arXiv subjects

Lu Yang

Publications and source records attributed to Lu Yang.

At least 37 records · Page 2Linked to original sources

arXiv2025

AutoMAS: A Generic Multi-Agent System for Algorithm Self-Adaptation in Wireless Networks

The wireless communication environment has the characteristic of strong dynamics. Conventional wireless networks operate based on the static rules with predefined algorithms, lacking the self-adaptation ability. The rapid development of artificial intelligence (AI) provides a possibility for wireless networks to become more intelligent and fully automated. As such, we plan to integrate the cognitive capability and high intelligence of the emerging AI agents into wireless networks. In this work, we propose AutoMAS, a generic multi-agent system which can autonomously select the most suitable wireless optimization algorithm according to the dynamic wireless environment. Our AutoMAS combines theoretically guaranteed wireless algorithms with agents' perception ability, thereby providing sounder solutions to complex tasks no matter how the environment changes. As an example, we conduct a case study on the classical channel estimation problem, where the mobile user moves in diverse environments with different channel propagation characteristics. Simulation results demonstrate that our AutoMAS can guarantee the highest accuracy in changing scenarios. Similarly, our AutoMAS can be generalized to autonomously handle various tasks in 6G wireless networks with high accuracy.

eess.SP↗

arXiv2025

LSAP: Rethinking Inversion Fidelity, Perception and Editability in GAN Latent Space

As research on image inversion advances, the process is generally divided into two stages. The first step is Image Embedding, involves using an encoder or optimization procedure to embed an image and obtain its corresponding latent code. The second stage, referred to as Result Refinement, further improves the inversion and editing outcomes. Although this refinement stage substantially enhances reconstruction fidelity, perception and editability remain largely unchanged and are highly dependent on the latent codes derived from the first stage. Therefore, a key challenge lies in obtaining latent codes that preserve reconstruction fidelity while simultaneously improving perception and editability. In this work, we first reveal that these two properties are closely related to the degree of alignment (or disalignment) between the inverted latent codes and the synthetic distribution. Based on this insight, we propose the \textbf{ Latent Space Alignment Inversion Paradigm (LSAP)}, which integrates both an evaluation metric and a unified inversion solution. Specifically, we introduce the \textbf{Normalized Style Space ($\mathcal{S^N}$ space)} and \textbf{Normalized Style Space Cosine Distance (NSCD)} to quantify the disalignment of inversion methods. Moreover, our paradigm can be optimized for both encoder-based and optimization-based embeddings, providing a consistent alignment framework. Extensive experiments across various domains demonstrate that NSCD effectively captures perceptual and editable characteristics, and that our alignment paradigm achieves state-of-the-art performance in both stages of inversion.

cs.CV↗

arXiv2025

Hyper-VIB: A Hypernetwork-Enhanced Information Bottleneck Approach for Task-Oriented Communications

This paper presents Hyper-VIB, a hypernetwork-enhanced information bottleneck (IB) approach designed to enable efficient task-oriented communications in 6G collaborative intelligent systems. Leveraging IB theory, our approach enables an optimal end-to-end joint training of device and network models, in terms of the maximal task execution accuracy as well as the minimal communication overhead, through optimizing the trade-off hyperparameter. To address computational intractability in high-dimensional IB optimization, a tractable variational upper-bound approximation is derived. Unlike conventional grid or random search methods that require multiple training rounds with substantial computational costs, Hyper-VIB introduces a hypernetwork that generates approximately optimal DNN parameters for different values of the hyperparameter within a single training phase. Theoretical analysis in the linear case validates the hypernetwork design. Experimental results demonstrate our Hyper-VIB's superior accuracy and training efficiency over conventional VIB approaches in both classification and regression tasks.

cs.IT↗

arXiv2025

A Novel Algorithm for Representing Positive Semi-Definite Polynomials as Sums of Squares with Rational Coefficients

