arXiv subjects

Zhicheng Zhang

Publications and source records attributed to Zhicheng Zhang.

At least 73 records · Page 4Linked to original sources

arXiv2025

Multi-scale Activation, Refinement, and Aggregation: Exploring Diverse Cues for Fine-Grained Bird Recognition

Given the critical role of birds in ecosystems, Fine-Grained Bird Recognition (FGBR) has gained increasing attention, particularly in distinguishing birds within similar subcategories. Although Vision Transformer (ViT)-based methods often outperform Convolutional Neural Network (CNN)-based methods in FGBR, recent studies reveal that the limited receptive field of plain ViT model hinders representational richness and makes them vulnerable to scale variance. Thus, enhancing the multi-scale capabilities of existing ViT-based models to overcome this bottleneck in FGBR is a worthwhile pursuit. In this paper, we propose a novel framework for FGBR, namely Multi-scale Diverse Cues Modeling (MDCM), which explores diverse cues at different scales across various stages of a multi-scale Vision Transformer (MS-ViT) in an "Activation-Selection-Aggregation" paradigm. Specifically, we first propose a multi-scale cue activation module to ensure the discriminative cues learned at different stage are mutually different. Subsequently, a multi-scale token selection mechanism is proposed to remove redundant noise and highlight discriminative, scale-specific cues at each stage. Finally, the selected tokens from each stage are independently utilized for bird recognition, and the recognition results from multiple stages are adaptively fused through a multi-scale dynamic aggregation mechanism for final model decisions. Both qualitative and quantitative results demonstrate the effectiveness of our proposed MDCM, which outperforms CNN- and ViT-based models on several widely-used FGBR benchmarks.

cs.CV↗

arXiv2025

Majorana Flat Bands in the Vortex Line of Superconducting Weyl Semimetals

We report the emergence of Majorana flat bands (MFBs) in the vortex line of superconducting (SC) time-reversal-symmetry-breaking Weyl semimetals. By considering a Weyl semimetal as a stack of Chern insulators with varying Chern numbers along one ($z$) direction, we decompose the vortex bound states of SC Weyl semimetals into those of $k_{z}$-resolved SC Chern insulators. Through analytical and numerical calculations of the topological phase diagram of the SC Chern insulators, we explain the appearance of MFBs and determine the exact boundaries of them. Notably, the tuning of chemical potential or pairing strength results in the MFBs along the entire $k_{z}$ axis. To characterize the MFBs, we propose a $k_{z}$-resolved $Z_{2}$ Chern-Simons invariant as the topological indicator. Finally, we take an attractive Hubbard interaction into consideration, and the aforementioned SC Weyl semimetal with BCS pairing can be realized under appropriate parameters.

cond-mat.supr-con↗

arXiv2025

Enhancing Adversarial Robustness of Vision-Language Models through Low-Rank Adaptation

Vision-Language Models (VLMs) play a crucial role in the advancement of Artificial General Intelligence (AGI). As AGI rapidly evolves, addressing security concerns has emerged as one of the most significant challenges for VLMs. In this paper, we present extensive experiments that expose the vulnerabilities of conventional adaptation methods for VLMs, highlighting significant security risks. Moreover, as VLMs grow in size, the application of traditional adversarial adaptation techniques incurs substantial computational costs. To address these issues, we propose a parameter-efficient adversarial adaptation method called \textbf{\textit{AdvLoRA}} based on Low-Rank Adaptation. We investigate and reveal the inherent low-rank properties involved in adversarial adaptation for VLMs. Different from LoRA, we enhance the efficiency and robustness of adversarial adaptation by introducing a novel reparameterization method that leverages parameter clustering and alignment. Additionally, we propose an adaptive parameter update strategy to further bolster robustness. These innovations enable our AdvLoRA to mitigate issues related to model security and resource wastage. Extensive experiments confirm the effectiveness and efficiency of AdvLoRA.

cs.CV↗

arXiv2025

Flaming-hot Initiation with Regular Execution Sampling for Large Language Models

Since the release of ChatGPT, large language models (LLMs) have demonstrated remarkable capabilities across various domains. A key challenge in developing these general capabilities is efficiently sourcing diverse, high-quality data. This becomes especially critical in reasoning-related tasks with sandbox checkers, such as math or code, where the goal is to generate correct solutions to specific problems with higher probability. In this work, we introduce Flaming-hot Initiation with Regular Execution (FIRE) sampling, a simple yet highly effective method to efficiently find good responses. Our empirical findings show that FIRE sampling enhances inference-time generation quality and also benefits training in the alignment stage. Furthermore, we explore how FIRE sampling improves performance by promoting diversity and analyze the impact of employing FIRE at different positions within a response.

