Skip to content

@EvolvingLMMs-Lab LMMs-Lab

Change the repository type filter

All

    Repositories list

    28 repositories

    • lmms-eval

      Public
      One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks
      evaluationagimultimodallarge-language-models
      Python
      •
      Other
      •444•3.3k•284•9•Updated Dec 5, 2025Dec 5, 2025

    • lmms-engine

      Public
      A simple, unified multimodal models training engine. Lean, flexible, and built for hacking at scale.
      agimultimodalvideo-generationlarge-language-modelsunified-multimodal-models
      Python
      •26•669•8•1•Updated Dec 5, 2025Dec 5, 2025

    • OpenMMReasoner

      Public
      OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipe
      Python
      •
      Apache License 2.0
      •3•116•1•0•Updated Dec 5, 2025Dec 5, 2025

    • LongVT

      Public
      LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling
      Python
      •
      Apache License 2.0
      •4•107•0•0•Updated Dec 4, 2025Dec 4, 2025

    • VLMEvalKit

      Public
      An open-source evaluation toolkit to evaluate MLLMs on Spatial Intelligence using the EASI protocol
      Python
      •
      Apache License 2.0
      •0•13•0•2•Updated Dec 4, 2025Dec 4, 2025

    • LLaVA-OneVision-1.5

      Public
      Fully Open Framework for Democratized Multimodal Training
      llmmllmvision-language-modelllavaqwen3
      Python
      •
      Apache License 2.0
      •45•643•27•1•Updated Dec 4, 2025Dec 4, 2025

    • EASI

      Public
      Holistic Evaluation of Multimodal LLMs on Spatial Intelligence
      multimodal-modelsmllmspatial-intelligencemllm-evaluation
      Apache License 2.0
      •3•45•2•0•Updated Dec 4, 2025Dec 4, 2025

    • NEO

      Public
      NEO Series: Native Vision-Language Models from First Principles
      Python
      •
      Apache License 2.0
      •15•280•0•0•Updated Oct 21, 2025Oct 21, 2025

    • .github

      Public
      1•1•0•1•Updated Sep 29, 2025Sep 29, 2025

    • multimodal-sae

      Public
      [ICCV 2025] Auto Interpretation Pipeline and many other functionalities for Multimodal SAE Analysis.
      Python
      •
      Other
      •9•166•4•0•Updated Sep 26, 2025Sep 26, 2025

    • VideoMMMU

      Public
      Python
      •
      Other
      •2•62•3•0•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
      •3.6k•3•0•0•Updated Aug 26, 2025Aug 26, 2025

    • multimodal-search-r1

      Public
      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
      •17•359•4•0•Updated Aug 26, 2025Aug 26, 2025

    • DiffSynth-Studio

      Public
      Enjoy the magic of Diffusion models!
      Python
      •
      Apache License 2.0
      •1k•0•0•0•Updated Aug 23, 2025Aug 23, 2025

    • lean-runner

      Public
      Deploying High-Performance Lean 4 Server in One Click
      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•52•4•0•Updated Jul 23, 2025Jul 23, 2025

    • sae

      Public
      A framework that allows you to apply Sparse AutoEncoder on any models
      Python
      •1•45•2•0•Updated Jul 11, 2025Jul 11, 2025

    • openevolve

      Public
      Open-source implementation of AlphaEvolve
      Python
      •
      Apache License 2.0
      •712•2•0•0•Updated Jun 20, 2025Jun 20, 2025

    • DeepEyes

      Public
      Python
      •
      Apache License 2.0
      •62•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
      •59•1•0•0•Updated Jun 14, 2025Jun 14, 2025

    • Aero-1

      Public
      Python
      •
      Apache License 2.0
      •6•78•3•0•Updated May 4, 2025May 4, 2025

    • EgoLife

      Public
      [CVPR 2025] EgoLife: Towards Egocentric Life Assistant
      ragegocentric-visionomnimodal
      Python
      •
      Other
      •19•352•9•0•Updated Mar 19, 2025Mar 19, 2025

    • LongVA

      Public
      Long Context Transfer from Language to Vision
      Python
      •
      Other
      •19•398•27•0•Updated Mar 18, 2025Mar 18, 2025

    • open-r1-multimodal

      Public
      A fork to add multimodal model training to open-r1
      Python
      •
      Apache License 2.0
      •68•1.4k•22•1•Updated Feb 8, 2025Feb 8, 2025

    • demos

      Public
      Python
      •0•0•0•0•Updated Sep 18, 2024Sep 18, 2024

    • DeepseekLeanPlayground

      Public
      The math library of Lean 4
      Lean
      •
      Apache License 2.0
      •912•0•0•0•Updated Aug 7, 2024Aug 7, 2024

    • Otter

      Public
      🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.
      machine-learningdeep-learningmulti-modalityartificial-inteligenceembodied-aigpt-4foundation-modelslarge-scale-modelsvisual-language-learningchatgpt
      Python
      •
      MIT License
      •208•3.3k•62•2•Updated Mar 5, 2024Mar 5, 2024

    • RelateAnything

      Public
      Relate Anything Model is capable of taking an image as input and utilizing SAM to identify the corresponding mask within the image.
      Python
      •
      Apache License 2.0
      •22•455•6•0•Updated Jul 4, 2023Jul 4, 2023