This paper presents a novel algorithm for constructing a sum-of-squares (SOS) decomposition for positive semi-definite polynomials with rational coefficients. Unlike previous methods that typically yield SOS decompositions with floating-point coefficients, our approach ensures that all coefficients in the decomposition remain rational. This is particularly useful in formal verification and symbolic computation, where exact arithmetic is required. We introduce a stepwise reduction technique that transforms a given polynomial into a sum of ladder-like squares while preserving rationality. Experimental results demonstrate the effectiveness of our method compared to existing numerical approaches. This artical is an extension of the following Chinnese paper: HUANG Yong , ZENG Zhenbing , YANG Lu , RAO Yongsheng. An Algorithm to Represent Positive Semi-Definite Polynomials to Sum of Lader-Like Squares of Polynomials with Rational Coefficients (in Chinese). Journal of Systems Science and Mathematical Sciences, 2024, 44(5): 1241-1271 https://doi.org/10.12341/jssms23584CM

cs.SC↗

arXiv2025

How Far Are We from Optimal Reasoning Efficiency?

Large Reasoning Models (LRMs) demonstrate remarkable problem-solving capabilities through extended Chain-of-Thought (CoT) reasoning but often produce excessively verbose and redundant reasoning traces. This inefficiency incurs high inference costs and limits practical deployment. While existing fine-tuning methods aim to improve reasoning efficiency, assessing their efficiency gains remains challenging due to inconsistent evaluations. In this work, we introduce the reasoning efficiency frontiers, empirical upper bounds derived from fine-tuning base LRMs across diverse approaches and training configurations. Based on these frontiers, we propose the Reasoning Efficiency Gap (REG), a unified metric quantifying deviations of any fine-tuned LRMs from these frontiers. Systematic evaluation on challenging mathematical benchmarks reveals significant gaps in current methods: they either sacrifice accuracy for short length or still remain inefficient under tight token budgets. To reduce the efficiency gap, we propose REO-RL, a class of Reinforcement Learning algorithms that minimizes REG by targeting a sparse set of token budgets. Leveraging numerical integration over strategically selected budgets, REO-RL approximates the full efficiency objective with low error using a small set of token budgets. Through systematic benchmarking, we demonstrate that our efficiency metric, REG, effectively captures the accuracy-length trade-off, with low-REG methods reducing length while maintaining accuracy. Our approach, REO-RL, consistently reduces REG by >=50 across all evaluated LRMs and matching Qwen3-4B/8B efficiency frontiers under a 16K token budget with minimal accuracy loss. Ablation studies confirm the effectiveness of our exponential token budget strategy. Finally, our findings highlight that fine-tuning LRMs to perfectly align with the efficiency frontiers remains an open challenge.

cs.CL↗

arXiv2025

Multiple SLEs and Dyson Brownian motion: transition density and Green's function

We consider multiple chordal Schramm-Loewner evolution (SLE) with $κ\in (0,4]$. Under common-time parameterization, we show that the transition density of the driving function of multiple chordal SLEs can be given by the transition density of Dyson Brownian motion and Green's function. This is a companion paper of [FWY24].

math.PR↗

arXiv2025

PCLVis: Visual Analytics of Process Communication Latency in Large-Scale Simulation

Large-scale simulations on supercomputers have become important tools for users. However, their scalability remains a problem due to the huge communication cost among parallel processes. Most of the existing communication latency analysis methods rely on the physical link layer information, which is only available to administrators. In this paper, a framework called PCLVis is proposed to help general users analyze process communication latency (PCL) events. Instead of the physical link layer information, the PCLVis uses the MPI process communication data for the analysis. First, a spatial PCL event locating method is developed. All processes with high correlation are classified into a single cluster by constructing a process-correlation tree. Second, the propagation path of PCL events is analyzed by constructing a communication-dependency-based directed acyclic graph (DAG), which can help users interactively explore a PCL event from the temporal evolution of a located PCL event cluster. In this graph, a sliding window algorithm is designed to generate the PCL events abstraction. Meanwhile, a new glyph called the communication state glyph (CS-Glyph) is designed for each process to show its communication states, including its in/out messages and load balance. Each leaf node can be further unfolded to view additional information. Third, a PCL event attribution strategy is formulated to help users optimize their simulations. The effectiveness of the PCLVis framework is demonstrated by analyzing the PCL events of several simulations running on the TH-1A supercomputer. By using the proposed framework, users can greatly improve the efficiency of their simulations.

