arXiv subjects

Dong Wang

Publications and source records attributed to Dong Wang.

At least 253 records · Page 14Linked to original sources

arXiv2025

CNVSRC 2024: The Second Chinese Continuous Visual Speech Recognition Challenge

This paper presents the second Chinese Continuous Visual Speech Recognition Challenge (CNVSRC 2024), which builds on CNVSRC 2023 to advance research in Chinese Large Vocabulary Continuous Visual Speech Recognition (LVC-VSR). The challenge evaluates two test scenarios: reading in recording studios and Internet speech. CNVSRC 2024 uses the same datasets as its predecessor CNVSRC 2023, which involves CN-CVS for training and CNVSRC-Single/Multi for development and evaluation. However, CNVSRC 2024 introduced two key improvements: (1) a stronger baseline system, and (2) an additional dataset, CN-CVS2-P1, for open tracks to improve data volume and diversity. The new challenge has demonstrated several important innovations in data preprocessing, feature extraction, model design, and training strategies, further pushing the state-of-the-art in Chinese LVC-VSR. More details and resources are available at the official website.

cs.CV↗

arXiv2025

Leveraging Large Language Models in Visual Speech Recognition: Model Scaling, Context-Aware Decoding, and Iterative Polishing

Visual Speech Recognition (VSR) transcribes speech by analyzing lip movements. Recently, Large Language Models (LLMs) have been integrated into VSR systems, leading to notable performance improvements. However, the potential of LLMs has not been extensively studied, and how to effectively utilize LLMs in VSR tasks remains unexplored. This paper systematically explores how to better leverage LLMs for VSR tasks and provides three key contributions: (1) Scaling Test: We study how the LLM size affects VSR performance, confirming a scaling law in the VSR task. (2) Context-Aware Decoding: We add contextual text to guide the LLM decoding, improving recognition accuracy. (3) Iterative Polishing: We propose iteratively refining LLM outputs, progressively reducing recognition errors. Extensive experiments demonstrate that by these designs, the great potential of LLMs can be largely harnessed, leading to significant VSR performance improvement.

cs.CV↗

arXiv2025

Efficient Motion Prompt Learning for Robust Visual Tracking

Due to the challenges of processing temporal information, most trackers depend solely on visual discriminability and overlook the unique temporal coherence of video data. In this paper, we propose a lightweight and plug-and-play motion prompt tracking method. It can be easily integrated into existing vision-based trackers to build a joint tracking framework leveraging both motion and vision cues, thereby achieving robust tracking through efficient prompt learning. A motion encoder with three different positional encodings is proposed to encode the long-term motion trajectory into the visual embedding space, while a fusion decoder and an adaptive weight mechanism are designed to dynamically fuse visual and motion features. We integrate our motion module into three different trackers with five models in total. Experiments on seven challenging tracking benchmarks demonstrate that the proposed motion module significantly improves the robustness of vision-based trackers, with minimal training costs and negligible speed sacrifice. Code is available at https://github.com/zj5559/Motion-Prompt-Tracking.

cs.CV↗

arXiv2025

SQLCritic: Correcting Text-to-SQL Generation via Clause-wise Critic

Existing refinement methods in LLM-based Text-to-SQL systems exhibit limited effectiveness. They often introduce new errors during the self-correction process and fail to detect and correct semantic inaccuracies. To address these gaps, we first introduce a clause-wise critique generation task along with a benchmark, SQLCriticBench, which performs fine-grained error localization including both syntax and semantic errors at the clause level. Furthermore, we introduce a variant of DPO for training our SQLCritic model, where the $β$ coefficient is adaptively changed according to the clause-level inconsistencies between the preferred and dispreferred critiques. We also propose an automatically training dataset curation pipeline which annotate clause-wise critique at scale in a cost-effective way. Experiments demonstrate that the SQLCritic model significantly improves SQL accuracy on the BIRD and Spider datasets, and the results on SQLCriticBench further reveals its superior critique capabilities compared to existing models.

