arXiv subjects

Dong Wang

Publications and source records attributed to Dong Wang.

At least 271 records · Page 15Linked to original sources

arXiv2025

COHERENT: Collaboration of Heterogeneous Multi-Robot System with Large Language Models

Leveraging the powerful reasoning capabilities of large language models (LLMs), recent LLM-based robot task planning methods yield promising results. However, they mainly focus on single or multiple homogeneous robots on simple tasks. Practically, complex long-horizon tasks always require collaboration among multiple heterogeneous robots especially with more complex action spaces, which makes these tasks more challenging. To this end, we propose COHERENT, a novel LLM-based task planning framework for collaboration of heterogeneous multi-robot systems including quadrotors, robotic dogs, and robotic arms. Specifically, a Proposal-Execution-Feedback-Adjustment (PEFA) mechanism is designed to decompose and assign actions for individual robots, where a centralized task assigner makes a task planning proposal to decompose the complex task into subtasks, and then assigns subtasks to robot executors. Each robot executor selects a feasible action to implement the assigned subtask and reports self-reflection feedback to the task assigner for plan adjustment. The PEFA loops until the task is completed. Moreover, we create a challenging heterogeneous multi-robot task planning benchmark encompassing 100 complex long-horizon tasks. The experimental results show that our work surpasses the previous methods by a large margin in terms of success rate and execution efficiency. The experimental videos, code, and benchmark are released at https://github.com/MrKeee/COHERENT.

cs.RO↗

arXiv2025

Improving Transferable Targeted Attacks with Feature Tuning Mixup

Deep neural networks (DNNs) exhibit vulnerability to adversarial examples that can transfer across different DNN models. A particularly challenging problem is developing transferable targeted attacks that can mislead DNN models into predicting specific target classes. While various methods have been proposed to enhance attack transferability, they often incur substantial computational costs while yielding limited improvements. Recent clean feature mixup methods use random clean features to perturb the feature space but lack optimization for disrupting adversarial examples, overlooking the advantages of attack-specific perturbations. In this paper, we propose Feature Tuning Mixup (FTM), a novel method that enhances targeted attack transferability by combining both random and optimized noises in the feature space. FTM introduces learnable feature perturbations and employs an efficient stochastic update strategy for optimization. These learnable perturbations facilitate the generation of more robust adversarial examples with improved transferability. We further demonstrate that attack performance can be enhanced through an ensemble of multiple FTM-perturbed surrogate models. Extensive experiments on the ImageNet-compatible dataset across various DNN models demonstrate that our method achieves significant improvements over state-of-the-art methods while maintaining low computational cost.

cs.CV↗

arXiv2025

Topology preserving Image segmentation using the iterative convolution-thresholding method

Variational models are widely used in image segmentation, with various models designed to address different types of images by optimizing specific objective functionals. However, traditional segmentation models primarily focus on the visual attributes of the image, often neglecting the topological properties of the target objects. This limitation can lead to segmentation results that deviate from the ground truth, particularly in images with complex topological structures. In this paper, we introduce a topology-preserving constraint into the iterative convolution-thresholding method (ICTM), resulting in the topology-preserving ICTM (TP-ICTM). Extensive experiments demonstrate that, by explicitly preserving the topological properties of target objects-such as connectivity-the proposed algorithm achieves enhanced accuracy and robustness, particularly in images with intricate structures or noise.

cs.CV↗

arXiv2025

AlignBot: Aligning VLM-powered Customized Task Planning with User Reminders Through Fine-Tuning for Household Robots

This paper presents AlignBot, a novel framework designed to optimize VLM-powered customized task planning for household robots by effectively aligning with user reminders. In domestic settings, aligning task planning with user reminders poses significant challenges due to the limited quantity, diversity, and multimodal nature of the reminders. To address these challenges, AlignBot employs a fine-tuned LLaVA-7B model, functioning as an adapter for GPT-4o. This adapter model internalizes diverse forms of user reminders-such as personalized preferences, corrective guidance, and contextual assistance-into structured instruction-formatted cues that prompt GPT-4o in generating customized task plans. Additionally, AlignBot integrates a dynamic retrieval mechanism that selects task-relevant historical successes as prompts for GPT-4o, further enhancing task planning accuracy. To validate the effectiveness of AlignBot, experiments are conducted in real-world household environments, which are constructed within the laboratory to replicate typical household settings. A multimodal dataset with over 1,500 entries derived from volunteer reminders is used for training and evaluation. The results demonstrate that AlignBot significantly improves customized task planning, outperforming existing LLM- and VLM-powered planners by interpreting and aligning with user reminders, achieving 86.8% success rate compared to the vanilla GPT-4o baseline at 21.6%, reflecting a 65% improvement and over four times greater effectiveness. Supplementary materials are available at: https://yding25.com/AlignBot/

cs.RO↗

arXiv2025

MoMa-Kitchen: A 100K+ Benchmark for Affordance-Grounded Last-Mile Navigation in Mobile Manipulation

