arXiv subjects

Dong Wang

Publications and source records attributed to Dong Wang.

At least 325 records · Page 18Linked to original sources

arXiv2024

Global well-posedness of the 3D primitive equations with horizontal viscosity and vertical diffusivity II: close to $H^1$ initial data

In this paper, we consider the initial-boundary value problem to the three-dimensional primitive equations for the oceanic and atmospheric dynamics with only horizontal eddy viscosities in the horizontal momentum equations and only vertical diffusivity in the temperature equation in the domain $Ω=M\times(-h,h)$, with $M=(0,1)\times(0,1)$. Global well-posedness of strong solutions is established, for any initial data $(v_0,T_0) \in H^1(Ω)\cap L^\infty(Ω)$ with $(\partial_z v_0, \nabla_H T_0) \in L^q(Ω)$ and $v_0 \in L_z^1(B^1_{q,2}(M))$, for some $q \in (2,\infty)$, by using delicate energy estimates and maximal regularity estimate in the anisotropic setting.

math.AP↗

arXiv2024

Reinforcement Learning with Elastic Time Steps

Traditional Reinforcement Learning (RL) policies are typically implemented with fixed control rates, often disregarding the impact of control rate selection. This can lead to inefficiencies as the optimal control rate varies with task requirements. We propose the Multi-Objective Soft Elastic Actor-Critic (MOSEAC), an off-policy actor-critic algorithm that uses elastic time steps to dynamically adjust the control frequency. This approach minimizes computational resources by selecting the lowest viable frequency. We show that MOSEAC converges and produces stable policies at the theoretical level, and validate our findings in a real-time 3D racing game. MOSEAC significantly outperformed other variable time step approaches in terms of energy efficiency and task effectiveness. Additionally, MOSEAC demonstrated faster and more stable training, showcasing its potential for real-world RL applications in robotics.

cs.RO↗

arXiv2024

Depth Helps: Improving Pre-trained RGB-based Policy with Depth Information Injection

3D perception ability is crucial for generalizable robotic manipulation. While recent foundation models have made significant strides in perception and decision-making with RGB-based input, their lack of 3D perception limits their effectiveness in fine-grained robotic manipulation tasks. To address these limitations, we propose a Depth Information Injection ($\bold{DI}^{\bold{2}}$) framework that leverages the RGB-Depth modality for policy fine-tuning, while relying solely on RGB images for robust and efficient deployment. Concretely, we introduce the Depth Completion Module (DCM) to extract the spatial prior knowledge related to depth information and generate virtual depth information from RGB inputs to aid policy deployment. Further, we propose the Depth-Aware Codebook (DAC) to eliminate noise and reduce the cumulative error from the depth prediction. In the inference phase, this framework employs RGB inputs and accurately predicted depth data to generate the manipulation action. We conduct experiments on simulated LIBERO environments and real-world scenarios, and the experiment results prove that our method could effectively enhance the pre-trained RGB-based policy with 3D perception ability for robotic manipulation. The website is released at https://gewu-lab.github.io/DepthHelps-IROS2024.

cs.RO↗

arXiv2024

Towards Identifying Code Proficiency through the Analysis of Python Textbooks

Python, one of the most prevalent programming languages today, is widely utilized in various domains, including web development, data science, machine learning, and DevOps. Recent scholarly efforts have proposed a methodology to assess Python competence levels, similar to how proficiency in natural languages is evaluated. This method involves assigning levels of competence to Python constructs, for instance, placing simple 'print' statements at the most basic level and abstract base classes at the most advanced. The aim is to gauge the level of proficiency a developer must have to understand a piece of source code. This is particularly crucial for software maintenance and evolution tasks, such as debugging or adding new features. For example, in a code review process, this method could determine the competence level required for reviewers. However, categorizing Python constructs by proficiency levels poses significant challenges. Prior attempts, which relied heavily on expert opinions and developer surveys, have led to considerable discrepancies. In response, this paper presents a new approach to identifying Python competency levels through the systematic analysis of introductory Python programming textbooks. By comparing the sequence in which Python constructs are introduced in these textbooks with the current state of the art, we have uncovered notable discrepancies in the order of introduction of Python constructs. Our study underscores a misalignment in the sequences, demonstrating that pinpointing proficiency levels is not trivial. Insights from the study serve as pivotal steps toward reinforcing the idea that textbooks serve as a valuable source for evaluating developers' proficiency, and particularly in terms of their ability to undertake maintenance and evolution tasks.

cs.SE↗

arXiv2024

Large Language Models for Equivalent Mutant Detection: How Far Are We?