cs.LG↗

arXiv2025

Perception Compressor: A Training-Free Prompt Compression Framework in Long Context Scenarios

Large language models (LLMs) demonstrate exceptional capabilities in various scenarios. However, they suffer from much redundant information and are sensitive to the position of key information in long context scenarios. To address these challenges, we present Perception Compressor, a training-free prompt compression framework. It includes a perception retriever that leverages guiding questions and instruction to retrieve the most relevant demonstrations, a dual-slope ratio allocator to dynamically allocate compression ratios and open-book ratios, and a semi-guided iterative compression that retains key information at the token level while removing tokens that distract the LLM. We conduct extensive experiments on long context benchmarks, i.e., NaturalQuestions, LongBench, and MuSiQue. Experiment results show that Perception Compressor outperforms existing methods by a large margin, achieving state-of-the-art performance.

cs.CL↗

arXiv2024

Flow Matching for Optimal Reaction Coordinates of Biomolecular System

We present flow matching for reaction coordinates (FMRC), a novel deep learning algorithm designed to identify optimal reaction coordinates (RC) in biomolecular reversible dynamics. FMRC is based on the mathematical principles of lumpability and decomposability, which we reformulate into a conditional probability framework for efficient data-driven optimization using deep generative models. While FMRC does not explicitly learn the well-established transfer operator or its eigenfunctions, it can effectively encode the dynamics of leading eigenfunctions of the system transfer operator into its low-dimensional RC space. We further quantitatively compare its performance with several state-of-the-art algorithms by evaluating the quality of Markov state models (MSM) constructed in their respective RC spaces, demonstrating the superiority of FMRC in three increasingly complex biomolecular systems. In addition, we successfully demonstrated the efficacy of FMRC for bias deposition in the enhanced sampling of a simple model system. Finally, we discuss its potential applications in downstream applications such as enhanced sampling methods and MSM construction.

cs.LG↗

arXiv2024

Enhancing Transformer-based models for Long Sequence Time Series Forecasting via Structured Matrix

Recently, Transformer-based models for long sequence time series forecasting have demonstrated promising results. The self-attention mechanism as the core component of these Transformer-based models exhibits great potential in capturing various dependencies among data points. Despite these advancements, it has been a subject of concern to improve the efficiency of the self-attention mechanism. Unfortunately, current specific optimization methods are facing the challenges in applicability and scalability for the future design of long sequence time series forecasting models. Hence, in this article, we propose a novel architectural framework that enhances Transformer-based models through the integration of Surrogate Attention Blocks (SAB) and Surrogate Feed-Forward Neural Network Blocks (SFB). The framework reduces both time and space complexity by the replacement of the self-attention and feed-forward layers with SAB and SFB while maintaining their expressive power and architectural advantages. The equivalence of this substitution is fully demonstrated. The extensive experiments on 10 Transformer-based models across five distinct time series tasks demonstrate an average performance improvement of 12.4%, alongside 61.3% reduction in parameter counts.

cs.LG↗

arXiv2024

Mirabolic Howe duality

We establish a duality between a pair of mirabolic quantum groups, i.e., the mirabolic counterpart of quantum Howe duality.

math.QA↗

arXiv2024

DP and QP Based Decision-making and Planning for Autonomous Vehicle

Autonomous driving technology is rapidly evolving and becoming a pivotal element of modern automation systems. Effective decision-making and planning are essential to ensuring autonomous vehicles operate safely and efficiently in complex environments. This paper introduces a decision-making and planning framework for autonomous vehicles, leveraging dynamic programming (DP) for global path planning and quadratic programming (QP) for local trajectory optimization. The proposed approach utilizes S-T graphs to achieve both dynamic and static obstacle avoidance. A comprehensive vehicle dynamics model supports the control system, enabling precise path tracking and obstacle handling. Simulation studies are conducted to evaluate the system's performance in a variety of scenarios, including global path planning, static obstacle avoidance, and dynamic obstacle avoidance involving pedestrian interactions. The results confirm the effectiveness and robustness of the proposed decision-making and planning algorithms in navigating complex environments, demonstrating the feasibility of this approach for autonomous driving applications.