In mobile manipulation, navigation and manipulation are often treated as separate problems, resulting in a significant gap between merely approaching an object and engaging with it effectively. Many navigation approaches primarily define success by proximity to the target, often overlooking the necessity for optimal positioning that facilitates subsequent manipulation. To address this, we introduce MoMa-Kitchen, a benchmark dataset comprising over 100k samples that provide training data for models to learn optimal final navigation positions for seamless transition to manipulation. Our dataset includes affordance-grounded floor labels collected from diverse kitchen environments, in which robotic mobile manipulators of different models attempt to grasp target objects amidst clutter. Using a fully automated pipeline, we simulate diverse real-world scenarios and generate affordance labels for optimal manipulation positions. Visual data are collected from RGB-D inputs captured by a first-person view camera mounted on the robotic arm, ensuring consistency in viewpoint during data collection. We also develop a lightweight baseline model, NavAff, for navigation affordance grounding that demonstrates promising performance on the MoMa-Kitchen benchmark. Our approach enables models to learn affordance-based final positioning that accommodates different arm types and platform heights, thereby paving the way for more robust and generalizable integration of navigation and manipulation in embodied AI. Project page: \href{https://momakitchen.github.io/}{https://momakitchen.github.io/}.

cs.RO↗

arXiv2025

Evolution of Adaptive Force Chains in Reconfigurable Granular Metamaterials

Under an externally applied load, granular packings form force chains that depend on the contact network and moduli of the grains. In this work, we investigate packings of variable modulus (VM) particles, where we can direct force chains by changing the Young's modulus of individual particles within the packing on demand. Each VM particle is made of a silicone shell that encapsulates a core made of a low-melting-point metallic alloy (Field's metal). By sending an electric current through a co-located copper heater, the Field's metal internal to each particle can be melted via Joule heating, which softens the particle. As the particle cools to room temperature, the alloy solidifies and the particle recovers its original modulus. To optimize the mechanical response of granular packings containing both soft and stiff particles, we employ an evolutionary algorithm coupled with discrete element method simulations to predict the patterns of particle moduli that will yield specific force outputs on the assembly boundaries. The predicted patterns of particle moduli from the simulations were realized in experiments using 2D assemblies of VM particles and the force outputs on the assembly boundaries were measured using photoelastic techniques. These studies represent a step towards making robotic granular metamaterials that can dynamically adapt their mechanical properties in response to different environmental conditions or perform specific tasks on demand.

cond-mat.soft↗

arXiv2025

LiveScene: Language Embedding Interactive Radiance Fields for Physical Scene Rendering and Control

This paper scales object-level reconstruction to complex scenes, advancing interactive scene reconstruction. We introduce two datasets, OmniSim and InterReal, featuring 28 scenes with multiple interactive objects. To tackle the challenge of inaccurate interactive motion recovery in complex scenes, we propose LiveScene, a scene-level language-embedded interactive radiance field that efficiently reconstructs and controls multiple objects. By decomposing the interactive scene into local deformable fields, LiveScene enables separate reconstruction of individual object motions, reducing memory consumption. Additionally, our interaction-aware language embedding localizes individual interactive objects, allowing for arbitrary control using natural language. Our approach demonstrates significant superiority in novel view synthesis, interactive scene control, and language grounding performance through extensive experiments. Project page: https://livescenes.github.io.

