arXiv subjects

Yu Zhang

Publications and source records attributed to Yu Zhang.

At least 775 records · Page 43Linked to original sources

arXiv2024

Morphing median fin enhances untethered bionic robotic tuna's linear acceleration and turning maneuverability

Median fins of fish-like swimmers play a crucial role in linear acceleration and maneuvering processes. However, few research focused on untethered robotic fish experiments. Imitating the behaviour of real tuna, we developed a free-swimming bionic tuna with a foldable dorsal fin. The erection of dorsal fin, at proper conditions, can reduce head heave by 50%, enhance linear acceleration by 15.7%, increase turning angular velocity by 32.78%, and turning radius decreasing by 33.13%. Conversely, erecting the dorsal fin increases the wetted surface area, resulting in decreased maximum speed and efficiency during steady swimming phase. This finding partially explains why tuna erect their median fins during maneuvers or acceleration and fold them afterward to reduce drag. In addition, we verified that folding the median fins after acceleration does not significantly affect locomotion efficiency. This study supports the application of morphing median fins in undulating underwater robots and helps to further understand the impact of median fins on fish locomotion.

cs.RO↗

arXiv2024

Load Restoration in Islanded Microgrids: Formulation and Solution Strategies

Adverse circumstances such as extreme weather events can cause significant disruptions to normal operation of electric distribution systems (DS), which includes isolating parts of the DS due to damaged transmission equipment. In this paper, we consider the problem of load restoration in a microgrid (MG) that is islanded from the upstream DS. The MG contains sources of distributed generation such as microturbines and renewable energy sources, as well as energy storage systems (ESS). We formulate the load restoration task as a non-convex optimization problem. This problem embodies the physics of the MG by leveraging a branch flow model, while incorporating salient phenomenon in islanded MGs such as the need for internal frequency regulation, and complementarity requirements arising in ESS operations. Since the formulated optimization problem is non-convex, we introduce a convex relaxation which can be solved through model predictive control as a baseline method. However, in order to solve the problem considering its full non-convexity, we leverage a policy-learning method called constrained policy optimization, a tailored version of which is used as our proposed algorithm. The aforementioned approaches, along with an additional deep learning method are compared through extensive simulations.

eess.SY↗

arXiv2024

Discrete Linear Canonical Transform on Graphs: Uncertainty Principle and Sampling

With an increasing influx of classical signal processing methodologies into the field of graph signal processing, approaches grounded in discrete linear canonical transform have found application in graph signals. In this paper, we initially propose the uncertainty principle of the graph linear canonical transform (GLCT), which is based on a class of graph signals maximally concentrated in both vertex and graph spectral domains. Subsequently, leveraging the uncertainty principle, we establish conditions for recovering bandlimited signals of the GLCT from a subset of samples, thereby formulating the sampling theory for the GLCT. We elucidate interesting connections between the uncertainty principle and sampling. Further, by employing sampling set selection and experimental design sampling strategies, we introduce optimal sampling operators in the GLCT domain. Finally, we evaluate the performance of our methods through simulations and numerical experiments across applications.

math.GM↗

arXiv2024

IG Captioner: Information Gain Captioners are Strong Zero-shot Classifiers

Generative training has been demonstrated to be powerful for building visual-language models. However, on zero-shot discriminative benchmarks, there is still a performance gap between models trained with generative and discriminative objectives. In this paper, we aim to narrow this gap by improving the efficacy of generative training on classification tasks, without any finetuning processes or additional modules. Specifically, we focus on narrowing the gap between the generative captioner and the CLIP classifier. We begin by analysing the predictions made by the captioner and classifier and observe that the caption generation inherits the distribution bias from the language model trained with pure text modality, making it less grounded on the visual signal. To tackle this problem, we redesign the scoring objective for the captioner to alleviate the distributional bias and focus on measuring the gain of information brought by the visual inputs. We further design a generative training objective to match the evaluation objective. We name our model trained and evaluated from the novel procedures as Information Gain (IG) captioner. We pretrain the models on the public Laion-5B dataset and perform a series of discriminative evaluations. For the zero-shot classification on ImageNet, IG captioner achieves $> 18\%$ improvements over the standard captioner, achieving comparable performances with the CLIP classifier. IG captioner also demonstrated strong performance on zero-shot image-text retrieval tasks on MSCOCO and Flickr30K. We hope this paper inspires further research towards unifying generative and discriminative training procedures for visual-language models.