cs.CV↗

arXiv2025

WMAS: A Multi-Agent System Towards Intelligent and Customized Wireless Networks

The fast development of Artificial Intelligence (AI) agents provides a promising way for the realization of intelligent and customized wireless networks. In this paper, we propose a Wireless Multi-Agent System (WMAS), which can provide intelligent and customized services for different user equipment (UEs). Note that orchestrating multiple agents carries the risk of malfunction, and multi-agent conversations may fall into infinite loops. It is thus crucial to design a conversation topology for WMAS that enables agents to complete UE task requests with high accuracy and low conversation overhead. To address this issue, we model the multi-agent conversation topology as a directed acyclic graph and propose a reinforcement learning-based algorithm to optimize the adjacency matrix of this graph. As such, WMAS is capable of generating and self-optimizing multi-agent conversation topologies, enabling agents to effectively and collaboratively handle a variety of task requests from UEs. Simulation results across various task types demonstrate that WMAS can achieve higher task performance and lower conversation overhead compared to existing multi-agent systems. These results validate the potential of WMAS to enhance the intelligence of future wireless networks.

cs.MA↗

arXiv2025

Distribution-Based Masked Medical Vision-Language Model Using Structured Reports

Medical image-language pre-training aims to align medical images with clinically relevant text to improve model performance on various downstream tasks. However, existing models often struggle with the variability and ambiguity inherent in medical data, limiting their ability to capture nuanced clinical information and uncertainty. This work introduces an uncertainty-aware medical image-text pre-training model that enhances generalization capabilities in medical image analysis. Building on previous methods and focusing on Chest X-Rays, our approach utilizes structured text reports generated by a large language model (LLM) to augment image data with clinically relevant context. These reports begin with a definition of the disease, followed by the `appearance' section to highlight critical regions of interest, and finally `observations' and `verdicts' that ground model predictions in clinical semantics. By modeling both inter- and intra-modal uncertainty, our framework captures the inherent ambiguity in medical images and text, yielding improved representations and performance on downstream tasks. Our model demonstrates significant advances in medical image-text pre-training, obtaining state-of-the-art performance on multiple downstream tasks.

cs.CV↗

arXiv2025

Laser transfer and retrieval via nanophotonic supercontinuum process

The nature of optical metrology is to perform efficient transfer and precise retrieval for lasers and optical signals, which is beneficial for a variety of applications ranging from optical clocking, spectroscopy, to telecommunications and quantum optics. While efforts have been made to promote the detection accuracy of optical frequencies, retrieval on optical waveforms remains on the autocorrelation scheme with limited performances. Here, we demonstrate a novel scheme for optical metrology, particularly on direct retrieval of optical waveform in terms of the field amplitude profile. The scheme is based on massive four-wave-mixings underlying a nanophotonic supercontinuum process, which enables arbitrary transfer of an additive laser to modulational sidebands of the broadened continuum. Detection of the transferred signals is then flexible to be within the whole span of the supercontinuum from visible to the mid-infrared range. We demonstrate such a transfer scheme for both CW lasers and pulsed lasers. For the latter, the temporal amplitude profile of the optical wave can be retrieved, which reveals high-order dynamics of solitary pulses including the self-steepening, self-compression, and the soliton splitting, and shows a remarkable square-fold increase of signal-to-noise ratio in the power spectrum. Our results may contribute to advance optical metrology particularly towards chip scale optical waveform detection, and more fundamentally, they reveal insights of massive ultrafast nonlinear interactions underlying the soliton-based supercontinuum process.

physics.optics↗

arXiv2025

Preliminary Explorations with GPT-4o(mni) Native Image Generation

Recently, the visual generation ability by GPT-4o(mni) has been unlocked by OpenAI. It demonstrates a very remarkable generation capability with excellent multimodal condition understanding and varied task instructions. In this paper, we aim to explore the capabilities of GPT-4o across various tasks. Inspired by previous study, we constructed a task taxonomy along with a carefully curated set of test samples to conduct a comprehensive qualitative test. Benefiting from GPT-4o's powerful multimodal comprehension, its image-generation process demonstrates abilities surpassing those of traditional image-generation tasks. Thus, regarding the dimensions of model capabilities, we evaluate its performance across six task categories: traditional image generation tasks, discriminative tasks, knowledge-based generation, commonsense-based generation, spatially-aware image generation, and temporally-aware image generation. These tasks not only assess the quality and conditional alignment of the model's outputs but also probe deeper into GPT-4o's understanding of real-world concepts. Our results reveal that GPT-4o performs impressively well in general-purpose synthesis tasks, showing strong capabilities in text-to-image generation, visual stylization, and low-level image processing. However, significant limitations remain in its ability to perform precise spatial reasoning, instruction-grounded generation, and consistent temporal prediction. Furthermore, when faced with knowledge-intensive or domain-specific scenarios, such as scientific illustrations or mathematical plots, the model often exhibits hallucinations, factual errors, or structural inconsistencies. These findings suggest that while GPT-4o marks a substantial advancement in unified multimodal generation, there is still a long way to go before it can be reliably applied to professional or safety-critical domains.