cs.CV↗

arXiv2025

THz Beam Squint Mitigation via 3D Rotatable Antennas

Analog beamforming holds great potential for future terahertz (THz) communications due to its ability to generate high-gain directional beams with low-cost phase shifters.However, conventional analog beamforming may suffer substantial performance degradation in wideband systems due to the beam-squint effects. Instead of relying on high-cost true time delayers, we propose in this paper an efficient three-dimensional (3D) rotatable antenna technology to mitigate the beam-squint effects, motivated by the fact that beam squint disappears along the boresight direction. In particular, we focus on a wideband wide-beam coverage problem in this paper, aiming to maximize the minimum beamforming gain within a given angle and frequency range by jointly optimizing the analog beamforming vector and the 3D rotation angles of the antenna array. However, this problem is non-convex and difficult to be optimally solved due to the coupling of the spatial and frequency domains and that of the antenna weights and rotation. To tackle this issue, we first reformulate the problem into an equivalent form by merging the spatial and frequency domains into a single composite domain. Next, we combine alternating optimization (AO) and successive convex approximation (SCA) algorithms to optimize the analog beamforming and rotation angles within this composite domain. Simulation results demonstrate that the proposed scheme can significantly outperform conventional schemes without antenna rotation, thus offering a cost-effective solution for wideband transmission over THz bands.

eess.SP↗

arXiv2025

Tuning the Size and Stiffness of Inflatable Particles

We describe size-varying cylindrical particles made from silicone elastomers that can serve as building blocks for robotic granular materials. The particle size variation, which is achieved by inflation, gives rise to changes in stiffness under compression. We design and fabricate inflatable particles that can become stiffer or softer during inflation, depending on key parameters of the particle geometry, such as the ratio of the fillet radius to the wall thickness, r/t. We also conduct numerical simulations of the inflatable particles and show that they only soften during inflation when localization of large strains occurs in the regime r/t -> 0. This work introduces novel particle systems with tunable size and stiffness that can be implemented in numerous soft robotic applications.

cond-mat.soft↗

arXiv2025

Quantumness and entropic uncertainty for a pair of static Unruh-DeWitt detectors

In this study, we investigate a pair of detectors operating in Minkowski space-time and analyze the characteristics of various quantum resources within this framework. Specifically, we focus on examining the properties of Bell nonlocality, quantum coherence, the nonlocal advantage of quantum coherence (NAQC), and measured uncertainty in relation to the energy ratio and the distance between the detectors. Additionally, we examine how the initial states influence these quantum properties. Notably, our findings reveal that both a larger energy ratio and a greater separation between the detectors degrade the system's quantumness. Moreover, we explore the evolution of entropic uncertainty and demonstrate its inverse correlation with both Bell nonlocality and coherence, highlighting the intricate interplay between these quantum resources. These insights provide a deeper understanding of quantumness in a relativistic framework and may contribute to the ongoing discussion on the black hole information paradox.

hep-th↗

arXiv2025

Inference Scaling for Long-Context Retrieval Augmented Generation

The scaling of inference computation has unlocked the potential of long-context large language models (LLMs) across diverse settings. For knowledge-intensive tasks, the increased compute is often allocated to incorporate more external knowledge. However, without effectively utilizing such knowledge, solely expanding context does not always enhance performance. In this work, we investigate inference scaling for retrieval augmented generation (RAG), exploring the combination of multiple strategies beyond simply increasing the quantity of knowledge, including in-context learning and iterative prompting. These strategies provide additional flexibility to scale test-time computation (e.g., by increasing retrieved documents or generation steps), thereby enhancing LLMs' ability to effectively acquire and utilize contextual information. We address two key questions: (1) How does RAG performance benefit from the scaling of inference computation when optimally configured? (2) Can we predict the optimal test-time compute allocation for a given budget by modeling the relationship between RAG performance and inference parameters? Our observations reveal that increasing inference computation leads to nearly linear gains in RAG performance when optimally allocated, a relationship we describe as the inference scaling laws for RAG. Building on this, we further develop the computation allocation model to estimate RAG performance across different inference configurations. The model predicts optimal inference parameters under various computation constraints, which align closely with the experimental results. By applying these optimal configurations, we demonstrate that scaling inference compute on long-context LLMs achieves up to 58.9% gains on benchmark datasets compared to standard RAG.

cs.CL↗

arXiv2025

ICPE: An Item Cluster-Wise Pareto-Efficient Framework for Recommendation Debiasing

