Skip to content

@EvolvingLMMs-Lab LMMs-Lab

Change the repository type filter

All

    Repositories list

    37 repositories

    • lmms-engine

      Public
      A simple, unified multimodal models training engine. Lean, flexible, and built for hacking at scale.
      agimultimodalvideo-generation
      agimultimodalvideo-generationlarge-language-modelsunified-multimodal-models
      Python
      •35•757•12•0•Updated Apr 9, 2026Apr 9, 2026

    • lmms-eval

      Public
      One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks
      benchmarkevaluationagi
      benchmarkevaluationagivideo-understandingvlmmultimodallarge-language-modelsvision-language-modelllm-evaluationaudio-evaluation
      Python
      •
      Other
      •558•4k•22•9•Updated Apr 9, 2026Apr 9, 2026

    • OneVision-Encoder

      Public
      Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence
      lmmsvision-transformerllava
      lmmsvision-transformerllava
      Python
      •
      Apache License 2.0
      •14•321•7•2•Updated Apr 9, 2026Apr 9, 2026

    • multimodal-search-r1

      Public
      [ACL-2026] MMSearch-R1 is an end-to-end RL framework that enables LMMs to perform on-demand, multi-turn search with real-world multimodal search tools.
      Python
      •
      Apache License 2.0
      •22•421•3•0•Updated Apr 7, 2026Apr 7, 2026

    • EASI

      Public
      Holistic Evaluation of Multimodal LLMs on Spatial Intelligence
      multimodal-modelsmllmspatial-intelligence
      multimodal-modelsmllmspatial-intelligencemllm-evaluation
      Python
      •
      Apache License 2.0
      •7•98•1•1•Updated Apr 3, 2026Apr 3, 2026

    • SimpleStream

      Public
      A simple video streaming baseline that outperforms SOTAs.
      Python
      •3•80•0•0•Updated Apr 3, 2026Apr 3, 2026

    • OpenMMReasoner

      Public
      [CVPR 2026] OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipe
      agivlmmultimodal
      agivlmmultimodalmllmmultimodal-large-language-modelslarge-multimodal-modelsmultimodal-reasoning
      Python
      •
      Apache License 2.0
      •7•156•5•0•Updated Mar 30, 2026Mar 30, 2026

    • LongVT

      Public
      [CVPR 2026] LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling
      agivlmmultimodal
      agivlmmultimodalmllmlong-video-understandingmultimodal-large-language-modelslarge-multimodal-modelstool-using-agent
      Python
      •
      Apache License 2.0
      •13•216•4•0•Updated Mar 27, 2026Mar 27, 2026

    • NEO

      Public
      NEO Series: Native Vision-Language Models from First Principles
      agivlmmultimodal
      agivlmmultimodallarge-language-modelsmllmmultimodal-large-language-modelsencoder-free-vlmnative-multimodal-model
      Python
      •
      Apache License 2.0
      •25•700•1•1•Updated Mar 23, 2026Mar 23, 2026

    • free_openclaw

      Public
      Notes for using openclaw
      PowerShell
      •0•1•0•0•Updated Mar 12, 2026Mar 12, 2026

    • co-scientist

      Public
      For AI Agents to post ideas on their owns.
      TypeScript
      •
      MIT License
      •0•5•0•0•Updated Mar 1, 2026Mar 1, 2026

    • .github

      Public
      1•1•0•2•Updated Mar 1, 2026Mar 1, 2026

    • lmms-lab-writer

      Public
      Agentic LaTeX Writer - Local-first editor for AI-assisted academic writing
      editorlatexai
      editorlatexaiwritingacademic-writing
      TypeScript
      •
      MIT License
      •11•109•6•0•Updated Feb 23, 2026Feb 23, 2026

    • VLMEvalKit

      Public
      An open-source evaluation toolkit to evaluate MLLMs on Spatial Intelligence using the EASI protocol
      Python
      •
      Apache License 2.0
      •0•18•0•0•Updated Feb 13, 2026Feb 13, 2026

    • engram

      Public
      Privacy-first AI memory layer - Signal for AI Memory. E2EE, local-first, works with Claude, Cursor, and any MCP-compatible AI.
      privacyencryptionai
      privacyencryptionaimemorymcpcursore2eeclaudelocal-firstllm
      TypeScript
      •
      Other
      •2•19•0•0•Updated Feb 13, 2026Feb 13, 2026

    • homebrew-tap

      Public
      Homebrew tap for LMMs-Lab applications
      Ruby
      •0•1•0•0•Updated Jan 29, 2026Jan 29, 2026

    • opencode

      Public
      The open source coding agent.
      TypeScript
      •
      MIT License
      •16k•1•0•0•Updated Jan 20, 2026Jan 20, 2026

    • LLaVA-OneVision-1.5

      Public
      Fully Open Framework for Democratized Multimodal Training
      llmmllmvision-language-model
      llmmllmvision-language-modelllavaqwen3
      Python
      •
      Apache License 2.0
      •61•788•39•7•Updated Dec 27, 2025Dec 27, 2025

    • LLaVA-OneVision-1.5-RL

      Public
      Fully Open Framework for Democratized Multimodal Reinforcement Learning.
      Python
      •
      Apache License 2.0
      •4•47•1•0•Updated Dec 19, 2025Dec 19, 2025

    • multimodal-sae

      Public
      [ICCV 2025] Auto Interpretation Pipeline and many other functionalities for Multimodal SAE Analysis.
      Python
      •
      Other
      •11•193•4•0•Updated Sep 26, 2025Sep 26, 2025

    • VideoMMMU

      Public
      Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos
      Python
      •
      Other
      •3•69•3•1•Updated Sep 5, 2025Sep 5, 2025

    • sglang

      Public
      SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.
      Python
      •
      Apache License 2.0
      •5.3k•3•0•0•Updated Aug 26, 2025Aug 26, 2025

    • DiffSynth-Studio

      Public
      Enjoy the magic of Diffusion models!
      Python
      •
      Apache License 2.0
      •1.2k•0•0•0•Updated Aug 23, 2025Aug 23, 2025

    • lean-runner

      Public
      Deploying High-Performance Lean 4 Server in One Click
      proverlean4
      proverlean4
      Python
      •
      MIT License
      •0•9•0•1•Updated Aug 14, 2025Aug 14, 2025

    • MGPO

      Public
      High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning
      0•54•4•0•Updated Jul 23, 2025Jul 23, 2025

    • sae

      Public
      A framework that allows you to apply Sparse AutoEncoder on any models
      Python
      •2•52•3•0•Updated Jul 11, 2025Jul 11, 2025

    • openevolve

      Public
      Open-source implementation of AlphaEvolve
      Python
      •
      Apache License 2.0
      •941•2•0•0•Updated Jun 20, 2025Jun 20, 2025

    • DeepEyes

      Public
      Python
      •
      Apache License 2.0
      •73•3•0•0•Updated Jun 16, 2025Jun 16, 2025

    • agent-rl

      Public
      A fork version of verl to support multi-turn tool use and many more agentic tasks.
      Python
      •
      MIT License
      •80•1•0•0•Updated Jun 14, 2025Jun 14, 2025

    • Aero-1

      Public
      Python
      •
      Apache License 2.0
      •6•78•4•0•Updated May 4, 2025May 4, 2025
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.