Awesome Visual-Language-Action (VLA)

This repository contains a curated list of resources addressing the VLA (Visual Language Action).

If you find some ignored papers, feel free to create pull requests, or open issues.

Contributions in any form to make this list more comprehensive are welcome.

If you find this repository useful, a simple star should be the best affirmation. 😊

Feel free to share this list with others!

Overview

• Efficient-VLA
• Survey Paper
• Other Resources

• For an in-depth summary of selected papers, see Link

Year	Venue	Paper Title	Repository	Note
2026	arXiv	DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation		website
2026	arXiv	A Pragmatic VLA Foundation Model		website
2026	arXiv	TwinBrainVLA: Unleashing the Potential of Generalist VLMs for Embodied Tasks via Asymmetric Mixture-of-Transformers		---
2026	arXiv	Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization		website
2026	arXiv	RoboReward: General-Purpose Vision-Language Reward Models for Robotics	---	website 小参数专用模型胜过大VLM，“专用场景微调”比“通用机器人预训练”
2025	arXiv	MomaGraph: State-Aware Unified Scene Graphs with Vision-Language Model for Embodied Task Planning		website
2025	arXiv	Unified Embodied VLM Reasoning with Robotic Action via Autoregressive Discretized Pre-training	---	website VLA评价体系
2025	arXiv	Galaxea open-world dataset and g0 dual-system vla model		website
2025	arXiv	Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresight		Model & dataset
2025	arXiv	Motus: A Unified Latent Action World Model		website
2025	arXiv	XR-1: Towards Versatile Vision-Language-Action Models via Learning Unified Vision-Motion Representations		website
2025	arXiv	SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overhead		website
2025	arXiv	Training-Time Action Conditioning for Efficient Real-Time Chunking	---	---
2025	arXiv	Reinforcing Action Policies by Prophesying	---	website
2025	arXiv	Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresight		---
2025	arXiv	WholeBodyVLA: Towards Unified Latent VLA for Whole-body Loco-manipulation Control		website
2025	arXiv	RynnVLA-002: A Unified Vision-Language-Action and World Model		---
2025	arXiv	πRL: Online RL Fine-tuning for Flow-based Vision-Language-Action Models		website
2025	arXiv	X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model		website
2025	arXiv	RobustVLA: Robustness-Aware Reinforcement Post-Training for Vision-Language-Action Models	---	---
2025	arXiv	VLA-4D: Embedding 4D Awareness into Vision-Language-Action Models for SpatioTemporally Coherent Robotic Manipulation	---	---
2025	arXiv	Libero-plus: In-depth robustness analysis of vision-language-action models		website
2025	arXiv	TraceGen: World Modeling in 3D Trace Space Enables Learning from Cross-Embodiment Videos	---	website
2025	arXiv	VLA-Pruner: Temporal-Aware Dual-Level Visual Token Pruning for Efficient Vision-Language-Action Inference	---	---
2025	arXiv	Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment		---
2025	arXiv	Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model		website
2025	arXiv	Evo-0: Vision-language-action model with implicit spatial understanding		website
2025	arXiv	EvoVLA: Self-Evolving Vision-Language-Action Model		website
2025	arXiv	Towards Deploying VLA without Fine-Tuning: Plug-and-Play Inference-Time VLA Policy Steering via Embodied Evolutionary Diffusion	---	website
2025	arXiv	π0.6: a VLA That Learns From Experience	---	website
2025	ICCV	Robomm: All-in-one multimodal large model for robotic manipulation		website
2025	arXiv	InternVLA-M1: Latent Spatial Grounding for Instruction-Following Robotic Manipulation		Website
2025	CoRL	π0.5: a Vision-Language-Action Model with Open-World Generalization		Blog PI0.5
2025	CoRR	GR00T N1: An Open Foundation Model for Generalist Humanoid Robots		website
2025	arXiv	AnywhereVLA: Language-Conditioned Exploration and Mobile Manipulation		website
2025	arXiv	Hi robot: Open-ended instruction following with hierarchical vision-language-action models	---	Website
2025	arXiv	Fast: Efficient action tokenization for vision-language-action models		Website PI0-Fast
2025	CoRL	Dexvla: Vision-language model with plug-in diffusion expert for general robot control		website
2025	ICML	DiffusionVLA: Scaling Robot Foundation Models via Unified Diffusion and Autoregression	---	website DiVLA
2025	IROS	Agibot world colosseo: A large-scale manipulation platform for scalable and intelligent embodied systems		website GO-1
2025	arXiv	Fine-tuning vision-language-action models: Optimizing speed and success		Website OpenVLA-OFT
2025	CoRL	OpenVLA: An Open-Source Vision-Language-Action Model		Website
2025	ICLR	Latent action pretraining from videos		website LAPA
2024	RSS	Octo: An Open-Source Generalist Robot Policy		Website
2024	CoRR	π0: A Vision-Language-Action Flow Model for General Robot Control		Blog PI0
2024	arXiv	GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation	---	website
2024	ICLR	Unleashing large-scale video generative pre-training for visual robot manipulation		website GR1
2024	CoRL	Rekep: Spatio-temporal reasoning of relational keypoint constraints for robotic manipulation		website
2023	CoRL	Voxposer: Composable 3d value maps for robotic manipulation with language models		website
2023	CoRL	Rt-2: Vision-language-action models transfer web knowledge to robotic control	---	Website
2023	RSS	Learning fine-grained bimanual manipulation with low-cost hardware		Website ALOHA/ACT
2023	CoRL	Do as i can, not as i say: Grounding language in robotic affordances	---	website SayCan
2022	arXiv	Rt-1: Robotics transformer for real-world control at scale		website Blog

