arXiv subjects

Zheng Wang

Publications and source records attributed to Zheng Wang.

At least 199 records · Page 11Linked to original sources

arXiv2025

A Lightweight Hybrid Dual Channel Speech Enhancement System under Low-SNR Conditions

Although deep learning based multi-channel speech enhancement has achieved significant advancements, its practical deployment is often limited by constrained computational resources, particularly in low signal-to-noise ratio (SNR) conditions. In this paper, we propose a lightweight hybrid dual-channel speech enhancement system that combines independent vector analysis (IVA) with a modified version of the dual-channel grouped temporal convolutional recurrent network (GTCRN). IVA functions as a coarse estimator, providing auxiliary information for both speech and noise, while the modified GTCRN further refines the speech quality. We investigate several modifications to ensure the comprehensive utilization of both original and auxiliary information. Experimental results demonstrate the effectiveness of the proposed system, achieving enhanced speech with minimal parameters and low computational complexity.

eess.AS↗

arXiv2025

LEGO-Compiler: Enhancing Neural Compilation Through Translation Composability

Large language models (LLMs) have the potential to revolutionize how we design and implement compilers and code translation tools. However, existing LLMs struggle to handle long and complex programs. We introduce LEGO-Compiler, a novel neural compilation system that leverages LLMs to translate high-level languages into assembly code. Our approach centers on three key innovations: LEGO translation, which decomposes the input program into manageable blocks; breaking down the complex compilation process into smaller, simpler verifiable steps by organizing it as a verifiable LLM workflow by external tests; and a feedback mechanism for self-correction. Supported by formal proofs of translation composability, LEGO-Compiler demonstrates high accuracy on multiple datasets, including over 99% on ExeBench and 97.9% on industrial-grade AnsiBench. Additionally, LEGO-Compiler has also acheived near one order-of-magnitude improvement on compilable code size scalability. This work opens new avenues for applying LLMs to system-level tasks, complementing traditional compiler technologies.

cs.PL↗

arXiv2025

AI Idea Bench 2025: AI Research Idea Generation Benchmark

Large-scale Language Models (LLMs) have revolutionized human-AI interaction and achieved significant success in the generation of novel ideas. However, current assessments of idea generation overlook crucial factors such as knowledge leakage in LLMs, the absence of open-ended benchmarks with grounded truth, and the limited scope of feasibility analysis constrained by prompt design. These limitations hinder the potential of uncovering groundbreaking research ideas. In this paper, we present AI Idea Bench 2025, a framework designed to quantitatively evaluate and compare the ideas generated by LLMs within the domain of AI research from diverse perspectives. The framework comprises a comprehensive dataset of 3,495 AI papers and their associated inspired works, along with a robust evaluation methodology. This evaluation system gauges idea quality in two dimensions: alignment with the ground-truth content of the original papers and judgment based on general reference material. AI Idea Bench 2025's benchmarking system stands to be an invaluable resource for assessing and comparing idea-generation techniques, thereby facilitating the automation of scientific discovery.

cs.AI↗

arXiv2025

Human-Aligned Bench: Fine-Grained Assessment of Reasoning Ability in MLLMs vs. Humans

The goal of achieving Artificial General Intelligence (AGI) is to imitate humans and surpass them. Models such as OpenAI's o1, o3, and DeepSeek's R1 have demonstrated that large language models (LLMs) with human-like reasoning capabilities exhibit exceptional performance and are being gradually integrated into multimodal large language models (MLLMs). However, whether these models possess capabilities comparable to humans in handling reasoning tasks remains unclear at present. In this paper, we propose Human-Aligned Bench, a benchmark for fine-grained alignment of multimodal reasoning with human performance. Specifically, we collected 9,794 multimodal questions that solely rely on contextual reasoning, including bilingual (Chinese and English) multimodal questions and pure text-based questions, encompassing four question types: visual reasoning, definition judgment, analogical reasoning, and logical judgment. More importantly, each question is accompanied by human success rates and options that humans are prone to choosing incorrectly. Extensive experiments on the Human-Aligned Bench reveal notable differences between the performance of current MLLMs in multimodal reasoning and human performance. The findings on our benchmark provide insights into the development of the next-generation models.