Mutation testing is vital for ensuring software quality. However, the presence of equivalent mutants is known to introduce redundant cost and bias issues, hindering the effectiveness of mutation testing in practical use. Although numerous equivalent mutant detection (EMD) techniques have been proposed, they exhibit limitations due to the scarcity of training data and challenges in generalizing to unseen mutants. Recently, large language models (LLMs) have been extensively adopted in various code-related tasks and have shown superior performance by more accurately capturing program semantics. Yet the performance of LLMs in equivalent mutant detection remains largely unclear. In this paper, we conduct an empirical study on 3,302 method-level Java mutant pairs to comprehensively investigate the effectiveness and efficiency of LLMs for equivalent mutant detection. Specifically, we assess the performance of LLMs compared to existing EMD techniques, examine the various strategies of LLMs, evaluate the orthogonality between EMD techniques, and measure the time overhead of training and inference. Our findings demonstrate that LLM-based techniques significantly outperform existing techniques (i.e., the average improvement of 35.69% in terms of F1-score), with the fine-tuned code embedding strategy being the most effective. Moreover, LLM-based techniques offer an excellent balance between cost (relatively low training and inference time) and effectiveness. Based on our findings, we further discuss the impact of model size and embedding quality, and provide several promising directions for future research. This work is the first to examine LLMs in equivalent mutant detection, affirming their effectiveness and efficiency.

cs.SE↗

arXiv2024

Knowledge-driven AI-generated data for accurate and interpretable breast ultrasound diagnoses

Data-driven deep learning models have shown great capabilities to assist radiologists in breast ultrasound (US) diagnoses. However, their effectiveness is limited by the long-tail distribution of training data, which leads to inaccuracies in rare cases. In this study, we address a long-standing challenge of improving the diagnostic model performance on rare cases using long-tailed data. Specifically, we introduce a pipeline, TAILOR, that builds a knowledge-driven generative model to produce tailored synthetic data. The generative model, using 3,749 lesions as source data, can generate millions of breast-US images, especially for error-prone rare cases. The generated data can be further used to build a diagnostic model for accurate and interpretable diagnoses. In the prospective external evaluation, our diagnostic model outperforms the average performance of nine radiologists by 33.5% in specificity with the same sensitivity, improving their performance by providing predictions with an interpretable decision-making process. Moreover, on ductal carcinoma in situ (DCIS), our diagnostic model outperforms all radiologists by a large margin, with only 34 DCIS lesions in the source data. We believe that TAILOR can potentially be extended to various diseases and imaging modalities.

eess.IV↗

arXiv2024

EvSign: Sign Language Recognition and Translation with Streaming Events

Sign language is one of the most effective communication tools for people with hearing difficulties. Most existing works focus on improving the performance of sign language tasks on RGB videos, which may suffer from degraded recording conditions, such as fast movement of hands with motion blur and textured signer's appearance. The bio-inspired event camera, which asynchronously captures brightness change with high speed, could naturally perceive dynamic hand movements, providing rich manual clues for sign language tasks. In this work, we aim at exploring the potential of event camera in continuous sign language recognition (CSLR) and sign language translation (SLT). To promote the research, we first collect an event-based benchmark EvSign for those tasks with both gloss and spoken language annotations. EvSign dataset offers a substantial amount of high-quality event streams and an extensive vocabulary of glosses and words, thereby facilitating the development of sign language tasks. In addition, we propose an efficient transformer-based framework for event-based SLR and SLT tasks, which fully leverages the advantages of streaming events. The sparse backbone is employed to extract visual features from sparse events. Then, the temporal coherence is effectively utilized through the proposed local token fusion and gloss-aware temporal aggregation modules. Extensive experimental results are reported on both simulated (PHOENIX14T) and EvSign datasets. Our method performs favorably against existing state-of-the-art approaches with only 0.34% computational cost (0.84G FLOPS per video) and 44.2% network parameters. The project is available at https://zhang-pengyu.github.io/EVSign.

cs.CV↗

arXiv2024

Entropic uncertainty relations in Schwarzschild space-time

The uncertainty principle is deemed as one of cornerstones in quantum mechanics, and exploring its lower limit of uncertainty will be helpful to understand the principle's nature. In this study, we propose a generalized entropic uncertainty relation for arbitrary multiple-observable in multipartite system, and further derive a tighter lower bound by considering Holevo quality and mutual information. Importantly, we detailedly discuss the proposed uncertainty relations and quantum coherence in the context of Schwarzschild space-time. It is interesting to find that Hawking radiation will damage the coherence of the physically accessible region and increase the uncertainty. Furthermore, we argue that the properties of the uncertainty in Schwarzschild space-time can be explained from the systems' purity and the information redistribution of the different regions. Therefore, it is believed that our findings provide the generalized entropic uncertainty relations in multipartite systems, which may facilitate us deeper understanding of quantumness and information paradox of the black holes.