cs.AI↗

arXiv2025

STAR-RIS-Enabled Multi-Path Beam Routing with Passive Beam Splitting

Reconfigurable intelligent surfaces (RISs) can be densely deployed in the environment to create multi-reflection line-of-sight (LoS) links for signal coverage enhancement. However, conventional reflection-only RISs can only achieve half-space reflection, which limits the LoS path diversity. In contrast, simultaneously transmitting and reflecting RISs (STAR-RISs) can achieve full-space reflection and transmission, thereby creating more LoS paths. Hence, in this paper, we study a new multi-STAR-RIS-aided communication system, where a multi-antenna base station (BS) transmits to multiple single-antenna users by exploiting the signal beam routing over a set of cascaded LoS paths each formed by multiple STAR-RISs. To reveal essential insights, we first consider a simplified single-user case, aiming to maximize its received signal power by jointly optimizing the active beamforming at the BS, the BS's power allocation over different paths, the number of selected beam-routing paths, the selected STAR-RISs for each path, as well as their amplitude and phase shifts for transmission/reflection. However, this problem is difficult to be optimally solved as different paths may be intricately coupled at their shared STAR-RISs. To tackle this difficulty, we first derive the optimal solution to this problem in closed-form for a given set of paths. The clique-based approach in graph theory is then applied to solve the remaining multi-path selection problem efficiently. Next, we extend the proposed clique-based method to the multi-user case to maximize the minimum received signal power among all users, subject to additional constraints on the disjointness of the selected paths for different users. Simulation results show that our proposed STAR-RIS-enabled beam routing outperforms the conventional beam routing with reflection-only RISs in both single- and multi-user cases.

eess.SP↗

arXiv2025

SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model

In this paper, we claim that spatial understanding is the keypoint in robot manipulation, and propose SpatialVLA to explore effective spatial representations for the robot foundation model. Specifically, we introduce Ego3D Position Encoding to inject 3D information into the input observations of the visual-language-action model, and propose Adaptive Action Grids to represent spatial robot movement actions with adaptive discretized action grids, facilitating learning generalizable and transferrable spatial action knowledge for cross-robot control. SpatialVLA is first pre-trained on top of a vision-language model with 1.1 Million real-world robot episodes, to learn a generalist manipulation policy across multiple robot environments and tasks. After pre-training, SpatialVLA is directly applied to perform numerous tasks in a zero-shot manner. The superior results in both simulation and real-world robots demonstrate its advantage of inferring complex robot motion trajectories and its strong in-domain multi-task generalization ability. We further show the proposed Adaptive Action Grids offer a new and effective way to fine-tune the pre-trained SpatialVLA model for new simulation and real-world setups, where the pre-learned action grids are re-discretized to capture robot-specific spatial action movements of new setups. The superior results from extensive evaluations demonstrate the exceptional in-distribution generalization and out-of-distribution adaptation capability, highlighting the crucial benefit of the proposed spatial-aware representations for generalist robot policy learning. All the details and codes will be open-sourced.

cs.RO↗

arXiv2025

Item Level Exploration Traffic Allocation in Large-scale Recommendation Systems

This paper contributes to addressing the item cold start problem in large-scale recommender systems, focusing on how to efficiently gain initial visibility for newly ingested content. We propose an exploration system designed to efficiently allocate impressions to these fresh items. Our approach leverages a learned probabilistic model to predict an item's discoverability, which then informs a scalable and adaptive traffic allocation strategy. This system intelligently distributes exploration budgets, optimizing for the long-term benefit of the recommendation platform. The impact is a demonstrably more efficient cold-start process, leading to a significant increase in the discoverability of new content and ultimately enriching the item corpus available for exploitation, as evidenced by its successful deployment in a large-scale production environment.

cs.IR↗

arXiv2025

A Preliminary Study of Large Language Models for Multilingual Vulnerability Detection