cs.CV↗

arXiv2025

DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection

Anomaly detection has garnered extensive applications in real industrial manufacturing due to its remarkable effectiveness and efficiency. However, previous generative-based models have been limited by suboptimal reconstruction quality, hampering their overall performance. We introduce DiffusionAD, a novel anomaly detection pipeline comprising a reconstruction sub-network and a segmentation sub-network. A fundamental enhancement lies in our reformulation of the reconstruction process using a diffusion model into a noise-to-norm paradigm. Here, the anomalous region loses its distinctive features after being disturbed by Gaussian noise and is subsequently reconstructed into an anomaly-free one. Afterward, the segmentation sub-network predicts pixel-level anomaly scores based on the similarities and discrepancies between the input image and its anomaly-free reconstruction. Additionally, given the substantial decrease in inference speed due to the iterative denoising nature of diffusion models, we revisit the denoising process and introduce a rapid one-step denoising paradigm. This paradigm achieves hundreds of times acceleration while preserving comparable reconstruction quality. Furthermore, considering the diversity in the manifestation of anomalies, we propose a norm-guided paradigm to integrate the benefits of multiple noise scales, enhancing the fidelity of reconstructions. Comprehensive evaluations on four standard and challenging benchmarks reveal that DiffusionAD outperforms current state-of-the-art approaches and achieves comparable inference speed, demonstrating the effectiveness and broad applicability of the proposed pipeline. Code is released at https://github.com/HuiZhang0812/DiffusionAD

cs.CV↗

arXiv2025

Doppler Resilient Complementary Sequences: Tighter Aperiodic Ambiguity Function Bound and Optimal Constructions

Doppler-resilient complementary sequence sets (DRCSs) are crucial in modern communication and sensing systems in mobile environments. In this paper, we propose a new lower bound for the aperiodic ambiguity function (AF) of unimodular DRCSs based on weight vectors, which generalizes the existing bound as a special case. The proposed lower bound is tighter than the Shen-Yang-Zhou-Liu-Fan bound. Finally, we propose a novel class of aperiodic DRCSs with small alphabets based on quasi-Florentine rectangles and Butson-type Hadamard matrices. Interestingly, the proposed DRCSs asymptotically satisfy the proposed bound.

cs.IT↗

arXiv2025

RoNo: A novel way in generating reconfigurable on-chip nonlinear activation functions

Due to the limitations of Moore's Law and the increasing demand of computing, optical neural network (ONNs) are gradually coming to the stage as an alternative to electrical neural networks. The control of nonlinear activation functions in optical environments, as an important component of neural networks, has always been a challenge. In this work, firstly, we use inverse design tools to design a optical patterned area in silicon-carbide-on-insulator. This patterned area could generate two different nonlinear responses of the amplitude. Secondly, the patterned region is integrated with a control network to form a reconfigurable on-chip nonlinear activation function generator for wave-based analog computing. Experiment shows that neural network that uses such a system as an activation function performs well in the MNIST handwritten dataset and CIFAR-10, respectively. Compared to previous works, we propose a novel approach to generate on-chip reconfigurable activation functions in optical neural networks, which achieves compact footprint and enables high-quality activation function generation.

physics.optics↗

arXiv2025

BMTree: Designing, Learning, and Updating Piecewise Space-Filling Curves for Multi-Dimensional Data Indexing