cs.CV↗

arXiv2025

NTIRE 2025 Challenge on Event-Based Image Deblurring: Methods and Results

This paper presents an overview of NTIRE 2025 the First Challenge on Event-Based Image Deblurring, detailing the proposed methodologies and corresponding results. The primary goal of the challenge is to design an event-based method that achieves high-quality image deblurring, with performance quantitatively assessed using Peak Signal-to-Noise Ratio (PSNR). Notably, there are no restrictions on computational complexity or model size. The task focuses on leveraging both events and images as inputs for single-image deblurring. A total of 199 participants registered, among whom 15 teams successfully submitted valid results, offering valuable insights into the current state of event-based image deblurring. We anticipate that this challenge will drive further advancements in event-based vision research.

cs.CV↗

arXiv2025

LLGS: Unsupervised Gaussian Splatting for Image Enhancement and Reconstruction in Pure Dark Environment

3D Gaussian Splatting has shown remarkable capabilities in novel view rendering tasks and exhibits significant potential for multi-view optimization.However, the original 3D Gaussian Splatting lacks color representation for inputs in low-light environments. Simply using enhanced images as inputs would lead to issues with multi-view consistency, and current single-view enhancement systems rely on pre-trained data, lacking scene generalization. These problems limit the application of 3D Gaussian Splatting in low-light conditions in the field of robotics, including high-fidelity modeling and feature matching. To address these challenges, we propose an unsupervised multi-view stereoscopic system based on Gaussian Splatting, called Low-Light Gaussian Splatting (LLGS). This system aims to enhance images in low-light environments while reconstructing the scene. Our method introduces a decomposable Gaussian representation called M-Color, which separately characterizes color information for targeted enhancement. Furthermore, we propose an unsupervised optimization method with zero-knowledge priors, using direction-based enhancement to ensure multi-view consistency. Experiments conducted on real-world datasets demonstrate that our system outperforms state-of-the-art methods in both low-light enhancement and 3D Gaussian Splatting.

cs.CV↗

arXiv2025

Image is All You Need to Empower Large-scale Diffusion Models for In-Domain Generation

In-domain generation aims to perform a variety of tasks within a specific domain, such as unconditional generation, text-to-image, image editing, 3D generation, and more. Early research typically required training specialized generators for each unique task and domain, often relying on fully-labeled data. Motivated by the powerful generative capabilities and broad applications of diffusion models, we are driven to explore leveraging label-free data to empower these models for in-domain generation. Fine-tuning a pre-trained generative model on domain data is an intuitive but challenging way and often requires complex manual hyper-parameter adjustments since the limited diversity of the training data can easily disrupt the model's original generative capabilities. To address this challenge, we propose a guidance-decoupled prior preservation mechanism to achieve high generative quality and controllability by image-only data, inspired by preserving the pre-trained model from a denoising guidance perspective. We decouple domain-related guidance from the conditional guidance used in classifier-free guidance mechanisms to preserve open-world control guidance and unconditional guidance from the pre-trained model. We further propose an efficient domain knowledge learning technique to train an additional text-free UNet copy to predict domain guidance. Besides, we theoretically illustrate a multi-guidance in-domain generation pipeline for a variety of generative tasks, leveraging multiple guidances from distinct diffusion models and conditions. Extensive experiments demonstrate the superiority of our method in domain-specific synthesis and its compatibility with various diffusion-based control methods and applications.