Deep learning-based approaches, particularly those leveraging pre-trained language models (PLMs), have shown promise in automated software vulnerability detection. However, existing methods are predominantly limited to specific programming languages, restricting their applicability in multilingual settings. Recent advancements in large language models (LLMs) offer language-agnostic capabilities and enhanced semantic understanding, presenting a potential solution to this limitation. While existing studies have explored LLMs for vulnerability detection, their detection performance remains unknown for multilingual vulnerabilities. To address this gap, we conducted a preliminary study to evaluate the effectiveness of PLMs and state-of-the-art LLMs across seven popular programming languages. Our findings reveal that the PLM CodeT5P achieves the best performance in multilingual vulnerability detection, particularly in identifying the most critical vulnerabilities. Based on these results, we further discuss the potential of LLMs in advancing real-world multilingual vulnerability detection. This work represents an initial step toward exploring PLMs and LLMs for cross-language vulnerability detection, offering key insights for future research and practical deployment.

cs.SE↗

arXiv2025

Scattering symmetry of diffusive systems

Significant progress in manipulating heat diffusion has been achieved with the advent of non-Hermitian physics and topology. However, previous studies on diffusive systems have primarily concentrated on isolated cases, where fields decay exponentially over time. In practical scenarios, systems inevitably interact with external environments, making it essential to study their responses to external heat signals. This, in turn, relies on analyzing the scattering behavior of these signals. In our work, we experimentally realize thermal scattering in a diffusive anti-parity-time (APT) system. We define key parameters of the temperature field-amplitude, phase, and chirality-and reveal that the scattering symmetry of the APT diffusive system only arises when temperature signals with different chiralities interact. Such mechanism is induced by the unique dispersion properties in diffusive systems, where positive and negative frequencies are inequivalent, corresponding to different chiralities. This also explains the difficulty of observing APT scattering symmetry in wave systems. Our findings highlight the pivotal role of scattering channels in the symmetry and phase transitions of non-Hermitian systems and propose novel approaches for analyzing and controlling strongly dissipative phenomena.

physics.app-ph↗

arXiv2025

Component-Based Fairness in Face Attribute Classification with Bayesian Network-informed Meta Learning

The widespread integration of face recognition technologies into various applications (e.g., access control and personalized advertising) necessitates a critical emphasis on fairness. While previous efforts have focused on demographic fairness, the fairness of individual biological face components remains unexplored. In this paper, we focus on face component fairness, a fairness notion defined by biological face features. To our best knowledge, our work is the first work to mitigate bias of face attribute prediction at the biological feature level. In this work, we identify two key challenges in optimizing face component fairness: attribute label scarcity and attribute inter-dependencies, both of which limit the effectiveness of bias mitigation from previous approaches. To address these issues, we propose \textbf{B}ayesian \textbf{N}etwork-informed \textbf{M}eta \textbf{R}eweighting (BNMR), which incorporates a Bayesian Network calibrator to guide an adaptive meta-learning-based sample reweighting process. During the training process of our approach, the Bayesian Network calibrator dynamically tracks model bias and encodes prior probabilities for face component attributes to overcome the above challenges. To demonstrate the efficacy of our approach, we conduct extensive experiments on a large-scale real-world human face dataset. Our results show that BNMR is able to consistently outperform recent face bias mitigation baselines. Moreover, our results suggest a positive impact of face component fairness on the commonly considered demographic fairness (e.g., \textit{gender}). Our findings pave the way for new research avenues on face component fairness, suggesting that face component fairness could serve as a potential surrogate objective for demographic fairness. The code for our work is publicly available~\footnote{https://github.com/yliuaa/BNMR-FairCompFace.git}.

cs.CV↗

arXiv2025

Knowledge Graph Completion with Relation-Aware Anchor Enhancement

Text-based knowledge graph completion methods take advantage of pre-trained language models (PLM) to enhance intrinsic semantic connections of raw triplets with detailed text descriptions. Typical methods in this branch map an input query (textual descriptions associated with an entity and a relation) and its candidate entities into feature vectors, respectively, and then maximize the probability of valid triples. These methods are gaining promising performance and increasing attention for the rapid development of large language models. According to the property of the language models, the more related and specific context information the input query provides, the more discriminative the resultant embedding will be. In this paper, through observation and validation, we find a neglected fact that the relation-aware neighbors of the head entities in queries could act as effective contexts for more precise link prediction. Driven by this finding, we propose a relation-aware anchor enhanced knowledge graph completion method (RAA-KGC). Specifically, in our method, to provide a reference of what might the target entity be like, we first generate anchor entities within the relation-aware neighborhood of the head entity. Then, by pulling the query embedding towards the neighborhoods of the anchors, it is tuned to be more discriminative for target entity matching. The results of our extensive experiments not only validate the efficacy of RAA-KGC but also reveal that by integrating our relation-aware anchor enhancement strategy, the performance of current leading methods can be notably enhanced without substantial modifications.

