HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model

• URL: http://arxiv.org/abs/2503.10631v3
• Date: Mon, 23 Jun 2025 07:37:53 GMT
• Title: HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model
• Authors: Jiaming Liu, Hao Chen, Pengju An, Zhuoyang Liu, Renrui Zhang, Chenyang Gu, Xiaoqi Li, Ziyu Guo, Sixiang Chen, Mengzhen Liu, Chengkai Hou, Mengdi Zhao, KC alex Zhou, Pheng-Ann Heng, Shanghang Zhang,
• Abstract summary: A fundamental objective of manipulation policy design is to endow robots to comprehend human instructions, reason about scene cues, and execute generalized actions in dynamic environments.<n>Recent autoregressive vision-language-action (VLA) methods inherit common-sense reasoning capabilities from vision-language models (VLMs) for next action-token prediction.<n>We introduce HybridVLA, a unified framework that absorbs the continuous nature of diffusion-based actions and the contextual reasoning of autoregression.
• Score: 54.64088247291416
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A fundamental objective of manipulation policy design is to endow robots to comprehend human instructions, reason about scene cues, and execute generalized actions in dynamic environments. Recent autoregressive vision-language-action (VLA) methods inherit common-sense reasoning capabilities from vision-language models (VLMs) for next action-token prediction. However, these methods quantize actions into discrete bins, which disrupts the continuity required for precise control. In contrast, existing diffusion-based VLA methods incorporate an additional diffusion head to predict continuous actions solely conditioned on feature representations extracted by the VLM, without fully leveraging the VLM's pretrained reasoning capabilities through token-level generation. To address these limitations, we introduce HybridVLA, a unified framework that absorbs the continuous nature of diffusion-based actions and the contextual reasoning of autoregression within a single large language model. To mitigate interference between the two generation paradigms, we propose a collaborative training recipe that seamlessly incorporates diffusion denoising into the next-token prediction process. With this recipe, we find these two action prediction methods not only reinforce each other but also exhibit varying strength across different tasks. Therefore, we design a collaborative action ensemble mechanism that adaptively fuses both predictions, leading to more robust control. HybridVLA outperforms previous state-of-the-art VLA methods by 14\% and 19\% in mean success rate on simulation and real-world tasks, respectively, while demonstrating stable manipulation in unseen configurations.

