Alternatives and similar repositories for LLM-I

Users that are interested in LLM-I are comparing it to the libraries listed below

• shulin16 / MMInA
  [ACL2025 Findings] Benchmarking Multihop Multimodal Internet Agents
  ☆48Updated 11 months ago
• MetaStone-AI / MetaStone-S1
  The open-source code of MetaStone-S1.
  ☆105Updated 6 months ago
• DCDmllm / HyperLLaVA
  Pytorch implementation of HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language Models
  ☆28Updated last year
• neulab / MultiUI
  Code for Paper: Harnessing Webpage Uis For Text Rich Visual Understanding
  ☆53Updated last year
• DualityRL / multi-attempt
  ☆19Updated 10 months ago
• TIGER-AI-Lab / VisualWebInstruct
  The official repo for "VisualWebInstruct: Scaling up Multimodal Instruction Data through Web Search" [EMNLP25]
  ☆37Updated this week
• GMLR-Penn / Multiplex-Thinking
  Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge
  ☆104Updated last week
• yannqi / R-4B
  The official repository of "R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Integration"
  ☆136Updated 5 months ago
• shangshang-wang / Resa
  Resa: Transparent Reasoning Models via SAEs
  ☆47Updated 4 months ago
• yale-nlp / refdpo
  ☆16Updated last year
• SparksJoe / Prism
  A Framework for Decoupling and Assessing the Capabilities of VLMs
  ☆43Updated last year
• sotopia-lab / sotopia-rl
  Sotopia-RL: Reward Design for Social Intelligence
  ☆46Updated last week
• callsys / GMPO
  [ICLR 2026] Geometric-Mean Policy Optimization
  ☆99Updated last week
• MLLM-Data-Contamination / MM-Detect
  This repo contains code for the paper "Both Text and Images Leaked! A Systematic Analysis of Data Contamination in Multimodal LLM"
  ☆17Updated 3 months ago
• ASTRAL-Group / AlphaOne
  [EMNLP 2025 Main] AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time
  ☆89Updated 7 months ago
• TIGER-AI-Lab / MEGA-Bench
  This repo contains the code for "MEGA-Bench Scaling Multimodal Evaluation to over 500 Real-World Tasks" [ICLR 2025]
  ☆77Updated 7 months ago
• jdf-prog / LLM-Engines
  ☆50Updated 8 months ago
• beichenzbc / BoostStep
  official code for "BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning"
  ☆37Updated last year
• DAMO-NLP-SG / LongPO
  [ICLR 2025] LongPO: Long Context Self-Evolution of Large Language Models through Short-to-Long Preference Optimization
  ☆43Updated 11 months ago
• SalesforceAIResearch / LATTE
  ☆68Updated 4 months ago
• TIGER-AI-Lab / One-Shot-CFT
  The official repo for “Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem” [EMNLP25]
  ☆33Updated 5 months ago
• facebookresearch / multimodal_rewardbench
  Multimodal RewardBench
  ☆60Updated 11 months ago
• JieyuZ2 / TaskMeAnything
  [NeurIPS 2024] A task generation and model evaluation system for multimodal language models.
  ☆73Updated last year
• microsoft / x-reasoner
  X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domains
  ☆50Updated 8 months ago
• tianyi-lab / C3PO
  [COLM 2025] "C3PO: Critical-Layer, Core-Expert, Collaborative Pathway Optimization for Test-Time Expert Re-Mixing"
  ☆19Updated 9 months ago
• SWE-EVO / SWE-EVO
  ☆32Updated last week
• open-compass / GPassK
  [ACL 2025] Are Your LLMs Capable of Stable Reasoning?
  ☆32Updated 6 months ago
• complex-reasoning / RPG
  [ICLR 2026] RPG: KL-Regularized Policy Gradient (https://arxiv.org/abs/2505.17508)
  ☆65Updated last week
• Yarayx / livelongbench
  The first spoken long-text dataset derived from live streams, designed to reflect the redundancy-rich and conversational nature of real-w…
  ☆13Updated 7 months ago
• OpenMOSS / rope_pp
  Beyond Real: Imaginary Extension of Rotary Position Embeddings for Long-Context LLMs
  ☆33Updated last month