cs.CV↗

arXiv2024

MTMamba: Enhancing Multi-Task Dense Scene Understanding by Mamba-Based Decoders

Multi-task dense scene understanding, which learns a model for multiple dense prediction tasks, has a wide range of application scenarios. Modeling long-range dependency and enhancing cross-task interactions are crucial to multi-task dense prediction. In this paper, we propose MTMamba, a novel Mamba-based architecture for multi-task scene understanding. It contains two types of core blocks: self-task Mamba (STM) block and cross-task Mamba (CTM) block. STM handles long-range dependency by leveraging Mamba, while CTM explicitly models task interactions to facilitate information exchange across tasks. Experiments on NYUDv2 and PASCAL-Context datasets demonstrate the superior performance of MTMamba over Transformer-based and CNN-based methods. Notably, on the PASCAL-Context dataset, MTMamba achieves improvements of +2.08, +5.01, and +4.90 over the previous best methods in the tasks of semantic segmentation, human parsing, and object boundary detection, respectively. The code is available at https://github.com/EnVision-Research/MTMamba.

cs.CV↗

arXiv2024

Learning Multiplex Representations on Text-Attributed Graphs with One Language Model Encoder

In real-world scenarios, texts in a graph are often linked by multiple semantic relations (e.g., papers in an academic graph are referenced by other publications, written by the same author, or published in the same venue), where text documents and their relations form a multiplex text-attributed graph. Mainstream text representation learning methods use pretrained language models (PLMs) to generate one embedding for each text unit, expecting that all types of relations between texts can be captured by these single-view embeddings. However, this presumption does not hold particularly in multiplex text-attributed graphs. Along another line of work, multiplex graph neural networks (GNNs) directly initialize node attributes as a feature vector for node representation learning, but they cannot fully capture the semantics of the nodes' associated texts. To bridge these gaps, we propose METAG, a new framework for learning Multiplex rEpresentations on Text-Attributed Graphs. In contrast to existing methods, METAG uses one text encoder to model the shared knowledge across relations and leverages a small number of parameters per relation to derive relation-specific representations. This allows the encoder to effectively capture the multiplex structures in the graph while also preserving parameter efficiency. We conduct experiments on nine downstream tasks in five graphs from both academic and e-commerce domains, where METAG outperforms baselines significantly and consistently. The code is available at https://github.com/PeterGriffinJin/METAG.

cs.CL↗

arXiv2024

Stabilizing Dynamic Systems through Neural Network Learning: A Robust Approach

Point-to-point and periodic motions are ubiquitous in the world of robotics. To master these motions, Autonomous Dynamic System (DS) based algorithms are fundamental in the domain of Learning from Demonstration (LfD). However, these algorithms face the significant challenge of balancing precision in learning with the maintenance of system stability. This paper addresses this challenge by presenting a novel ADS algorithm that leverages neural network technology. The proposed algorithm is designed to distill essential knowledge from demonstration data, ensuring stability during the learning of both point-to-point and periodic motions. For point-to-point motions, a neural Lyapunov function is proposed to align with the provided demonstrations. In the case of periodic motions, the neural Lyapunov function is used with the transversal contraction to ensure that all generated motions converge to a stable limit cycle. The model utilizes a streamlined neural network architecture, adept at achieving dual objectives: optimizing learning accuracy while maintaining global stability. To thoroughly assess the efficacy of the proposed algorithm, rigorous evaluations are conducted using the LASA dataset and a manually designed dataset. These assessments were complemented by empirical validation through robotic experiments, providing robust evidence of the algorithm's performance