Space-filling curves (SFC, for short) have been widely applied to index multi-dimensional data, which first maps the data to one dimension, and then a one-dimensional indexing method, e.g., the B-tree indexes the mapped data. Existing SFCs adopt a single mapping scheme for the whole data space. However, a single mapping scheme often does not perform well on all the data space. In this paper, we propose a new type of SFC called piecewise SFCs that adopts different mapping schemes for different data subspaces. Specifically, we propose a data structure termed the Bit Merging tree (BMTree) that can generate data subspaces and their SFCs simultaneously, and achieve desirable properties of the SFC for the whole data space. Furthermore, we develop a reinforcement learning-based solution to build the BMTree, aiming to achieve excellent query performance. To update the BMTree efficiently when the distributions of data and/or queries change, we develop a new mechanism that achieves fast detection of distribution shifts in data and queries, and enables partial retraining of the BMTree. The retraining mechanism achieves performance enhancement efficiently since it avoids retraining the BMTree from scratch. Extensive experiments show the effectiveness and efficiency of the BMTree with the proposed learning-based methods.

cs.DB↗

arXiv2025

Optimizing Personalized Federated Learning through Adaptive Layer-Wise Learning

Real-life deployment of federated Learning (FL) often faces non-IID data, which leads to poor accuracy and slow convergence. Personalized FL (pFL) tackles these issues by tailoring local models to individual data sources and using weighted aggregation methods for client-specific learning. However, existing pFL methods often fail to provide each local model with global knowledge on demand while maintaining low computational overhead. Additionally, local models tend to over-personalize their data during the training process, potentially dropping previously acquired global information. We propose FLAYER, a novel layer-wise learning method for pFL that optimizes local model personalization performance. FLAYER considers the different roles and learning abilities of neural network layers of individual local models. It incorporates global information for each local model as needed to initialize the local model cost-effectively. It then dynamically adjusts learning rates for each layer during local training, optimizing the personalized learning process for each local model while preserving global knowledge. Additionally, to enhance global representation in pFL, FLAYER selectively uploads parameters for global aggregation in a layer-wise manner. We evaluate FLAYER on four representative datasets in computer vision and natural language processing domains. Compared to six state-of-the-art pFL methods, FLAYER improves the inference accuracy, on average, by 5.40\% (up to 14.29\%).

cs.LG↗

arXiv2025

PSCon: Product Search Through Conversations

Conversational Product Search ( CPS ) systems interact with users via natural language to offer personalized and context-aware product lists. However, most existing research on CPS is limited to simulated conversations, due to the lack of a real CPS dataset driven by human-like language. Moreover, existing conversational datasets for e-commerce are constructed for a particular market or a particular language and thus can not support cross-market and multi-lingual usage. In this paper, we propose a CPS data collection protocol and create a new CPS dataset, called PSCon, which assists product search through conversations with human-like language. The dataset is collected by a coached human-human data collection protocol and is available for dual markets and two languages. By formulating the task of CPS, the dataset allows for comprehensive and in-depth research on six subtasks: user intent detection, keyword extraction, system action prediction, question selection, item ranking, and response generation. Moreover, we present a concise analysis of the dataset and propose a benchmark model on the proposed CPS dataset. Our proposed dataset and model will be helpful for facilitating future research on CPS.

cs.CL↗

arXiv2025

Devil is in Details: Locality-Aware 3D Abdominal CT Volume Generation for Self-Supervised Organ Segmentation

In the realm of medical image analysis, self-supervised learning (SSL) techniques have emerged to alleviate labeling demands, while still facing the challenge of training data scarcity owing to escalating resource requirements and privacy constraints. Numerous efforts employ generative models to generate high-fidelity, unlabeled 3D volumes across diverse modalities and anatomical regions. However, the intricate and indistinguishable anatomical structures within the abdomen pose a unique challenge to abdominal CT volume generation compared to other anatomical regions. To address the overlooked challenge, we introduce the Locality-Aware Diffusion (Lad), a novel method tailored for exquisite 3D abdominal CT volume generation. We design a locality loss to refine crucial anatomical regions and devise a condition extractor to integrate abdominal priori into generation, thereby enabling the generation of large quantities of high-quality abdominal CT volumes essential for SSL tasks without the need for additional data such as labels or radiology reports. Volumes generated through our method demonstrate remarkable fidelity in reproducing abdominal structures, achieving a decrease in FID score from 0.0034 to 0.0002 on AbdomenCT-1K dataset, closely mirroring authentic data and surpassing current methods. Extensive experiments demonstrate the effectiveness of our method in self-supervised organ segmentation tasks, resulting in an improvement in mean Dice scores on two abdominal datasets effectively. These results underscore the potential of synthetic data to advance self-supervised learning in medical image analysis.