Recommender system based on historical user-item interactions is of vital importance for web-based services. However, the observed data used to train the recommender model suffers from severe bias issues. Practically, the item frequency distribution of the dataset is a highly skewed power-law distribution. Interactions of a small fraction of head items account for almost the whole training data. The normal training paradigm from such biased data tends to repetitively generate recommendations from the head items, which further exacerbates the biases and affects the exploration of potentially interesting items from the niche set. In this work, we innovatively explore the central theme of recommendation debiasing from an item cluster-wise multi-objective optimization perspective. Aiming to balance the learning on various item clusters that differ in popularity during the training process, we propose a model-agnostic framework namely Item Cluster-Wise Pareto-Efficient Recommendation (ICPE). In detail, we define our item cluster-wise optimization target as the recommender model should balance all item clusters that differ in popularity, thus we set the model learning on each item cluster as a unique optimization objective. To achieve this goal, we first explore items' popularity levels from a novel causal reasoning perspective. Then, we devise popularity discrepancy-based bisecting clustering to separate the item clusters. Next, we adaptively find the overall harmonious gradient direction for cluster-wise optimization objectives from a Pareto-efficient solver. Finally, in the prediction stage, we perform counterfactual inference to further eliminate the impact of global propensity. Extensive experimental results verify the superiorities of ICPE on overall recommendation performance and biases elimination.

cs.IR↗

arXiv2025

Two-stream Beats One-stream: Asymmetric Siamese Network for Efficient Visual Tracking

Efficient tracking has garnered attention for its ability to operate on resource-constrained platforms for real-world deployment beyond desktop GPUs. Current efficient trackers mainly follow precision-oriented trackers, adopting a one-stream framework with lightweight modules. However, blindly adhering to the one-stream paradigm may not be optimal, as incorporating template computation in every frame leads to redundancy, and pervasive semantic interaction between template and search region places stress on edge devices. In this work, we propose a novel asymmetric Siamese tracker named \textbf{AsymTrack} for efficient tracking. AsymTrack disentangles template and search streams into separate branches, with template computing only once during initialization to generate modulation signals. Building on this architecture, we devise an efficient template modulation mechanism to unidirectional inject crucial cues into the search features, and design an object perception enhancement module that integrates abstract semantics and local details to overcome the limited representation in lightweight tracker. Extensive experiments demonstrate that AsymTrack offers superior speed-precision trade-offs across different platforms compared to the current state-of-the-arts. For instance, AsymTrack-T achieves 60.8\% AUC on LaSOT and 224/81/84 FPS on GPU/CPU/AGX, surpassing HiT-Tiny by 6.0\% AUC with higher speeds. The code is available at https://github.com/jiawen-zhu/AsymTrack.

cs.CV↗

arXiv2025

Quantum computation via Floquet-tailored Rydberg interactions

Rydberg atoms stand out as a highly promising platform for realizing quantum computation with significant advantages in constructing high-fidelity quantum gates. Floquet frequency modulation (FFM), in Rydberg-atom systems, provides a unique platform for achieving precise quantum control and uncovering exotic physical phenomena, paving the way for innovative methodologies in quantum dynamics research. This work introduces a method to realize controlled arbitrary phase gates in Rydberg atoms by manipulating system dynamics using FFM. Notably, this method eliminates the need for laser addressing of individual atoms, significantly enhancing convenience for future practical applications. Furthermore, this approach can be integrated with soft quantum control strategies to enhance the fidelity and robustness of the resultant controlled-phase gates. Finally, as an example, this methodology is applied in Grover-Long algorithm to search target items with zero failure rate, demonstrating its substantial significance for future quantum information processing applications. This work leveraging Rydberg atoms and Floquet frequency modulation may herald a new era of scalable and reliable quantum computing.

quant-ph↗

arXiv2025

Modality Interactive Mixture-of-Experts for Fake News Detection

The proliferation of fake news on social media platforms disproportionately impacts vulnerable populations, eroding trust, exacerbating inequality, and amplifying harmful narratives. Detecting fake news in multimodal contexts -- where deceptive content combines text and images -- is particularly challenging due to the nuanced interplay between modalities. Existing multimodal fake news detection methods often emphasize cross-modal consistency but ignore the complex interactions between text and visual elements, which may complement, contradict, or independently influence the predicted veracity of a post. To address these challenges, we present Modality Interactive Mixture-of-Experts for Fake News Detection (MIMoE-FND), a novel hierarchical Mixture-of-Experts framework designed to enhance multimodal fake news detection by explicitly modeling modality interactions through an interaction gating mechanism. Our approach models modality interactions by evaluating two key aspects of modality interactions: unimodal prediction agreement and semantic alignment. The hierarchical structure of MIMoE-FND allows for distinct learning pathways tailored to different fusion scenarios, adapting to the unique characteristics of each modality interaction. By tailoring fusion strategies to diverse modality interaction scenarios, MIMoE-FND provides a more robust and nuanced approach to multimodal fake news detection. We evaluate our approach on three real-world benchmarks spanning two languages, demonstrating its superior performance compared to state-of-the-art methods. By enhancing the accuracy and interpretability of fake news detection, MIMoE-FND offers a promising tool to mitigate the spread of misinformation, with the potential to better safeguard vulnerable communities against its harmful effects.