cs.RO↗

arXiv2024

AUITestAgent: Automatic Requirements Oriented GUI Function Testing

The Graphical User Interface (GUI) is how users interact with mobile apps. To ensure it functions properly, testing engineers have to make sure it functions as intended, based on test requirements that are typically written in natural language. While widely adopted manual testing and script-based methods are effective, they demand substantial effort due to the vast number of GUI pages and rapid iterations in modern mobile apps. This paper introduces AUITestAgent, the first automatic, natural language-driven GUI testing tool for mobile apps, capable of fully automating the entire process of GUI interaction and function verification. Since test requirements typically contain interaction commands and verification oracles. AUITestAgent can extract GUI interactions from test requirements via dynamically organized agents. Then, AUITestAgent employs a multi-dimensional data extraction strategy to retrieve data relevant to the test requirements from the interaction trace and perform verification. Experiments on customized benchmarks demonstrate that AUITestAgent outperforms existing tools in the quality of generated GUI interactions and achieved the accuracy of verifications of 94%. Moreover, field deployment in Meituan has shown AUITestAgent's practical usability, with it detecting 4 new functional bugs during 10 regression tests in two months.

cs.SE↗

arXiv2024

A First-Order Multi-Gradient Algorithm for Multi-Objective Bi-Level Optimization

In this paper, we study the Multi-Objective Bi-Level Optimization (MOBLO) problem, where the upper-level subproblem is a multi-objective optimization problem and the lower-level subproblem is for scalar optimization. Existing gradient-based MOBLO algorithms need to compute the Hessian matrix, causing the computational inefficient problem. To address this, we propose an efficient first-order multi-gradient method for MOBLO, called FORUM. Specifically, we reformulate MOBLO problems as a constrained multi-objective optimization (MOO) problem via the value-function approach. Then we propose a novel multi-gradient aggregation method to solve the challenging constrained MOO problem. Theoretically, we provide the complexity analysis to show the efficiency of the proposed method and a non-asymptotic convergence result. Empirically, extensive experiments demonstrate the effectiveness and efficiency of the proposed FORUM method in different learning problems. In particular, it achieves state-of-the-art performance on three multi-task learning benchmark datasets. The code is available at https://github.com/Baijiong-Lin/FORUM.

cs.LG↗

arXiv2024

Additive and subtractive bases of $ \mathbb{Z}_m$ in average

Given a positive integer $m$, let $\mathbb{Z}_m$ be the set of residue classes mod $m$. For $A\subseteq \mathbb{Z}_m$ and $n\in \mathbb{Z}_m$, let $σ_A(n)$ be the number of solutions to the equation $n=x+y$ with $x,y\in A$. Let $\mathcal{H}_m$ be the set of subsets $A\subseteq \mathbb{Z}_m$ such that $σ_A(n)\geq1$ for all $n\in \mathbb{Z}_m$. Let $$ \ell_m=\min\limits_{A\in \mathcal{H}_m}\left\lbrace m^{-1}\sum_{n\in \mathbb{Z}_m}σ_A(n)\right\rbrace. $$ Following a prior result of Ding and Zhao on Ruzsa's number, we know that $$ \limsup_{m\rightarrow\infty}\ell_m\le 192. $$ Ding and Zhao then asked possible improvements on this value. In this paper, we prove $$ \limsup\limits_{m\rightarrow\infty}\ell_m\leq 144. $$ Moreover, parallel results on subtractive bases of $ \mathbb{Z}_m$ were also investigated here.

math.NT↗

arXiv2024

Spin/Phonon Dynamics in Single Molecular Magnets: II. spin/phonon entanglemen

We introduce a new quantum embedding method to explore spin-phonon interactions in molecular magnets. This technique consolidates various spin/phonon couplings into a limited number of collective degrees of freedom, allowing for a fully quantum mechanical treatment. By precisely factorizing the entire system into "system" and "bath" sub-ensembles, our approach simplifies a previously intractable problem, making it solvable on modest-scale computers. We demonstrate the effectiveness of this method by studying the spin relaxation and dephasing times of the single-molecule qubit \ce{VOPc(OH)8}, which features a lone unpaired electron on the central vanadium atom. By using this mode projection method, we are able to perform numerical exact quantum dynamical calculation on this system which allows us to follow the flow of quantum information from the single spin qubit into the projected phonon degrees of freedom. Our results demonstrate both the utility of the method and suggest how one can engineer the environment as to further optimize the quantum properties of a qubit system.

