Alternatives and similar repositories for R-4B

Users that are interested in R-4B are comparing it to the libraries listed below

• agents-x-project / PyVision
  Official implementation of "PyVision: Agentic Vision with Dynamic Tooling."
  ☆133Updated 3 months ago
• yihedeng9 / OpenVLThinker
  OpenVLThinker: An Early Exploration to Vision-Language Reasoning via Iterative Self-Improvement
  ☆118Updated 3 months ago
• callsys / GMPO
  Geometric-Mean Policy Optimization
  ☆89Updated 3 weeks ago
• hewei2001 / ReachQA
  [EMNLP 2025] Distill Visual Chart Reasoning Ability from LLMs to MLLMs
  ☆56Updated 2 months ago
• We-Math / We-Math2.0
  The code and data of We-Math 2.0.
  ☆160Updated 2 months ago
• SalesforceAIResearch / LATTE
  ☆68Updated last month
• RUCAIBox / Virgo
  Official code of *Virgo: A Preliminary Exploration on Reproducing o1-like MLLM*
  ☆109Updated 5 months ago
• xufangzhi / Genius
  [ACL 2025] A Generalizable and Purely Unsupervised Self-Training Framework
  ☆71Updated 5 months ago
• SHI-Labs / VisPer-LM
  [NeurIPS 2025] Elevating Visual Perception in Multimodal LLMs with Visual Embedding Distillation, arXiv 2024
  ☆64Updated 3 weeks ago
• allenai / pixmo-docs
  ACL 2025: Synthetic data generation pipelines for text-rich images.
  ☆145Updated 8 months ago
• neulab / MultiUI
  Code for Paper: Harnessing Webpage Uis For Text Rich Visual Understanding
  ☆53Updated 11 months ago
• kxfan2002 / SophiaVL-R1
  SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward
  ☆86Updated 3 months ago
• MetaStone-AI / MetaStone-S1
  The open-source code of MetaStone-S1.
  ☆107Updated 3 months ago
• MBZUAI-LLM / web2code
  Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs
  ☆92Updated last year
• JieyuZ2 / TaskMeAnything
  [NeurIPS 2024] A task generation and model evaluation system for multimodal language models.
  ☆73Updated 11 months ago
• shulin16 / MMInA
  [ACL2025 Findings] Benchmarking Multihop Multimodal Internet Agents
  ☆47Updated 8 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 4 months ago
• wangqinsi1 / Vision-Zero
  This is the official Python version of Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play.
  ☆98Updated 3 weeks ago
• SparksJoe / Prism
  A Framework for Decoupling and Assessing the Capabilities of VLMs
  ☆43Updated last year
• microsoft / x-reasoner
  X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domains
  ☆49Updated 6 months ago
• FudanNLPLAB / MouSi
  ☆74Updated last year
• ASTRAL-Group / AlphaOne
  [EMNLP 2025 Main] AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time
  ☆85Updated 5 months ago
• PKU-YuanGroup / LLaVA-o1
  ☆55Updated 11 months ago
• zli12321 / Vision-SR1
  Reinforcement Learning of Vision Language Models with Self Visual Perception Reward
  ☆142Updated last month
• TIGER-AI-Lab / VL-Rethinker
  The official code of "VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning" [NeurIPS25]
  ☆164Updated 5 months ago
• metal-chart-generation / metal
  ☆40Updated 5 months ago
• FreedomIntelligence / LongLLaVA
  LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via Hybrid Architecture
  ☆211Updated 10 months ago
• Haochen-Wang409 / Grasp-Any-Region
  Official implementation of "Grasp Any Region: Towards Precise, Contextual Pixel Understanding for Multimodal LLMs".
  ☆88Updated last week
• beichenzbc / BoostStep
  official code for "BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning"
  ☆36Updated 9 months ago
• TIGER-AI-Lab / VisualWebInstruct
  The official repo for "VisualWebInstruct: Scaling up Multimodal Instruction Data through Web Search" [EMNLP25]
  ☆35Updated 2 months ago