Alternatives and similar repositories for Vision-Zero

Users that are interested in Vision-Zero are comparing it to the libraries listed below

• yihedeng9 / OpenVLThinker
  OpenVLThinker: An Early Exploration to Vision-Language Reasoning via Iterative Self-Improvement
  ☆129Updated 5 months ago
• yannqi / R-4B
  The official repository of "R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Integration"
  ☆134Updated 4 months ago
• callsys / GMPO
  Geometric-Mean Policy Optimization
  ☆96Updated 2 months ago
• VainF / Thinkless
  [NeurIPS 2025] Thinkless: LLM Learns When to Think
  ☆250Updated 3 months ago
• zli12321 / Vision-SR1
  Reinforcement Learning of Vision Language Models with Self Visual Perception Reward
  ☆158Updated 3 months ago
• Princeton-AI2-Lab / DeepOCR
  A reproduction of the Deepseek-OCR model including training
  ☆202Updated 2 months ago
• agents-x-project / PyVision
  [MTI-LLM@NeurIPS 2025] Official implementation of "PyVision: Agentic Vision with Dynamic Tooling."
  ☆144Updated 5 months ago
• NVlabs / GDPO
  Official implementation of GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
  ☆271Updated last week
• Princeton-AI2-Lab / Web-World-Models
  Official Project Page for Web World Models (https://arxiv.org/abs/2512.23676)
  ☆74Updated 2 weeks ago
• SHI-Labs / VisPer-LM
  [NeurIPS 2025] Elevating Visual Perception in Multimodal LLMs with Visual Embedding Distillation
  ☆70Updated 3 months ago
• We-Math / We-Math2.0
  The code and data of We-Math 2.0.
  ☆163Updated 4 months ago
• GAIR-NLP / LIMI
  LIMI: Less is More for Agency
  ☆158Updated 3 months ago
• JinjieNi / MegaDLMs
  GPU-optimized framework for training diffusion language models at any scale. The backend of Quokka, Super Data Learners, and OpenMoE 2 tr…
  ☆312Updated 2 months ago
• Gen-Verse / Open-AgentRL
  Demystifying Reinforcement Learning in Agentic Reasoning
  ☆149Updated 3 months ago
• xlang-ai / OSWorld-G
  [NeurIPS 2025 Spotlight] Scaling Computer-Use Grounding via UI Decomposition and Synthesis
  ☆141Updated 2 months ago
• CSfufu / Revisual-R1
  🚀ReVisual-R1 is a 7B open-source multimodal language model that follows a three-stage curriculum—cold-start pre-training, multimodal rei…
  ☆192Updated last month
• thu-coai / Glyph
  Official Repository for "Glyph: Scaling Context Windows via Visual-Text Compression"
  ☆552Updated 2 months ago
• xufangzhi / Genius
  [ACL 2025] A Generalizable and Purely Unsupervised Self-Training Framework
  ☆71Updated 7 months ago
• Haochen-Wang409 / Grasp-Any-Region
  Official implementation of "Grasp Any Region: Towards Precise, Contextual Pixel Understanding for Multimodal LLMs".
  ☆95Updated 2 months ago
• inclusionAI / Ring-V2
  Ring-V2 is a reasoning MoE LLM provided and open-sourced by InclusionAI.
  ☆89Updated 2 months ago
• PKU-YuanGroup / LLaVA-o1
  ☆56Updated last year
• mbzuai-oryx / LlamaV-o1
  [ACL 2025 🔥] Rethinking Step-by-step Visual Reasoning in LLMs
  ☆310Updated 7 months ago
• bingreeky / MemEvolve
  MemEvolve & EvolveLab
  ☆102Updated 3 weeks ago
• ASTRAL-Group / AlphaOne
  [EMNLP 2025 Main] AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time
  ☆89Updated 7 months ago
• SalesforceAIResearch / LATTE
  ☆68Updated 4 months ago
• si0wang / ThinkLite-VL
  ☆106Updated 7 months ago
• FreedomIntelligence / LongLLaVA
  LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via Hybrid Architecture
  ☆212Updated last year
• SakanaAI / RLT
  Training teachers with reinforcement learning able to make LLMs learn how to reason for test time scaling.
  ☆358Updated 6 months ago
• Vchitect / Evaluation-Agent
  [ACL2025 Oral & Award] Evaluate Image/Video Generation like Humans - Fast, Explainable, Flexible
  ☆114Updated 5 months ago
• Tencent / llm.hunyuan.T1
  ☆83Updated 9 months ago