cs.CV↗

arXiv2025

Towards Harmless Multimodal Assistants with Blind Preference Optimization

Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in multimodal understanding, reasoning, and interaction. Given the extensive applications of MLLMs, the associated safety issues have become increasingly critical. Due to the effectiveness of preference optimization in aligning MLLMs with human preferences, there is an urgent need for safety-related preference data for MLLMs. To address this, we construct the MMSafe-PO preference dataset towards harmless multimodal assistants, featuring multimodal instructions, the conversational format, and ranked paired responses from human feedback. We also identify two insightful observations: modality co-defense and modality cheating, which illustrate that MLLMs possess a certain level of inherent defense while still presenting unique safety challenges. Based on these observations, we propose the Blind Preference Optimization (BPO) approach. Comprehensive experiments on three benchmarks show that BPO effectively enhances the safety capabilities of MLLMs. Notably, BPO significantly improves the safety rate of the base MLLM by 45.0%, outperforming the DPO approach. Additionally, applying BPO to the MMSafe-PO dataset greatly reduces the base MLLM's unsafe rate on other safety benchmarks (14.5% on MM-SafetyBench and 82.9% on HarmEval, demonstrating the effectiveness and robustness of both the dataset and the approach. We release code and data at https://lu-yang666.github.io/MMsafe-PO-Web/.

cs.CL↗

arXiv2025

Exploring Position Encoding in Diffusion U-Net for Training-free High-resolution Image Generation

Denoising higher-resolution latents via a pre-trained U-Net leads to repetitive and disordered image patterns. Although recent studies make efforts to improve generative quality by aligning denoising process across original and higher resolutions, the root cause of suboptimal generation is still lacking exploration. Through comprehensive analysis of position encoding in U-Net, we attribute it to inconsistent position encoding, sourced by the inadequate propagation of position information from zero-padding to latent features in convolution layers as resolution increases. To address this issue, we propose a novel training-free approach, introducing a Progressive Boundary Complement (PBC) method. This method creates dynamic virtual image boundaries inside the feature map to enhance position information propagation, enabling high-quality and rich-content high-resolution image synthesis. Extensive experiments demonstrate the superiority of our method.

cs.CV↗

arXiv2025

Label Drop for Multi-Aspect Relation Modeling in Universal Information Extraction

Universal Information Extraction (UIE) has garnered significant attention due to its ability to address model explosion problems effectively. Extractive UIE can achieve strong performance using a relatively small model, making it widely adopted. Extractive UIEs generally rely on task instructions for different tasks, including single-target instructions and multiple-target instructions. Single-target instruction UIE enables the extraction of only one type of relation at a time, limiting its ability to model correlations between relations and thus restricting its capability to extract complex relations. While multiple-target instruction UIE allows for the extraction of multiple relations simultaneously, the inclusion of irrelevant relations introduces decision complexity and impacts extraction accuracy. Therefore, for multi-relation extraction, we propose LDNet, which incorporates multi-aspect relation modeling and a label drop mechanism. By assigning different relations to different levels for understanding and decision-making, we reduce decision confusion. Additionally, the label drop mechanism effectively mitigates the impact of irrelevant relations. Experiments show that LDNet outperforms or achieves competitive performance with state-of-the-art systems on 9 tasks, 33 datasets, in both single-modal and multi-modal, few-shot and zero-shot settings.\footnote{https://github.com/Lu-Yang666/LDNet}

cs.CL↗

arXiv2025

NOTA: Multimodal Music Notation Understanding for Visual Large Language Model

Symbolic music is represented in two distinct forms: two-dimensional, visually intuitive score images, and one-dimensional, standardized text annotation sequences. While large language models have shown extraordinary potential in music, current research has primarily focused on unimodal symbol sequence text. Existing general-domain visual language models still lack the ability of music notation understanding. Recognizing this gap, we propose NOTA, the first large-scale comprehensive multimodal music notation dataset. It consists of 1,019,237 records, from 3 regions of the world, and contains 3 tasks. Based on the dataset, we trained NotaGPT, a music notation visual large language model. Specifically, we involve a pre-alignment training phase for cross-modal alignment between the musical notes depicted in music score images and their textual representation in ABC notation. Subsequent training phases focus on foundational music information extraction, followed by training on music notation analysis. Experimental results demonstrate that our NotaGPT-7B achieves significant improvement on music understanding, showcasing the effectiveness of NOTA and the training pipeline. Our datasets are open-sourced at https://huggingface.co/datasets/MYTH-Lab/NOTA-dataset.

cs.CV↗