaleCUA is the open-sourced computer use agents that can operate on corss-platform environments (Windows, macOS, Ubuntu, Android).

Official Repo for "Why Settle for One? Text-to-ImageSet Generation and Evaluation"

Code, benchmark and environment for "ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows"

Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey

MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding

Code for Research Project TLDR

Neural Code Intelligence Survey 2024; Reading lists and resources

[ICLR'25 Oral] UGround: Universal GUI Visual Grounding for GUI Agents

The model, data and code for the visual GUI Agent SeeClick

Code for "From Ideal to Real: Unified and Data-Efficient Dense Prediction for Real-World Scenarios"

Official Code for "Coser: Coordinating LLM-Based Persona Simulation of Established Roles"

[ICLR 2025] A trinity of environments, tools, and benchmarks for general virtual agents

Latest Advances on System-2 Reasoning

This is a collection of resources for computer-use GUI agents, including videos, blogs, papers, and projects.