Native Multimodal Models are World Learners

MiroMind Research Agent: Fully Open-Source Deep Research Agent with Reproducible State-of-the-Art Performance on FutureX, GAIA, HLE, BrowserComp and xBench.

A browser automation framework and ecosystem.

Playwright is a framework for Web Testing and Automation. It allows testing Chromium, Firefox and WebKit with a single API.

Contexts Optical Compression

Auto get diffusion nlp papers in Axriv. More papers Information can be found in another repository "Diffusion-LM-Papers".

Democratizing AI scientists with ToolUniverse

SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models

AG-UI: the Agent-User Interaction Protocol. Bring Agents into Frontend Applications.

A Gym for Agentic LLMs

An Unreal Engine plugin for LLM/GenAI models & MCP UE5 server. Supports Claude Desktop App, Windsurf & Cursor, also includes OpenAI's GPT 5, Deepseek V3.1, Claude Sonnet 4 APIs and Grok 4, with pla…

🎥 Make videos programmatically with React

GSM8K-V: Can Vision Language Models Solve Grade School Math Word Problems in Visual Contexts

RynnEC: Bringing MLLMs into Embodied World

[NeurIPS2025] "AI-Researcher: Autonomous Scientific Innovation" -- A production-ready version: https://novix.science/chat

Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference

ComoRAG is a Retrieval-Augmented Generation (RAG) system for long documents and multi-document QA, information extraction, and knowledge graph construction. It integrates various LLMs, embedding mo…

SSRL: Self-Search Reinforcement Learning

TraceRL & TraDo-8B: Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models

Tongyi Deep Research, the Leading Open-source Deep Research Agent

Simple, scalable AI model deployment on GPU clusters

[NeurIPS 2025] MMaDA - Open-Sourced Multimodal Large Diffusion Language Models

Official Implementation for the paper "d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning"

[COLM 2025] Code for Paper: Learning Adaptive Parallel Reasoning with Language Models

Agentic Web: Weaving the Next Web with AI Agents.

Benchmarking agent reasoning capabilities in physical interactions, tool usage, and multi-agent coordination.