quant-ph↗

arXiv2024

Spin/Phonon Dynamics in Single Molecular Magnets: I. quantum embedding

Single molecular magnets (SMMs) and Metal-Organic Frameworks (MOFs) attract significant interest due to their potential in quantum information processing, scalable quantum computing, and extended lifetimes and coherence times. The limiting factor in these systems is often the spin dephasing caused by interactions and couplings with the vibrational motions of the molecular framework. This work introduces a systematic projection/embedding scheme to analyze spin-phonon dynamics in molecular magnets. This scheme consolidates all spin/phonon couplings into a few collective degrees of freedom. quantum mechanically. Using parameters obtained from ab initio methods for spin/phonon coupling via Zeeman interaction, we apply this approach to compute the electronic spin relaxation times for a single-molecule qubit \ce{VOPc(OH)8}, which features a single unpaired electron localized on the central vanadium atom. However, our general embedding scheme can be applied to any single-molecule magnet or qubit MOF with any coupling/interaction Hamiltonian. This development offers a crucial tool for simulating spin relaxation in complex environments with significantly reduced computational complexity.

quant-ph↗

arXiv2024

Multiple scattering and diffusion of scalar coherent waves in a group of small spheroidal particles with random orientations

In this manuscript we study multiple scattering and diffusion of scalar wave in a group of monodisperse spheroidal particles with random orientations. We begin by fixing a spheroid in a prolate spheroidal coordinate system, and attain the expansion of the scalar Green's function in this space. The expansion is firstly based on spheroidal wave functions, and then we transform it into the expansion of spherical wave functions. Next, we average the Green's function over the orientations of the spheroid to get the averaged transition operator. Finally, we calculate the transport mean free path and anisotropy factor for the spheroidal particles group, based on the irreducible vertex in the Bethe-Salpeter equation. The approaches to get the average transition operator and the mean free paths in this manuscript will be of benefit to the research area of multiple scattering by non-spherical particles.

physics.optics↗

arXiv2024

Mixture of Cluster-conditional LoRA Experts for Vision-language Instruction Tuning

Instruction tuning of Large Vision-language Models (LVLMs) has revolutionized the development of versatile models with zero-shot generalization across a wide range of downstream vision-language tasks. However, the diversity of training tasks of different sources and formats would lead to inevitable task conflicts, where different tasks conflict for the same set of model parameters, resulting in sub-optimal instruction-following abilities. To address that, we propose the Mixture of Cluster-conditional LoRA Experts (MoCLE), a novel Mixture of Experts (MoE) architecture designed to activate the task-customized model parameters based on the instruction clusters. A separate universal expert is further incorporated to improve generalization capabilities of MoCLE for novel instructions. Extensive experiments on InstructBLIP and LLaVA demonstrate the effectiveness of MoCLE.

cs.CV↗

arXiv2024

Origin of extended Main Sequence Turn Off in open cluster NGC 2355

The presence of extended Main Sequence Turn-Off (eMSTO) in the open clusters has been attributed to various factors, such as spread in rotation rates, binary stars, and dust-like extinction from stellar excretion discs. We present a comprehensive analysis of the eMSTO in the open cluster NGC 2355. Using spectra from the Gaia-ESO archives, we find that the stars in the red part of the eMSTO have a higher mean v sin i value of 135.3$\pm$4.6 km s$^{-1}$ compared to the stars in the blue part that have an average v sin i equal to 81.3$\pm$5.6 km s$^{-1}$. This suggests that the eMSTO in NGC 2355 is possibly caused by the spread in rotation rates of stars. We do not find any substantial evidence of the dust-like extinction from the eMSTO stars using ultraviolet data from the Swift survey. The estimated synchronization time for low mass ratio close binaries in the blue part of the eMSTO suggests that they would be mostly slow-rotating if present. However, the stars in the blue part of the eMSTO are preferentially located in the outer region of the cluster indicating that they may lack low mass ratio close binaries. The spread in rotation rates of eMSTO stars in NGC 2355 is most likely caused by the star-disc interaction mechanism. The stars in the lower main sequence beyond the eMSTO region of NGC 2355 are slow-rotating (mean v sin i = 26.5$\pm$1.3 km s$^{-1}$) possibly due to the magnetic braking of their rotations.

