# A Self-Correcting Vision-Language-Action Model for Fast and Slow System Manipulation

arXiv: https://arxiv.org/abs/2405.17418 · HTML: https://mlsanity.com/paper/2405.17418/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 58 of its 69 references that are in the map.
- First posted on arXiv 27 May 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)
- Vision-language-action models / [Generalist VLA models and benchmarks](https://mlsanity.com/vla/generalist-vla-models-and-benchmarks/)

## Builds on (most cited first, 30 of 58)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention](https://mlsanity.com/paper/2303.16199/) (2023)
- [VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models](https://mlsanity.com/paper/2307.05973/) (2023)
- [RLBench: The Robot Learning Benchmark & Learning Environment](https://mlsanity.com/paper/1909.12271/) (2019)
- [LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model](https://mlsanity.com/paper/2304.15010/) (2023)
- [SAPIEN: A SimulAted Part-based Interactive ENvironment](https://mlsanity.com/paper/2003.08515/) (2020)
- [Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation](https://mlsanity.com/paper/2209.05451/) (2022)
- [PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding](https://mlsanity.com/paper/1812.02713/) (2018)
- [VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks](https://mlsanity.com/paper/2305.11175/) (2023)
- [Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots](https://mlsanity.com/paper/2402.10329/) (2024)
- [Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning](https://mlsanity.com/paper/2107.09645/) (2021)
- [Vision-Language Foundation Models as Effective Robot Imitators](https://mlsanity.com/paper/2311.01378/) (2023)
- [SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models](https://mlsanity.com/paper/2311.07575/) (2023)

## Built on by (most cited first, 21 of 21)

- [MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine](https://mlsanity.com/paper/2407.08739/) (2024)
- [Lift3D Foundation Policy: Lifting 2D Large-Scale Pretrained Models for Robust 3D Robotic Manipulation](https://mlsanity.com/paper/2411.18623/) (2024)
- [RoboFAC: A Comprehensive Framework for Robotic Failure Analysis and Correction](https://mlsanity.com/paper/2505.12224/) (2025)
- [Fast-in-Slow: A Dual-System Foundation Model Unifying Fast Manipulation within Slow Reasoning](https://mlsanity.com/paper/2506.01953/) (2025)
- [ManipLVM-R1: Reinforcement Learning for Reasoning in Embodied Manipulation with Large Vision-Language Models](https://mlsanity.com/paper/2505.16517/) (2025)
- [AIC MLLM: Autonomous Interactive Correction MLLM for Robust Robotic Manipulation](https://mlsanity.com/paper/2406.11548/) (2024)
- [Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trends](https://mlsanity.com/paper/2506.20966/) (2025)
- [AsyncVLA: Asynchronous Flow Matching for Vision-Language-Action Models](https://mlsanity.com/paper/2511.14148/) (2025)
- [Goal-VLA: Image-Generative VLMs as Object-Centric World Models Empowering Zero-shot Robot Manipulation](https://mlsanity.com/paper/2506.23919/) (2025)
- [Reinforcement Learning for Flow-Matching Policies](https://mlsanity.com/paper/2507.15073/) (2025)
- [CycleVLA: Proactive Self-Correcting Vision-Language-Action Models via Subtask Backtracking and Minimum Bayes Risk Decoding](https://mlsanity.com/paper/2601.02295/) (2026)
- [Aligning Multimodal LLM with Human Preference: A Survey](https://mlsanity.com/paper/2503.14504/) (2025)
- [EMMA: Generalizing Real-World Robot Manipulation via Generative Visual Transfer](https://mlsanity.com/paper/2509.22407/) (2025)
- [FLARE: A Failure-Aware Framework for Autonomous Correction and Recovery in Visual-Language Robotic Manipulation](https://mlsanity.com/paper/2608.26645/) (2026)
- [Sentinel-VLA: A Metacognitive VLA Model with Active Status Monitoring for Dynamic Reasoning and Error Recovery](https://mlsanity.com/paper/2605.01191/) (2026)
- [VISOR: A Vision-Language Model-based Test Oracle for Testing Robots](https://mlsanity.com/paper/2605.10408/) (2026)
- [SC2-WM: A Self-Correcting World Model with Closed-Loop Feedback for Vision-and-Language Navigation in Continuous Environments](https://mlsanity.com/paper/2608.07548/) (2026)
- [Perceiving, Reasoning, Adapting: A Dual-Layer Framework for VLM-Guided Precision Robotic Manipulation](https://mlsanity.com/paper/2503.05064/) (2025)
- [BLAZER: Bootstrapping LLM-based Manipulation Agents with Zero-Shot Data Generation](https://mlsanity.com/paper/2510.08572/) (2025)
- [Human-Aware Robot Behaviour in Self-Driving Labs](https://mlsanity.com/paper/2603.08420/) (2026)
- [Future Anchored Verification and Online Recovery for World Action Models](https://mlsanity.com/paper/2610.06280/) (2026)

## Abstract (arXiv)

Recently, some studies have integrated Multimodal Large Language Models into robotic manipulation, constructing vision-language-action models (VLAs) to interpret multimodal information and predict SE(3) poses. While VLAs have shown promising progress, they may suffer from failures when faced with novel and complex tasks. To emulate human-like reasoning for more robust manipulation, we propose the self-corrected (SC-)VLA framework, which integrates fast system for directly predicting actions and slow system for reflecting on failed actions within a single VLA policy. For the fast system, we incorporate parameter-efficient fine-tuning to equip the model with pose prediction capabilities while preserving the inherent reasoning abilities of MLLMs. For the slow system, we propose a Chain-of-Thought training strategy for failure correction, designed to mimic human reflection after a manipulation failure. Specifically, our model learns to identify the causes of action failures, adaptively seek expert feedback, reflect on the current failure scenario, and iteratively generate corrective actions, step by step. Furthermore, a continuous policy learning method is designed based on successfully corrected samples, enhancing the fast system's adaptability to the current configuration. We compare SC-VLA with the previous SOTA VLA in both simulation and real-world tasks, demonstrating an efficient correction process and improved manipulation accuracy on both seen and unseen tasks.