Alternatives and similar repositories for LLaVA-VLA

Users that are interested in LLaVA-VLA are comparing it to the libraries listed below

• PKU-HMI-Lab / Hybrid-VLA
  HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model
  ☆333Updated 3 months ago
• InternRobotics / InternVLA-M1
  InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy
  ☆342Updated 2 weeks ago
• baaivision / UniVLA
  Unified Vision-Language-Action Model
  ☆260Updated 3 months ago
• Zhangwenyao1 / DreamVLA
  [NeurIPS 2025] DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge
  ☆279Updated 2 weeks ago
• Zhoues / RoboRefer
  [NeurIPS 2025] Official implementation of "RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics"
  ☆220Updated last month
• RoboDita / Dita
  ICCV2025
  ☆146Updated last month
• OpenHelix-Team / VLA-RFT
  VLA-RFT: Vision-Language-Action Models with Reinforcement Fine-Tuning
  ☆117Updated 3 months ago
• qizekun / SoFar
  [NeurIPS 2025 Spotlight] SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation
  ☆221Updated 6 months ago
• pickxiguapi / Embodied-R1
  Official code for "Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation"
  ☆117Updated 5 months ago
• InternRobotics / InternVLA-A1
  InternVLA-A1: Unifying Understanding, Generation, and Action for Robotic Manipulation​
  ☆263Updated last week
• InternRobotics / F1-VLA
  F1: A Vision Language Action Model Bridging Understanding and Generation to Actions
  ☆154Updated 2 weeks ago
• InternRobotics / InstructVLA
  InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation
  ☆91Updated 3 months ago
• HeegerGao / VLA-OS
  Official Code For VLA-OS.
  ☆136Updated 6 months ago
• EmbodiedCity / Embodied-R.code
  ☆87Updated 8 months ago
• Fanqi-Lin / OneTwoVLA
  Official implementation of "OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoning"
  ☆206Updated 7 months ago
• hume-vla / hume
  🦾 A Dual-System VLA with System2 Thinking
  ☆131Updated 5 months ago
• alibaba-damo-academy / RynnVLA-001
  RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation
  ☆277Updated last month
• GuanxingLu / vlarl
  Single-file implementation to advance vision-language-action (VLA) models with reinforcement learning.
  ☆383Updated 2 months ago
• lmzpai / roboMamba
  The repo of paper `RoboMamba: Multimodal State Space Model for Efficient Robot Reasoning and Manipulation`
  ☆149Updated last year
• OpenHelix-robot / awesome-dual-system-vla
  A comprehensive list of papers about dual-system VLA models, including papers, codes, and related websites.
  ☆99Updated 2 months ago
• 2toinf / X-VLA
  The offical Implementation of "Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model"
  ☆436Updated last week
• JiuTian-VL / Large-VLM-based-VLA-for-Robotic-Manipulation
  A curated list of large VLM-based VLA models for robotic manipulation.
  ☆313Updated last month
• PKU-HMI-Lab / LIFT3D
  [CVPR 2025]Lift3D Foundation Policy: Lifting 2D Large-Scale Pretrained Models for Robust 3D Robotic Manipulation
  ☆174Updated 7 months ago
• BridgeVLA / BridgeVLA
  ✨✨【NeurIPS 2025】Official implementation of BridgeVLA
  ☆164Updated 4 months ago
• BAAI-DCAI / SpatialBot
  The official repo for "SpatialBot: Precise Spatial Understanding with Vision Language Models.
  ☆327Updated 4 months ago
• DelinQu / awesome-vision-language-action-model
  Latest Advances on Vison-Language-Action Models.
  ☆127Updated 10 months ago
• declare-lab / Emma-X
  Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning
  ☆79Updated 8 months ago
• aiming-lab / GRAPE
  GRAPE: Guided-Reinforced Vision-Language-Action Preference Optimization
  ☆155Updated 9 months ago
• showlab / EVOLVE-VLA
  EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models
  ☆58Updated last month
• MINT-SJTU / Evo-1
  Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment
  ☆199Updated last month