Efficient-VLA

Year	Venue	Paper Title	Repository	Note
2025	arXiv	Running VLAs at Real-time Speed		Blog
2025	arXiv	NanoVLA: Routing Decoupled Vision-Language Understanding for Nano-sized Generalist Robotic Policies	---	---
2025	arXiv	Action-aware dynamic pruning for efficient vision-language-action manipulation	---	---
2025	arXiv	Edgevla: Efficient vision-language-action models	---	---
2025	arXiv	Hume: Introducing System-2 Thinking in Visual-Language-Action Model		website
2025	CoRL	Flower: Democratizing generalist robot policies with efficient vision-language-action flow policies		website
2025	arXiv	Accelerating vision-language-action model integrated with action chunking via parallel decoding	---	---
2025	arXiv	Fine-tuning vision-language-action models: Optimizing speed and success		website
2025	arXiv	Nina: Normalizing flows in action. training vla models with normalizing flows		---
2025	ICCV	Saliency-aware quantized imitation learning for efficient robotic control	---	---
2025	arXiv	Don't Run with Scissors: Pruning Breaks VLA Models but They Can Be Recovered	---	website
2025	arXiv	VITA-VLA: Efficiently Teaching Vision-Language Models to Act via Action Expert Distillation		website
2025	arXiv	CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decoding		website
2025	arXiv	Omnisat: Compact action token, faster auto regression	---	---
2025	arXiv	RetoVLA: Reusing Register Tokens for Spatial Reasoning in Vision-Language-Action Models	---	demo
2025	arXiv	KV-Efficient VLA: A Method of Speed up Vision Language Model with RNN-Gated Chunked KV Cache		---
2025	arXiv	Fast ECoT: Efficient Embodied Chain-of-Thought via Thoughts Reuse	---	---
2025	arXiv	Ttf-vla: Temporal token fusion via pixel-attention integration for vision-language-action models	---	---
2025	arXiv	Unified Vision-Language-Action Model		website
2025	ICML	Otter: A vision-language-action model with text-aware visual feature extraction		Website
2025	arXiv	Sqap-vla: A synergistic quantization-aware pruning framework for high-performance vision-language-action models		---
2025	arXiv	Fastdrivevla: Efficient end-to-end driving via plug-and-play reconstruction-based token pruning	---	---
2025	RAL	TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation		Website
2025	arXiv	Smolvla: A vision-language-action model for affordable and efficient robotics	---	website
2025	arXiv	NORA: A Small Open-Sourced Generalist Vision-Language-Action Model for Embodied Tasks		Website
2025	arXiv	MoLe-VLA: Dynamic Layer-Skipping Vision-Language-Action Model via Mixture-of-Layers for Efficient Robot Manipulation		Website
2025	arXiv	EfficientVLA: Training‑Free Acceleration and Compression for Vision‑Language‑Action Models	---	---
2025	arXiv	Think Twice, Act Once: Token‑Aware Compression and Action Reuse for Efficient Inference in Vision‑Language‑Action Models	---	---
2025	arXiv	ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning	---	Website
2025	arXiv	OpenHelix: A Short Survey, Empirical Analysis, and Open-Source Dual-System VLA Model for Robotic Manipulation		Website
2025	arXiv	SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model		Website
2025	arXiv	Fast-in-Slow: A Dual-System Foundation Model Unifying Fast Manipulation within Slow Reasoning		Website
2025	arXiv	SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration	---	---
2025	arXiv	VLA‑Cache: Towards Efficient Vision‑Language‑Action Model via Adaptive Token Caching in Robotic Manipulation		---
2025	arXiv	SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning	---	---
2025	RSS	FAST: Efficient Action Tokenization for Vision-Language-Action Models	---	Website
2025	arXiv	Real-Time Execution of Action Chunking Flow Policies	---	Website
2025	arXiv	VOTE: Vision-Language-Action Optimization with Trajectory Ensemble Voting	---	---
2025	arXiv	BitVLA: 1-Bit Vision-Language-Action Models for Robotics Manipulation		---
2025	arXiv	SpecVLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptance	---	---
2024	NeurIPS	RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation		Website
2024	NeurIPS	DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution		---
2024	IROS	From LLMs to Actions: Latent Codes as Bridges in Hierarchical Robot Control	---	---
2024	CoRL	HIRT: Enhancing Robotic Control with Hierarchical Robot Transformers	---	---
2024	arXiv	Towards Synergistic, Generalized, and Efficient Dual-System for Robotic Manipulation	---	Website
2024	CoRL	Robotic Control via Embodied Chain-of-Thought Reasoning		Website

Survey Paper

Year	Venue	Paper Title	Repository	Note
2025	arXiv	An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challenges		website
2025	arXiv	A survey on efficient vision-language-action models		website
2025	arXiv	Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey		Blog
2025	arXiv	A Survey on Vision-Language-Action Models: An Action Tokenization Perspective		---
2025	arXiv	Vision-language-action models: Concepts, progress, applications and challenges	---	Blog
2025	arXiv	Vision language action models in robotic manipulation: A systematic review	---	---
2025	arXiv	Large vlm-based vision-language-action models for robotic manipulation: A survey		---
2025	Information Fusion	Exploring embodied multimodal large models: Development, datasets, and future directions	---	---
2025	arXiv	Pure Vision Language Action (VLA) Models: A Comprehensive Survey	---	---

Other Resources

• Paper List for VLN (Visual Language Navigation)
• Awesome-Efficient-VLA
• LeRobot: State-of-the-art Machine Learning for Real-World Robotics in Pytorch / LeRobot: Making AI for Robotics more accessible with end-to-end learning