cs.RO↗

arXiv2024

Verification of Recursively Defined Quantum Circuits

Recursive techniques have recently been introduced into quantum programming so that a variety of large quantum circuits and algorithms can be elegantly and economically programmed. In this paper, we present a proof system for formal verification of the correctness of recursively defined quantum circuits. The soundness and (relative) completeness of the proof system are established. To demonstrating its effectiveness, a series of application examples of the proof system are given, including (multi-qubit) controlled gates, a quantum circuit generating (multi-qubit) GHZ (Greenberger-Horne-Zeilinger) states, recursive definition of quantum Fourier transform, quantum state preparation, and quantum random-access memories (QRAM).

quant-ph↗

arXiv2024

Optimal Low-dimensional Approximation of Transfer Operators via Flow Matching: Computation and Error Analysis

Reaction coordinates (RCs) are low-dimensional representations of complex dynamical systems that capture their long-term dynamics. In this work, we focus on the criteria of lumpability and decomposability, previously established for assessing RCs, and propose a new flow matching approach for the analysis and optimization of reaction coordinates based on these criteria. This method effectively utilizes data to quantitatively determine whether a given RC satisfies these criteria and enables end-to-end optimization of the reaction coordinate mapping model. Furthermore, we provide a theoretical analysis of the relationship between the loss function used in our approach and the operator error induced by dimension reduction.

math.NA↗

arXiv2024

MTDA-HSED: Mutual-Assistance Tuning and Dual-Branch Aggregating for Heterogeneous Sound Event Detection

Sound Event Detection (SED) plays a vital role in comprehending and perceiving acoustic scenes. Previous methods have demonstrated impressive capabilities. However, they are deficient in learning features of complex scenes from heterogeneous dataset. In this paper, we introduce a novel dual-branch architecture named Mutual-Assistance Tuning and Dual-Branch Aggregating for Heterogeneous Sound Event Detection (MTDA-HSED). The MTDA-HSED architecture employs the Mutual-Assistance Audio Adapter (M3A) to effectively tackle the multi-scenario problem and uses the Dual-Branch Mid-Fusion (DBMF) module to tackle the multi-granularity problem. Specifically, M3A is integrated into the BEATs block as an adapter to improve the BEATs' performance by fine-tuning it on the multi-scenario dataset. The DBMF module connects BEATs and CNN branches, which facilitates the deep fusion of information from the BEATs and the CNN branches. Experimental results show that the proposed methods exceed the baseline of mpAUC by \textbf{$5\%$} on the DESED and MAESTRO Real datasets. Code is available at https://github.com/Visitor-W/MTDA.

cs.SD↗

arXiv2024

Reliable Deep Diffusion Tensor Estimation: Rethinking the Power of Data-Driven Optimization Routine

Diffusion tensor imaging (DTI) holds significant importance in clinical diagnosis and neuroscience research. However, conventional model-based fitting methods often suffer from sensitivity to noise, leading to decreased accuracy in estimating DTI parameters. While traditional data-driven deep learning methods have shown potential in terms of accuracy and efficiency, their limited generalization to out-of-training-distribution data impedes their broader application due to the diverse scan protocols used across centers, scanners, and studies. This work aims to tackle these challenges and promote the use of DTI by introducing a data-driven optimization-based method termed DoDTI. DoDTI combines the weighted linear least squares fitting algorithm and regularization by denoising technique. The former fits DW images from diverse acquisition settings into diffusion tensor field, while the latter applies a deep learning-based denoiser to regularize the diffusion tensor field instead of the DW images, which is free from the limitation of fixed-channel assignment of the network. The optimization object is solved using the alternating direction method of multipliers and then unrolled to construct a deep neural network, leveraging a data-driven strategy to learn network parameters. Extensive validation experiments are conducted utilizing both internally simulated datasets and externally obtained in-vivo datasets. The results, encompassing both qualitative and quantitative analyses, showcase that the proposed method attains state-of-the-art performance in DTI parameter estimation. Notably, it demonstrates superior generalization, accuracy, and efficiency, rendering it highly reliable for widespread application in the field.

cs.CV↗

arXiv2024

Full-frequency dynamic convolution: a physical frequency-dependent convolution for sound event detection

Recently, 2D convolution has been found unqualified in sound event detection (SED). It enforces translation equivariance on sound events along frequency axis, which is not a shift-invariant dimension. To address this issue, dynamic convolution is used to model the frequency dependency of sound events. In this paper, we proposed the first full-dynamic method named full-frequency dynamic convolution (FFDConv). FFDConv generates frequency kernels for every frequency band, which is designed directly in the structure for frequency-dependent modeling. It physically furnished 2D convolution with the capability of frequency-dependent modeling. FFDConv outperforms not only the baseline by 6.6% in DESED real validation dataset in terms of PSDS1, but outperforms the other full-dynamic methods. In addition, by visualizing features of sound events, we observed that FFDConv could effectively extract coherent features in specific frequency bands, consistent with the vocal continuity of sound events. This proves that FFDConv has great frequency-dependent perception ability.