cs.LG↗

arXiv2025

GraphMorph: Tubular Structure Extraction by Morphing Predicted Graphs

Accurately restoring topology is both challenging and crucial in tubular structure extraction tasks, such as blood vessel segmentation and road network extraction. Diverging from traditional approaches based on pixel-level classification, our proposed method, named GraphMorph, focuses on branch-level features of tubular structures to achieve more topologically accurate predictions. GraphMorph comprises two main components: a Graph Decoder and a Morph Module. Utilizing multi-scale features extracted from an image patch by the segmentation network, the Graph Decoder facilitates the learning of branch-level features and generates a graph that accurately represents the tubular structure in this patch. The Morph Module processes two primary inputs: the graph and the centerline probability map, provided by the Graph Decoder and the segmentation network, respectively. Employing a novel SkeletonDijkstra algorithm, the Morph Module produces a centerline mask that aligns with the predicted graph. Furthermore, we observe that employing centerline masks predicted by GraphMorph significantly reduces false positives in the segmentation task, which is achieved by a simple yet effective post-processing strategy. The efficacy of our method in the centerline extraction and segmentation tasks has been substantiated through experimental evaluations across various datasets. Source code will be released soon.

cs.CV↗

arXiv2025

Quantifying Quantumness in (A)dS spacetimes with Unruh-DeWitt Detector

Probing quantumness in curved spacetime is regarded as one of fundamental and important topics in the framework of relativistic quantum information. In this work, we focus on the theoretical feasibility of probing quantum properties in de Sitter (dS) and Anti-de Sitter (AdS) spacetimes via detectors. By employing the Unruh-DeWitt detector coupled with a massless scalar field, which is treated as an open system, quantum uncertainty and quantum coherence in both dS and AdS spacetimes are investigated. Our analysis reveals that the acceleration in dS spacetime and the boundary conditions in AdS spacetime significantly impact the detector's evolution in the initial stage. Notably, both of the uncertainty and coherence will oscillate with the initial state being in a superposition state, however the high temperature is able to suppress their oscillation. Interestingly, it is found that the constant values of the final uncertainty and coherence are identical as those in dS and AdS spacetimes, which are determined by the ratio of energy gap to temperature. Hence, the current exploration offers insight into quantumness in dS and AdS spacetimes, and might be helpful to facilitate the curved-spacetime-based quantum information processing.

hep-th↗

arXiv2025

FastUMI: A Scalable and Hardware-Independent Universal Manipulation Interface with Dataset

Real-world manipulation data involving robotic arms is crucial for developing generalist action policies, yet such data remains scarce since existing data collection methods are hindered by high costs, hardware dependencies, and complex setup requirements. In this work, we introduce FastUMI, a substantial redesign of the Universal Manipulation Interface (UMI) system that addresses these challenges by enabling rapid deployment, simplifying hardware-software integration, and delivering robust performance in real-world data acquisition. Compared with UMI, FastUMI has several advantages: 1) It adopts a decoupled hardware design and incorporates extensive mechanical modifications, removing dependencies on specialized robotic components while preserving consistent observation perspectives. 2) It also refines the algorithmic pipeline by replacing complex Visual-Inertial Odometry (VIO) implementations with an off-the-shelf tracking module, significantly reducing deployment complexity while maintaining accuracy. 3) FastUMI includes an ecosystem for data collection, verification, and integration with both established and newly developed imitation learning algorithms, accelerating policy learning advancement. Additionally, we have open-sourced a high-quality dataset of over 10,000 real-world demonstration trajectories spanning 22 everyday tasks, forming one of the most diverse UMI-like datasets to date. Experimental results confirm that FastUMI facilitates rapid deployment, reduces operational costs and labor demands, and maintains robust performance across diverse manipulation scenarios, thereby advancing scalable data-driven robotic learning.

cs.RO↗