arxiv:2602.09849

BagelVLA: Enhancing Long-Horizon Manipulation via Interleaved Vision-Language-Action Generation

Published on Feb 10

· Submitted by

Authors:

Abstract

BagelVLA is a unified Vision-Language-Action model that integrates linguistic planning, visual forecasting, and action generation through residual flow guidance for improved manipulation tasks.

AI-generated summary

Equipping embodied agents with the ability to reason about tasks, foresee physical outcomes, and generate precise actions is essential for general-purpose manipulation. While recent Vision-Language-Action (VLA) models have leveraged pre-trained foundation models, they typically focus on either linguistic planning or visual forecasting in isolation. These methods rarely integrate both capabilities simultaneously to guide action generation, leading to suboptimal performance in complex, long-horizon manipulation tasks. To bridge this gap, we propose BagelVLA, a unified model that integrates linguistic planning, visual forecasting, and action generation within a single framework. Initialized from a pretrained unified understanding and generative model, BagelVLA is trained to interleave textual reasoning and visual prediction directly into the action execution loop. To efficiently couple these modalities, we introduce Residual Flow Guidance (RFG), which initializes from current observation and leverages single-step denoising to extract predictive visual features, guiding action generation with minimal latency. Extensive experiments demonstrate that BagelVLA outperforms existing baselines by a significant margin on multiple simulated and real-world benchmarks, particularly in tasks requiring multi-stage reasoning.

View arXiv page View PDF Project page Add to collection

Community

Wiley085

Paper submitter 1 day ago

•

edited 1 day ago

BagelVLA is a unified model that integrates linguistic planning, visual forecasting, and action generation within a single framework for long-horizon manipulation tasks.

🧠 Model Architecture

BagelVLA utilizes a Mixture-of-Transformers (MoT) architecture, comprising three independent transformers specialized for linguistic, visual, and action modalities. To tackle long-horizon tasks and semantic generalization, we formulate language-conditioned action learning as a long-sequence interleaved planning problem. These modalities are structured into a unified sequence, enabling the model to generate predictions across all three modalities based on the interleaved context.

To address the high latency in combining visual generation with control, we introduce Residual Flow Guidance (RFG). Instead of generating future frames from scratch, RFG conditions on the current observation as a strong structural prior and performs single-step denoising to predict the residual change toward the next keyframe. RFG provides a lightweight predictive visual representation that captures task-relevant dynamics with minimal overhead. This substantially reduces the computational cost of foresight while preserving its utility for action generation.