eess.AS↗

arXiv2024

Joint Auction in the Online Advertising Market

Online advertising is a primary source of income for e-commerce platforms. In the current advertising pattern, the oriented targets are the online store owners who are willing to pay extra fees to enhance the position of their stores. On the other hand, brand suppliers are also desirable to advertise their products in stores to boost brand sales. However, the currently used advertising mode cannot satisfy the demand of both stores and brand suppliers simultaneously. To address this, we innovatively propose a joint advertising model termed Joint Auction, allowing brand suppliers and stores to collaboratively bid for advertising slots, catering to both their needs. However, conventional advertising auction mechanisms are not suitable for this novel scenario. In this paper, we propose JRegNet, a neural network architecture for the optimal joint auction design, to generate mechanisms that can achieve the optimal revenue and guarantee near dominant strategy incentive compatibility and individual rationality. Finally, multiple experiments are conducted on synthetic and real data to demonstrate that our proposed joint auction significantly improves platform revenue compared to the known baselines.

cs.GT↗

arXiv2024

SELD-Mamba: Selective State-Space Model for Sound Event Localization and Detection with Source Distance Estimation

In the Sound Event Localization and Detection (SELD) task, Transformer-based models have demonstrated impressive capabilities. However, the quadratic complexity of the Transformer's self-attention mechanism results in computational inefficiencies. In this paper, we propose a network architecture for SELD called SELD-Mamba, which utilizes Mamba, a selective state-space model. We adopt the Event-Independent Network V2 (EINV2) as the foundational framework and replace its Conformer blocks with bidirectional Mamba blocks to capture a broader range of contextual information while maintaining computational efficiency. Additionally, we implement a two-stage training method, with the first stage focusing on Sound Event Detection (SED) and Direction of Arrival (DoA) estimation losses, and the second stage reintroducing the Source Distance Estimation (SDE) loss. Our experimental results on the 2024 DCASE Challenge Task3 dataset demonstrate the effectiveness of the selective state-space model in SELD and highlight the benefits of the two-stage training approach in enhancing SELD performance.

cs.SD↗

arXiv2024

Tight Quantum Depth Lower Bound for Solving Systems of Linear Equations

Since Harrow, Hassidim, and Lloyd (2009) showed that a system of linear equations with $N$ variables and condition number $κ$ can be solved on a quantum computer in $\operatorname{poly}(\log(N), κ)$ time, exponentially faster than any classical algorithms, its improvements and applications have been extensively investigated. The state-of-the-art quantum algorithm for this problem is due to Costa, An, Sanders, Su, Babbush, and Berry (2022), with optimal query complexity $Θ(κ)$. An important question left is whether parallelism can bring further optimization. In this paper, we study the limitation of parallel quantum computing on this problem. We show that any quantum algorithm for solving systems of linear equations with time complexity $\operatorname{poly}(\log(N), κ)$ has a lower bound of $Ω(κ)$ on the depth of queries, which is tight up to a constant factor.

quant-ph↗

arXiv2024

LAKE-RED: Camouflaged Images Generation by Latent Background Knowledge Retrieval-Augmented Diffusion

Camouflaged vision perception is an important vision task with numerous practical applications. Due to the expensive collection and labeling costs, this community struggles with a major bottleneck that the species category of its datasets is limited to a small number of object species. However, the existing camouflaged generation methods require specifying the background manually, thus failing to extend the camouflaged sample diversity in a low-cost manner. In this paper, we propose a Latent Background Knowledge Retrieval-Augmented Diffusion (LAKE-RED) for camouflaged image generation. To our knowledge, our contributions mainly include: (1) For the first time, we propose a camouflaged generation paradigm that does not need to receive any background inputs. (2) Our LAKE-RED is the first knowledge retrieval-augmented method with interpretability for camouflaged generation, in which we propose an idea that knowledge retrieval and reasoning enhancement are separated explicitly, to alleviate the task-specific challenges. Moreover, our method is not restricted to specific foreground targets or backgrounds, offering a potential for extending camouflaged vision perception to more diverse domains. (3) Experimental results demonstrate that our method outperforms the existing approaches, generating more realistic camouflage images.

cs.CV↗