eess.IV↗

arXiv2025

InstructRAG: Leveraging Retrieval-Augmented Generation on Instruction Graphs for LLM-Based Task Planning

Recent advancements in large language models (LLMs) have enabled their use as agents for planning complex tasks. Existing methods typically rely on a thought-action-observation (TAO) process to enhance LLM performance, but these approaches are often constrained by the LLMs' limited knowledge of complex tasks. Retrieval-augmented generation (RAG) offers new opportunities by leveraging external databases to ground generation in retrieved information. In this paper, we identify two key challenges (enlargability and transferability) in applying RAG to task planning. We propose InstructRAG, a novel solution within a multi-agent meta-reinforcement learning framework, to address these challenges. InstructRAG includes a graph to organize past instruction paths (sequences of correct actions), an RL-Agent with Reinforcement Learning to expand graph coverage for enlargability, and an ML-Agent with Meta-Learning to improve task generalization for transferability. The two agents are trained end-to-end to optimize overall planning performance. Our experiments on four widely used task planning datasets demonstrate that InstructRAG significantly enhances performance and adapts efficiently to new tasks, achieving up to a 19.2% improvement over the best existing approach.

cs.AI↗

arXiv2025

Constants of motion network revisited

Discovering constants of motion is meaningful in helping understand the dynamical systems, but inevitably needs proficient mathematical skills and keen analytical capabilities. With the prevalence of deep learning, methods employing neural networks, such as Constant Of Motion nETwork (COMET), are promising in handling this scientific problem. Although the COMET method can produce better predictions on dynamics by exploiting the discovered constants of motion, there is still plenty of room to sharpen it. In this paper, we propose a novel neural network architecture, built using the singular-value-decomposition (SVD) technique, and a two-phase training algorithm to improve the performance of COMET. Extensive experiments show that our approach not only retains the advantages of COMET, such as applying to non-Hamiltonian systems and indicating the number of constants of motion, but also can be more lightweight and noise-robust than COMET.

cs.LG↗

arXiv2025

ReorderBench: A Benchmark for Matrix Reordering

Matrix reordering permutes the rows and columns of a matrix to reveal meaningful visual patterns, such as blocks that represent clusters. A comprehensive collection of matrices, along with a scoring method for measuring the quality of visual patterns in these matrices, contributes to building a benchmark. This benchmark is essential for selecting or designing suitable reordering algorithms for specific tasks. In this paper, we build a matrix reordering benchmark, ReorderBench, with the goal of evaluating and improving matrix reordering techniques. This is achieved by generating a large set of representative and diverse matrices and scoring these matrices with a convolution- and entropy-based method. Our benchmark contains 2,835,000 binary matrices and 5,670,000 continuous matrices, each featuring one of four visual patterns: block, off-diagonal block, star, or band. We demonstrate the usefulness of ReorderBench through three main applications in matrix reordering: 1) evaluating different reordering algorithms, 2) creating a unified scoring model to measure the visual patterns in any matrix, and 3) developing a deep learning model for matrix reordering.