cs.IR↗

arXiv2025

Alternately-optimized SNN method for acoustic scattering problem in unbounded domain

In this paper, we propose a novel machine learning-based method to solve the acoustic scattering problem in unbounded domain. We first employ the Dirichlet-to-Neumann (DtN) operator to truncate the physically unbounded domain into a computable bounded domain. This transformation reduces the original scattering problem in the unbounded domain to a boundary value problem within the bounded domain. To solve this boundary value problem, we design a neural network with a subspace layer, where each neuron in this layer represents a basis function. Consequently, the approximate solution can be expressed by a linear combination of these basis functions. Furthermore, we introduce an innovative alternating optimization technique which alternately updates the basis functions and their linear combination coefficients respectively by training and least squares methods. In our method, we set the coefficients of basis functions to 1 and use a new loss function each time train the subspace. These innovations ensure that the subspace formed by these basis functions is truly optimized. We refer to this method as the alternately-optimized subspace method based on neural networks (AO-SNN). Extensive numerical experiments demonstrate that our new method can significantly reduce the relative $l^2$ error to $10^{-7}$ or lower, outperforming existing machine learning-based methods to the best of our knowledge.

math.NA↗

arXiv2025

Phoenix: A Motion-based Self-Reflection Framework for Fine-grained Robotic Action Correction

Building a generalizable self-correction system is crucial for robots to recover from failures. Despite advancements in Multimodal Large Language Models (MLLMs) that empower robots with semantic reflection ability for failure, translating semantic reflection into how to correct fine-grained robotic actions remains a significant challenge. To address this gap, we build the Phoenix framework, which leverages motion instruction as a bridge to connect high-level semantic reflection with low-level robotic action correction. In this motion-based self-reflection framework, we start with a dual-process motion adjustment mechanism with MLLMs to translate the semantic reflection into coarse-grained motion instruction adjustment. To leverage this motion instruction for guiding how to correct fine-grained robotic actions, a multi-task motion-conditioned diffusion policy is proposed to integrate visual observations for high-frequency robotic action correction. By combining these two models, we could shift the demand for generalization capability from the low-level manipulation policy to the MLLMs-driven motion adjustment model and facilitate precise, fine-grained robotic action correction. Utilizing this framework, we further develop a lifelong learning method to automatically improve the model's capability from interactions with dynamic environments. The experiments conducted in both the RoboMimic simulation and real-world scenarios prove the superior generalization and robustness of our framework across a variety of manipulation tasks. Our code is released at \href{https://github.com/GeWu-Lab/Motion-based-Self-Reflection-Framework}{https://github.com/GeWu-Lab/Motion-based-Self-Reflection-Framework}.

cs.RO↗

arXiv2025

CPG-EVAL: A Multi-Tiered Benchmark for Evaluating the Chinese Pedagogical Grammar Competence of Large Language Models

Purpose: The rapid emergence of large language models (LLMs) such as ChatGPT has significantly impacted foreign language education, yet their pedagogical grammar competence remains under-assessed. This paper introduces CPG-EVAL, the first dedicated benchmark specifically designed to evaluate LLMs' knowledge of pedagogical grammar within the context of foreign language instruction. Methodology: The benchmark comprises five tasks designed to assess grammar recognition, fine-grained grammatical distinction, categorical discrimination, and resistance to linguistic interference. Findings: Smaller-scale models can succeed in single language instance tasks, but struggle with multiple instance tasks and interference from confusing instances. Larger-scale models show better resistance to interference but still have significant room for accuracy improvement. The evaluation indicates the need for better instructional alignment and more rigorous benchmarks, to effectively guide the deployment of LLMs in educational contexts. Value: This study offers the first specialized, theory-driven, multi-tiered benchmark framework for systematically evaluating LLMs' pedagogical grammar competence in Chinese language teaching contexts. CPG-EVAL not only provides empirical insights for educators, policymakers, and model developers to better gauge AI's current abilities in educational settings, but also lays the groundwork for future research on improving model alignment, enhancing educational suitability, and ensuring informed decision-making concerning LLM integration in foreign language instruction.