Related papers

• VITA: Vision-to-Action Flow Matching Policy [25.146609391293087]
  We present VITA, a Vision-To-Action flow matching policy that evolves latent visual representations into latent actions for visuomotor control.<n>VITA proposes a novel paradigm that treats latent images as the flow source, learning an inherent mapping from vision to action while eliminating separate conditioning modules.<n>VITA is evaluated on challenging bi-manual manipulation tasks on the ALOHA platform, including 5 simulation and 2 real-world tasks.
  arXiv  Detail & Related papers  (2025-07-17T15:41:57Z)
• Hybrid Autoregressive-Diffusion Model for Real-Time Streaming Sign Language Production [0.0]
  We introduce a hybrid approach combining autoregressive and diffusion models to generate Sign Language Production (SLP) models.<n>To capture fine-grained body movements, we design a Multi-Scale Pose Representation module that separately extracts detailed features from distinct arttors.<n>We also introduce a Confidence-Aware Causal Attention mechanism that utilizes joint-level confidence scores to dynamically guide the pose generation process.
  arXiv  Detail & Related papers  (2025-07-12T01:34:50Z)
• DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge [56.3802428957899]
  We propose DreamVLA, a novel VLA framework that integrates comprehensive world knowledge forecasting to enable inverse dynamics modeling.<n>DreamVLA introduces a dynamic-region-guided world knowledge prediction, integrated with the spatial and semantic cues, which provide compact yet comprehensive representations for action planning.<n>Experiments on both real-world and simulation environments demonstrate that DreamVLA achieves 76.7% success rate on real robot tasks.
  arXiv  Detail & Related papers  (2025-07-06T16:14:29Z)
• Consistent World Models via Foresight Diffusion [56.45012929930605]
  We argue that a key bottleneck in learning consistent diffusion-based world models lies in the suboptimal predictive ability.<n>We propose Foresight Diffusion (ForeDiff), a diffusion-based world modeling framework that enhances consistency by decoupling condition understanding from target denoising.
  arXiv  Detail & Related papers  (2025-05-22T10:01:59Z)
• CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models [89.44024245194315]
  We introduce a method that incorporates explicit visual chain-of-thought (CoT) reasoning into vision-language-action models (VLAs) We introduce CoT-VLA, a state-of-the-art 7B VLA that can understand and generate visual and action tokens. Our experimental results demonstrate that CoT-VLA achieves strong performance, outperforming the state-of-the-art VLA model by 17% in real-world manipulation tasks and 6% in simulation benchmarks.
  arXiv  Detail & Related papers  (2025-03-27T22:23:04Z)
• Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy [56.424032454461695]
  We present Dita, a scalable framework that leverages Transformer architectures to directly denoise continuous action sequences. Dita employs in-context conditioning -- enabling fine-grained alignment between denoised actions and raw visual tokens from historical observations. Dita effectively integrates cross-embodiment datasets across diverse camera perspectives, observation scenes, tasks, and action spaces.
  arXiv  Detail & Related papers  (2025-03-25T15:19:56Z)
• Enhanced Continual Learning of Vision-Language Models with Model Fusion [16.764069327701186]
  Vision-Language Models (VLMs) represent a breakthrough in artificial intelligence. VLMs are susceptible to catastrophic forgetting when sequentially fine-tuned on multiple downstream tasks. We propose Continual Decoupling-Unifying (ConDU), a novel approach, by introducing model fusion into continual learning.
  arXiv  Detail & Related papers  (2025-03-12T15:48:13Z)
• CLAD: Constrained Latent Action Diffusion for Vision-Language Procedure Planning [11.4414301678724]
  We propose a Constrained Latent Action Diffusion model for vision-language procedure planning in instructional videos.<n>Our method uses a Variational Autoencoder to learn the latent representation of actions and observations as constraints.<n>We show that our method outperforms state-of-the-art methods by a large margin.
  arXiv  Detail & Related papers  (2025-03-09T14:31:46Z)
• Controllable Motion Generation via Diffusion Modal Coupling [14.004287903552534]
  We propose a novel framework that enhances controllability in diffusion models by leveraging multi-modal prior distributions.<n>We evaluate our approach on motion prediction using a dataset and multi-task control in Maze2D environments.
  arXiv  Detail & Related papers  (2025-03-04T07:22:34Z)
• Accelerating Vision-Language-Action Model Integrated with Action Chunking via Parallel Decoding [24.1236728596359]
  Vision-Language-Action (VLA) models demonstrate remarkable potential for generalizable robotic manipulation.<n>We propose PD-VLA, the first parallel decoding framework for VLA models integrated with action chunking.<n>Our framework reformulates autoregressive decoding as a nonlinear system solved by parallel fixed-point iterations.
  arXiv  Detail & Related papers  (2025-03-04T06:12:08Z)
• Doubly-Universal Adversarial Perturbations: Deceiving Vision-Language Models Across Both Images and Text with a Single Perturbation [15.883062174902093]
  Large Vision-Language Models (VLMs) have demonstrated remarkable performance across multimodal tasks by integrating vision encoders with large language models (LLMs)<n>We introduce a novel UAP specifically designed for VLMs: the Doubly-Universal Adversarial Perturbation (Doubly-UAP)
  arXiv  Detail & Related papers  (2024-12-11T05:23:34Z)
• ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer [95.80384464922147]
  Continuous visual generation requires the full-sequence diffusion-based approach.<n>We present ACDiT, an Autoregressive blockwise Conditional Diffusion Transformer.<n>We demonstrate that ACDiT can be seamlessly used in visual understanding tasks despite being trained on the diffusion objective.
  arXiv  Detail & Related papers  (2024-12-10T18:13:20Z)
• Vision-Language-Action Model and Diffusion Policy Switching Enables Dexterous Control of an Anthropomorphic Hand [2.7036595757881323]
  We propose a hybrid control method that combines the relative advantages of a fine-tuned Vision-Language-Action model and diffusion models. We demonstrate this model switching approach results in a over 80% success rate compared to under 40% when only using a VLA model.
  arXiv  Detail & Related papers  (2024-10-17T20:49:45Z)
• Feedback-based Modal Mutual Search for Attacking Vision-Language Pre-training Models [8.943713711458633]
  We propose a new attack paradigm called Feedback-based Modal Mutual Search (FMMS) FMMS aims to push away the matched image-text pairs while randomly drawing mismatched pairs closer in feature space. This is the first work to exploit target model feedback to explore multi-modality adversarial boundaries.
  arXiv  Detail & Related papers  (2024-08-27T02:31:39Z)
• InterHandGen: Two-Hand Interaction Generation via Cascaded Reverse Diffusion [53.90516061351706]
  We present InterHandGen, a novel framework that learns the generative prior of two-hand interaction. For sampling, we combine anti-penetration and synthesis-free guidance to enable plausible generation. Our method significantly outperforms baseline generative models in terms of plausibility and diversity.
  arXiv  Detail & Related papers  (2024-03-26T06:35:55Z)
• Variance-Preserving-Based Interpolation Diffusion Models for Speech Enhancement [53.2171981279647]
  We present a framework that encapsulates both the VP- and variance-exploding (VE)-based diffusion methods. To improve performance and ease model training, we analyze the common difficulties encountered in diffusion models. We evaluate our model against several methods using a public benchmark to showcase the effectiveness of our approach.
  arXiv  Detail & Related papers  (2023-06-14T14:22:22Z)
• David helps Goliath: Inference-Time Collaboration Between Small Specialized and Large General Diffusion LMs [49.822063966687175]
  Diffusion-based language models are emerging as a promising alternative to autoregressive LMs. We propose methods to scale a recently proposed diffusion model SSD-LM from 0.4B to 13B parameters. We show that SSD-2 facilitates novel ensembles with 100x smaller models that can be customized and deployed by individual users.
  arXiv  Detail & Related papers  (2023-05-24T06:22:14Z)
• Diffusion Action Segmentation [63.061058214427085]
  We propose a novel framework via denoising diffusion models, which shares the same inherent spirit of such iterative refinement. In this framework, action predictions are iteratively generated from random noise with input video features as conditions.
  arXiv  Detail & Related papers  (2023-03-31T10:53:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.