cs.HC↗

arXiv2025

VEGAS: Towards Visually Explainable and Grounded Artificial Social Intelligence

Social Intelligence Queries (Social-IQ) serve as the primary multimodal benchmark for evaluating a model's social intelligence level. While impressive multiple-choice question(MCQ) accuracy is achieved by current solutions, increasing evidence shows that they are largely, and in some cases entirely, dependent on language modality, overlooking visual context. Additionally, the closed-set nature further prevents the exploration of whether and to what extent the reasoning path behind selection is correct. To address these limitations, we propose the Visually Explainable and Grounded Artificial Social Intelligence (VEGAS) model. As a generative multimodal model, VEGAS leverages open-ended answering to provide explainable responses, which enhances the clarity and evaluation of reasoning paths. To enable visually grounded answering, we propose a novel sampling strategy to provide the model with more relevant visual frames. We then enhance the model's interpretation of these frames through Generalist Instruction Fine-Tuning (GIFT), which aims to: i) learn multimodal-language transformations for fundamental emotional social traits, and ii) establish multimodal joint reasoning capabilities. Extensive experiments, comprising modality ablation, open-ended assessments, and supervised MCQ evaluations, consistently show that VEGAS effectively utilizes visual information in reasoning to produce correct and also credible answers. We expect this work to of fer a new perspective on Social-IQ and advance the development of human-like social AI.

cs.AI↗

arXiv2025

The Mini-SiTian Array: first-two-year operation

The SiTian project, designed to utilize 60 telescopes distributed across multiple sites in China, is a next-generation time-domain survey initiative. As a pathfinder for the SiTian project, the Mini-SiTian (MST) has been proposed and implemented to test the SiTian's brain and data pipeline, and to evaluate the feasibility of its technology and science cases. Mounted at the Xinglong Observatory, the MST project comprises three 30 cm telescopes and has been operated since Nov. 2022. Each telescope of the MST possesses a large field of view, covering $2.29^{\circ}$ $\times$ $1.53^{\circ}$ FOV, and is equipped with $g'$, $r'$ and $i'$ filters, respectively. Acting as the pioneer of the forthcoming SiTian project, the MST is dedicated to the discovery of variable stars, transients, and outburst events, and has already obtained some interesting scientific results. In this paper, we will summarize the first-two-year operation of the MST project.

astro-ph.IM↗

arXiv2025

The Mini-SiTian Array: Design and application of Master Control System

The SiTian Project represents a groundbreaking initiative in astronomy, aiming to deploy a global network of telescopes, each with a 1-meter aperture, for comprehensive time-domain sky surveys. The network's innovative architecture features multiple observational nodes, each comprising three strategically aligned telescopes equipped with filters. This design enables three-color (g, r, i) channel imaging within each node, facilitating precise and coordinated observations. As a pathfinder to the full-scale project, the Mini-SiTian Project serves as the scientific and technological validation platform, utilizing three 30-centimeter aperture telescopes to validate the methodologies and technologies planned for the broader SiTian network. This paper focuses on the development and implementation of the Master Control System (MCS),and the central command hub for the Mini-SiTian array. The MCS is designed to facilitate seamless communication with the SiTian Brain, the project's central processing and decision-making unit, while ensuring accurate task allocation, real-time status monitoring, and optimized observational workflows. The system adopts a robust architecture that separates front-end and back-end functionalities.A key innovation of the MCS is its ability to dynamically adjust observation plans in response to transient source alerts, enabling rapid and coordinated scans of target sky regions...(abridged)

astro-ph.IM↗

arXiv2025

A Prototype-Guided Coarse Annotations Refining Approach for Whole Slide Images

The fine-grained annotations in whole slide images (WSIs) show the boundaries of various pathological regions. However, generating such detailed annotation is often costly, whereas the coarse annotations are relatively simpler to produce. Existing methods for refining coarse annotations often rely on extensive training samples or clean datasets, and fail to capture both intra-slide and inter-slide latent sematic patterns, limiting their precision. In this paper, we propose a prototype-guided approach. Specifically, we introduce a local-to-global approach to construct non-redundant representative prototypes by jointly modeling intra-slide local semantics and inter-slide contextual relationships. Then a prototype-guided pseudo-labeling module is proposed for refining coarse annotations. Finally, we employ dynamic data sampling and re-finetuning strategy to train a patch classifier. Extensive experiments on three publicly available WSI datasets, covering lymph, liver, and colorectal cancers, demonstrate that our method significantly outperforms existing state-of-the-art (SOTA) methods. The code will be available.

cs.CV↗