cs.CL↗

arXiv2025

Near-Field THz Bending Beamforming: A Convex Optimization Perspective

Terahertz (THz) communication systems suffer severe blockage issues, which may significantly degrade the communication coverage and quality. Bending beams, capable of adjusting their propagation direction to bypass obstacles, have recently emerged as a promising solution to resolve this issue by engineering the propagation trajectory of the beam. However, traditional bending beam generation methods rely heavily on the specific geometric properties of the propagation trajectory and can only achieve sub-optimal performance. In this paper, we propose a new and general bending beamforming method by adopting the convex optimization techniques. In particular, we formulate the bending beamforming design as a max-min optimization problem, aiming to optimize the analog or digital transmit beamforming vector to maximize the minimum received signal power among all positions along the bending beam trajectory. However, the resulting problem is non-convex and difficult to be solved optimally. To tackle this difficulty, we apply the successive convex approximation (SCA) technique to obtain a high-quality suboptimal solution. Numerical results show that our proposed bending beamforming method outperforms the traditional method and shows robustness to the obstacle in the environment.

eess.SP↗

arXiv2025

EvMic: Event-based Non-contact sound recovery from effective spatial-temporal modeling

When sound waves hit an object, they induce vibrations that produce high-frequency and subtle visual changes, which can be used for recovering the sound. Early studies always encounter trade-offs related to sampling rate, bandwidth, field of view, and the simplicity of the optical path. Recent advances in event camera hardware show good potential for its application in visual sound recovery, because of its superior ability in capturing high-frequency signals. However, existing event-based vibration recovery methods are still sub-optimal for sound recovery. In this work, we propose a novel pipeline for non-contact sound recovery, fully utilizing spatial-temporal information from the event stream. We first generate a large training set using a novel simulation pipeline. Then we designed a network that leverages the sparsity of events to capture spatial information and uses Mamba to model long-term temporal information. Lastly, we train a spatial aggregation block to aggregate information from different locations to further improve signal quality. To capture event signals caused by sound waves, we also designed an imaging system using a laser matrix to enhance the gradient and collected multiple data sequences for testing. Experimental results on synthetic and real-world data demonstrate the effectiveness of our method.

cs.SD↗

arXiv2025

Exploring Dynamic Transformer for Efficient Object Tracking

The speed-precision trade-off is a critical problem for visual object tracking which usually requires low latency and deployment on constrained resources. Existing solutions for efficient tracking mainly focus on adopting light-weight backbones or modules, which nevertheless come at the cost of a sacrifice in precision. In this paper, inspired by dynamic network routing, we propose DyTrack, a dynamic transformer framework for efficient tracking. Real-world tracking scenarios exhibit diverse levels of complexity. We argue that a simple network is sufficient for easy frames in video sequences, while more computation could be assigned to difficult ones. DyTrack automatically learns to configure proper reasoning routes for various inputs, gaining better utilization of the available computational budget. Thus, it can achieve higher performance with the same running speed. We formulate instance-specific tracking as a sequential decision problem and attach terminating branches to intermediate layers of the entire model. Especially, to fully utilize the computations, we introduce the feature recycling mechanism to reuse the outputs of predecessors. Furthermore, a target-aware self-distillation strategy is designed to enhance the discriminating capabilities of early predictions by effectively mimicking the representation pattern of the deep model. Extensive experiments on multiple benchmarks demonstrate that DyTrack achieves promising speed-precision trade-offs with only a single model. For instance, DyTrack obtains 64.9% AUC on LaSOT with a speed of 256 fps.

cs.CV↗

arXiv2025

1-Tb/s/λ Transmission over Record 10714-km AR-HCF

We present the first single-channel 1.001-Tb/s DP-36QAM-PCS recirculating transmission over 73 loops of 146.77-km ultra-low-loss & low-IMI DNANF-5 fiber, achieving a record transmission distance of 10,714.28 km.

physics.optics↗