quant-ph↗

arXiv2024

Einstein-Podolsky-Rosen Steering Criterion and Monogamy Relation via Correlation Matrices in Tripartite Systems

Quantum steering is considered as one of the most well-known nonlocal phenomena in quantum mechanics. Unlike entanglement and Bell non-locality, the asymmetry of quantum steering makes it vital for one-sided device-independent quantum information processing. Although there has been much progress on steering detection for bipartite systems, the criterion for EPR steering in tripartite systems remains challenging and inadequate. In this paper, we firstly derive a novel and promising steering criterion for any three-qubit states via correlation matrix. Furthermore, we propose the monogamy relation between the tripartite steering of system and the bipartite steering of subsystems based on the derived criterion. Finally, as illustrations, we demonstrate the performance of the steering criterion and the monogamy relation by means of several representative examples. We believe that the results and methods presented in this work could be beneficial to capture genuine multipartite steering in the near future.

quant-ph↗

arXiv2024

Quantum battery in the Heisenberg spin chain models with Dzyaloshinskii-Moriya interaction

Quantum battery (QB) is an energy storage and extraction device conforming to the principles of quantum mechanics. In this study, we consider the characteristics of QBs for the Heisenberg spin chain models in the absence and presence of Dzyaloshinskii-Moriya (DM) interaction. Our results show that the DM interaction can enhance the ergotropy and power of QBs, which shows the collective charging can outperform parallel charging regarding QB's performance. Besides, it turns out that first-order coherence is a crucial quantum resource during charging, while quantum steering between the cells is not conducive to the energy storage of QBs. Our investigations offer insight into the properties of QBs with Heisenberg spin chain models with DM interaction and facilitate us to acquire the performance in the framework of realistic quantum batteries.

quant-ph↗

arXiv2024

Few-Shot Keyword Spotting from Mixed Speech

Few-shot keyword spotting (KWS) aims to detect unknown keywords with limited training samples. A commonly used approach is the pre-training and fine-tuning framework. While effective in clean conditions, this approach struggles with mixed keyword spotting -- simultaneously detecting multiple keywords blended in an utterance, which is crucial in real-world applications. Previous research has proposed a Mix-Training (MT) approach to solve the problem, however, it has never been tested in the few-shot scenario. In this paper, we investigate the possibility of using MT and other relevant methods to solve the two practical challenges together: few-shot and mixed speech. Experiments conducted on the LibriSpeech and Google Speech Command corpora demonstrate that MT is highly effective on this task when employed in either the pre-training phase or the fine-tuning phase. Moreover, combining SSL-based large-scale pre-training (HuBert) and MT fine-tuning yields very strong results in all the test conditions.

cs.SD↗

arXiv2024

WANCO: Weak Adversarial Networks for Constrained Optimization problems

This paper focuses on integrating the networks and adversarial training into constrained optimization problems to develop a framework algorithm for constrained optimization problems. For such problems, we first transform them into minimax problems using the augmented Lagrangian method and then use two (or several) deep neural networks(DNNs) to represent the primal and dual variables respectively. The parameters in the neural networks are then trained by an adversarial process. The proposed architecture is relatively insensitive to the scale of values of different constraints when compared to penalty based deep learning methods. Through this type of training, the constraints are imposed better based on the augmented Lagrangian multipliers. Extensive examples for optimization problems with scalar constraints, nonlinear constraints, partial differential equation constraints, and inequality constraints are considered to show the capability and robustness of the proposed method, with applications ranging from Ginzburg--Landau energy minimization problems, partition problems, fluid-solid topology optimization, to obstacle problems.

math.OC↗

arXiv2024

Serialized Output Training by Learned Dominance

Serialized Output Training (SOT) has showcased state-of-the-art performance in multi-talker speech recognition by sequentially decoding the speech of individual speakers. To address the challenging label-permutation issue, prior methods have relied on either the Permutation Invariant Training (PIT) or the time-based First-In-First-Out (FIFO) rule. This study presents a model-based serialization strategy that incorporates an auxiliary module into the Attention Encoder-Decoder architecture, autonomously identifying the crucial factors to order the output sequence of the speech components in multi-talker speech. Experiments conducted on the LibriSpeech and LibriMix databases reveal that our approach significantly outperforms the PIT and FIFO baselines in both 2-mix and 3-mix scenarios. Further analysis shows that the serialization module identifies dominant speech components in a mixture by factors including loudness and gender, and orders speech components based on the dominance score.

