D$^2$-VLA: Dual-Memory Dual-Frequency Vision-Language-Action Model For Long Dynamic Manipulation

Zijian Ye; Chengqi Wei; Wei Huang; Anlin Zheng; Chunyu Zou; Liangyu Wu; Zikang Zhao; Zhenjie Peng; Yushuo Yang; Shuman Zhao; Zhongrui Wang; Xiaojuan Qi

arXiv · 2609.34792

D$^2$-VLA: Dual-Memory Dual-Frequency Vision-Language-Action Model For Long Dynamic Manipulation

Zijian Ye·Chengqi Wei·Wei Huang·Anlin Zheng·Chunyu Zou·Liangyu Wu·Zikang Zhao·Zhenjie Peng·Yushuo Yang·Shuman Zhao·Zhongrui Wang·Xiaojuan Qi

View original source ↗Read source document ↗Export metadata ↓

Abstract

Long-horizon manipulation requires robots to remember cues that are no longer in view while responding to moving objects. Yet vision-language-action (VLA) policies often rely on the latest observation, and refreshing their visual context typically requires another costly vision-language model (VLM) pass. We present D$^2$-VLA, which combines dual memory and dual-frequency control at the KV-cache interface of a pretrained VLA. D$^2$-VLA uses block-wise causal KV caching to encode observations incrementally and, guided by distinct temporal attention patterns, constructs separate historical KV read views for the VLM and action expert. Between periodic VLM updates, a gated adapter incorporates fresh visual features into the latest history-conditioned KV block, while a short fast-memory queue supports action replanning. We introduce DOMINO-Long, a ten-task benchmark requiring robots to use earlier visual cues when manipulating moving objects. D$^2$-VLA achieves complete-task success rates of 29.3\% on DOMINO, compared with 9.6\% for $π_{0.5}$ and 17.2\% for PUMA, and 60.0\% on DOMINO-Long, compared with 35.4\% and 20.6\%, respectively. It improves success rates on eight real-robot tasks and reaches 97.5\% on LIBERO-Long and 74.3\% on RoboTwin 2.0.

Explore related subjects

cs.CV

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Zijian Ye, Chengqi Wei, Wei Huang, Anlin Zheng, Chunyu Zou, Liangyu Wu, Zikang Zhao, Zhenjie Peng, Yushuo Yang, Shuman Zhao, Zhongrui Wang, Xiaojuan Qi. 2026-09-28. D$^2$-VLA: Dual-Memory Dual-Frequency Vision-Language-Action Model For Long Dynamic Manipulation. https://arxiv.org/abs/2609.34792

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Long-Tailed 3D Detection via Multi-Modal Fusion

Contemporary autonomous vehicle (AV) benchmarks have significantly advanced multimodal (LiDAR+RGB) 3D detection. However, despite the naturally long-tailed distribution of object classes, existing benchmarking protocols primarily focus on frequent categories (e.g., pedestrian and car), largely overlooking rare but safety-critical classes such as stroller and emergency vehicle. In practice, reliable detection of both common and rare classes is essential for safe autonomous driving. We formalize this problem as Long-Tailed 3D Detection (LT3D), where evaluation encompasses all annotated classes, including rare ones. To address LT3D, we introduce hierarchical losses that promote feature sharing across classes, diagnostic metrics that assign partial credit to semantically reasonable mistakes with respect to the semantic hierarchy (e.g., confusing a child with an adult), and a multimodal late-fusion (MMLF) framework to fuse detections. In particular, we show that rare-class accuracy benefits substantially from MMLF of independently trained uni-modal LiDAR and RGB detectors. Because of the modular design, unlike prevailing end-to-end trained multi-modal detectors that require paired LiDAR-RGB data, MMLF enables the use of advanced unimodal detectors that are trained on large-scale uni-modal datasets with sufficient data for rare classes. Lastly, we examine three fundamental design choices in MMLF, including the RGB detector representation (2D vs. 3D), cross-modal association (3D vs. image plane), and fusion strategy. We find that 2D RGB detectors recognize rare classes more reliably than 3D RGB detectors, image-plane association is more robust to depth estimation errors, and probabilistic score-calibrated fusion consistently yields the best performance. Extensive experiments on nuScenes and Argoverse2 demonstrate substantial improvements of MMLF, establishing a new state of the art.

cs.CV↗

arXiv2026

Towards Formal Verification of Deep Neural Networks for Object Detection

Deep neural networks (DNNs) are widely used in real-world computer vision applications, yet they remain vulnerable to errors and adversarial attacks. Formal verification offers a systematic approach to identify and mitigate these vulnerabilities, enhancing model robustness and reliability. While most existing verification methods focus on image classification models, this work extends formal verification to the more complex domain of object detection models. We propose a formulation for verifying the robustness of such models and demonstrate how state-of-the-art verification tools, originally developed for classification, can be adapted for this purpose. Through a comprehensive evaluation, we highlight the ability of formal verification to uncover vulnerabilities in object detection models, and derive formal robustness guarantees, underscoring the potential and need to further extend verification efforts in this domain. This work lays the foundation for further research into formal verification of object detection models across a broader range of computer vision applications. Our source code is publicly available online.

cs.CV↗

arXiv2026

Patch Rebirth: Fast and Transferable Model Inversion of Vision Transformers

Model inversion is a widely adopted technique in data-free learning that reconstructs synthetic inputs from a pretrained model through iterative optimization, without access to original training data. Unfortunately, its application to state-of-the-art Vision Transformers (ViTs) poses a major computational challenge, due to their expensive self-attention mechanisms. To address this, Sparse Model Inversion (SMI) was proposed to improve efficiency by pruning and discarding seemingly unimportant patches, which were even claimed to be obstacles to knowledge transfer. However, our empirical findings suggest the opposite: even randomly selected patches can eventually acquire transferable knowledge through continued inversion. This reveals that discarding any prematurely inverted patches is inefficient, as it suppresses the extraction of class-agnostic features essential for knowledge transfer, along with class-specific features. In this paper, we propose Patch Rebirth Inversion (PRI), a novel approach that incrementally detaches the most important patches during the inversion process to construct sparse synthetic images, while allowing the remaining patches to continue evolving for future selection. This progressive strategy not only improves efficiency, but also encourages initially less informative patches to gradually accumulate more class-relevant knowledge, a phenomenon we refer to as the Re-Birth effect, thereby effectively balancing class-agnostic and class-specific knowledge. Experimental results show that PRI achieves up to 10x faster inversion than standard Dense Model Inversion (DMI) and 2x faster than SMI, while consistently outperforming SMI in accuracy and matching the performance of DMI.

cs.CV↗