astro-ph.SR↗

arXiv2024

Quantum voting machine encoded with microwave photons

We propose a simple quantum voting machine using microwave photon qubit encoding, based on a setup comprising multiple microwave cavities and a coupled superconducting flux qutrit. This approach primarily relies on a multi-control single-target quantum phase gate. The scheme offers operational simplicity, requiring only a single step, while ensuring verifiability through the measurement of a single qubit phase information to obtain the voting results. And it provides voter anonymity, as the voting outcome is solely tied to the total number of affirmative votes. Our quantum voting machine also has scalability in terms of the number of voters. Additionally, the physical realization of the quantum voting machine is general and not limited to circuit QED. Quantum voting machine can be implemented as long as the multi-control single-phase quantum phase gate is realized in other physical systems. Numerical simulations indicate the feasibility of this quantum voting machine within the current quantum technology.

quant-ph↗

arXiv2024

Learning Retrieval Augmentation for Personalized Dialogue Generation

Personalized dialogue generation, focusing on generating highly tailored responses by leveraging persona profiles and dialogue context, has gained significant attention in conversational AI applications. However, persona profiles, a prevalent setting in current personalized dialogue datasets, typically composed of merely four to five sentences, may not offer comprehensive descriptions of the persona about the agent, posing a challenge to generate truly personalized dialogues. To handle this problem, we propose $\textbf{L}$earning Retrieval $\textbf{A}$ugmentation for $\textbf{P}$ersonalized $\textbf{D}$ial$\textbf{O}$gue $\textbf{G}$eneration ($\textbf{LAPDOG}$), which studies the potential of leveraging external knowledge for persona dialogue generation. Specifically, the proposed LAPDOG model consists of a story retriever and a dialogue generator. The story retriever uses a given persona profile as queries to retrieve relevant information from the story document, which serves as a supplementary context to augment the persona profile. The dialogue generator utilizes both the dialogue history and the augmented persona profile to generate personalized responses. For optimization, we adopt a joint training framework that collaboratively learns the story retriever and dialogue generator, where the story retriever is optimized towards desired ultimate metrics (e.g., BLEU) to retrieve content for the dialogue generator to generate personalized responses. Experiments conducted on the CONVAI2 dataset with ROCStory as a supplementary data source show that the proposed LAPDOG method substantially outperforms the baselines, indicating the effectiveness of the proposed method. The LAPDOG model code is publicly available for further exploration. https://github.com/hqsiswiliam/LAPDOG

cs.CL↗

arXiv2024

Selective Prompting Tuning for Personalized Conversations with LLMs

In conversational AI, personalizing dialogues with persona profiles and contextual understanding is essential. Despite large language models' (LLMs) improved response coherence, effective persona integration remains a challenge. In this work, we first study two common approaches for personalizing LLMs: textual prompting and direct fine-tuning. We observed that textual prompting often struggles to yield responses that are similar to the ground truths in datasets, while direct fine-tuning tends to produce repetitive or overly generic replies. To alleviate those issues, we propose \textbf{S}elective \textbf{P}rompt \textbf{T}uning (SPT), which softly prompts LLMs for personalized conversations in a selective way. Concretely, SPT initializes a set of soft prompts and uses a trainable dense retriever to adaptively select suitable soft prompts for LLMs according to different input contexts, where the prompt retriever is dynamically updated through feedback from the LLMs. Additionally, we propose context-prompt contrastive learning and prompt fusion learning to encourage the SPT to enhance the diversity of personalized conversations. Experiments on the CONVAI2 dataset demonstrate that SPT significantly enhances response diversity by up to 90\%, along with improvements in other critical performance indicators. Those results highlight the efficacy of SPT in fostering engaging and personalized dialogue generation. The SPT model code (https://github.com/hqsiswiliam/SPT) is publicly available for further exploration.

cs.CL↗