cs.SD↗

arXiv2024

Variable Time Step Reinforcement Learning for Robotic Applications

Traditional reinforcement learning (RL) generates discrete control policies, assigning one action per cycle. These policies are usually implemented as in a fixed-frequency control loop. This rigidity presents challenges as optimal control frequency is task-dependent; suboptimal frequencies increase computational demands and reduce exploration efficiency. Variable Time Step Reinforcement Learning (VTS-RL) addresses these issues with adaptive control frequencies, executing actions only when necessary, thus reducing computational load and extending the action space to include action durations. In this paper we introduce the Multi-Objective Soft Elastic Actor-Critic (MOSEAC) method to perform VTS-RL, validating it through theoretical analysis and experimentation in simulation and on real robots. Results show faster convergence, better training results, and reduced energy consumption with respect to other variable- or fixed-frequency approaches.

cs.RO↗

arXiv2024

Experimental test of generalized multipartite entropic uncertainty relations

Entropic uncertainty relation (EUR) formulates the restriction of the inherent uncertainty of quantum mechanics from the information-theoretic perspective. A tighter lower bound for uncertainty relations can provide information-theoretic security to quantum communication protocols. Recently, a generalized EUR (GEUR) for the measurement of multiple observables in arbitrary many-body systems has been formulated. Here, we experimentally test this GEUR using a four-photon entangled state with a controllable decoherence channel and show that for the tripartite scenario, the GEUR improves the entropic bound from Renes--Boileau's famous results. As an application, we further demonstrate an improvement of the secure key rate in quantum key distribution from the GEUR. Our results extend the test of EURs into multipartite regimes and may find applications in practical quantum cryptography tasks.

quant-ph↗

arXiv2024

Optimal $(2,δ)$ Locally Repairable Codes via Punctured Simplex Codes

Locally repairable codes (LRCs) have attracted a lot of attention due to their applications in distributed storage systems. In this paper, we provide new constructions of optimal $(2, δ)$-LRCs over $\mathbb{F}_q$ with flexible parameters. Firstly, employing techniques from finite geometry, we introduce a simple yet useful condition to ensure that a punctured simplex code becomes a $(2, δ)$-LRC. It is worth noting that this condition only imposes a requirement on the size of the puncturing set. Secondly, utilizing character sums over finite fields and Krawtchouk polynomials, we determine the parameters of more punctured simplex codes with puncturing sets of new structures. Several infinite families of LRCs with new parameters are derived. All of our new LRCs are optimal with respect to the generalized Cadambe-Mazumdar bound and some of them are also Griesmer codes or distance-optimal codes.

cs.IT↗

arXiv2024

Retrieval Augmented Fact Verification by Synthesizing Contrastive Arguments

The rapid propagation of misinformation poses substantial risks to public interest. To combat misinformation, large language models (LLMs) are adapted to automatically verify claim credibility. Nevertheless, existing methods heavily rely on the embedded knowledge within LLMs and / or black-box APIs for evidence collection, leading to subpar performance with smaller LLMs or upon unreliable context. In this paper, we propose retrieval augmented fact verification through the synthesis of contrasting arguments (RAFTS). Upon input claims, RAFTS starts with evidence retrieval, where we design a retrieval pipeline to collect and re-rank relevant documents from verifiable sources. Then, RAFTS forms contrastive arguments (i.e., supporting or refuting) conditioned on the retrieved evidence. In addition, RAFTS leverages an embedding model to identify informative demonstrations, followed by in-context prompting to generate the prediction and explanation. Our method effectively retrieves relevant documents as evidence and evaluates arguments from varying perspectives, incorporating nuanced information for fine-grained decision-making. Combined with informative in-context examples as prior, RAFTS achieves significant improvements to supervised and LLM baselines without complex prompts. We demonstrate the effectiveness of our method through extensive experiments, where RAFTS can outperform GPT-based methods with a significantly smaller 7B LLM.

cs.CL↗

arXiv2024

CNVSRC 2023: The First Chinese Continuous Visual Speech Recognition Challenge

The first Chinese Continuous Visual Speech Recognition Challenge aimed to probe the performance of Large Vocabulary Continuous Visual Speech Recognition (LVC-VSR) on two tasks: (1) Single-speaker VSR for a particular speaker and (2) Multi-speaker VSR for a set of registered speakers. The challenge yielded highly successful results, with the best submission significantly outperforming the baseline, particularly in the single-speaker task. This paper comprehensively reviews the challenge, encompassing the data profile, task specifications, and baseline system construction. It also summarises the representative techniques employed by the submitted systems, highlighting the most effective approaches. Additional information and resources about this challenge can be accessed through the official website at http://cnceleb.org/competition.

cs.CL↗