arXiv subjects

Yuxuan Sun

Publications and source records attributed to Yuxuan Sun.

At least 55 records · Page 3Linked to original sources

arXiv2025

Multimodal LLM Integrated Semantic Communications for 6G Immersive Experiences

6G networks promise revolutionary immersive communication experiences including augmented reality (AR), virtual reality (VR), and holographic communications. These applications demand high-dimensional multimodal data transmission and intelligent data processing in real-time, which is extremely challenging over resource-limited wireless communication systems. Moreover, a joint understanding of the environment, context, and user intent is essential to deliver task-relevant content effectively. This article presents a novel multimodal large language model (MLLM) integrated semantic communications framework, termed MLLM-SC, which fully leverages reasoning and generative capabilities of pre-trained foundation models for context-aware and task-oriented wireless communication. The MLLM-SC framework adopts a device-edge collaborative architecture. At the edge, MLLM-empowered semantic guidance module analyzes multimodal inputs, user intents, and channel conditions to generate importance-aware attention maps prioritizing semantically critical information. An importance-aware semantic encoder and a resource-adaptive semantic decoder are jointly designed and optimized, which can utilize the semantic guidance for adaptive bandwidth allocation and high-quality content reconstruction or generation. Extensive case studies on visual question answering for AR/VR applications and diffusion-driven image generation validate the effectiveness of MLLM-SC.

cs.LG↗

arXiv2025

Dynamic Scheduling for Vehicle-to-Vehicle Communications Enhanced Federated Learning

Leveraging the computing and sensing capabilities of vehicles, vehicular federated learning (VFL) has been applied to edge training for connected vehicles. The dynamic and interconnected nature of vehicular networks presents unique opportunities to harness direct vehicle-to-vehicle (V2V) communications, enhancing VFL training efficiency. In this paper, we formulate a stochastic optimization problem to optimize the VFL training performance, considering the energy constraints and mobility of vehicles, and propose a V2V-enhanced dynamic scheduling (VEDS) algorithm to solve it. The model aggregation requirements of VFL and the limited transmission time due to mobility result in a stepwise objective function, which presents challenges in solving the problem. We thus propose a derivative-based drift-plus-penalty method to convert the long-term stochastic optimization problem to an online mixed integer nonlinear programming (MINLP) problem, and provide a theoretical analysis to bound the performance gap between the online solution and the offline optimal solution. Further analysis of the scheduling priority reduces the original problem into a set of convex optimization problems, which are efficiently solved using the interior-point method. Experimental results demonstrate that compared with the state-of-the-art benchmarks, the proposed algorithm enhances the image classification accuracy on the CIFAR-10 dataset by 4.20% and reduces the average displacement errors on the Argoverse trajectory prediction dataset by 9.82%.

cs.LG↗

arXiv2025

FedCGD: Collective Gradient Divergence Optimized Scheduling for Wireless Federated Learning

Federated learning (FL) is a promising paradigm for multiple devices to cooperatively train a model. When applied in wireless networks, two issues consistently affect the performance of FL, i.e., data heterogeneity of devices and limited bandwidth. Many papers have investigated device scheduling strategies considering the two issues. However, most of them recognize data heterogeneity as a property of individual devices. In this paper, we prove that the convergence speed of FL is affected by the sum of device-level and sample-level collective gradient divergence (CGD). The device-level CGD refers to the gradient divergence of the scheduled device group, instead of the sum of the individual device divergence. The sample-level CGD is statistically upper bounded by sampling variance, which is inversely proportional to the total number of samples scheduled for local update. To derive a tractable form of the device-level CGD, we further consider a classification problem and transform it into the weighted earth moving distance (WEMD) between the group distribution and the global distribution. Then we propose FedCGD algorithm to minimize the sum of multi-level CGDs by balancing WEMD and sampling variance, within polynomial time. Simulation shows that the proposed strategy increases classification accuracy on the CIFAR-10 dataset by up to 4.2\% while scheduling 41.8\% fewer devices, and flexibly switches between reducing WEMD and reducing sampling variance.

cs.LG↗

arXiv2025

Mobility-Aware Asynchronous Federated Learning with Dynamic Sparsification

Asynchronous Federated Learning (AFL) enables distributed model training across multiple mobile devices, allowing each device to independently update its local model without waiting for others. However, device mobility introduces intermittent connectivity, which necessitates gradient sparsification and leads to model staleness, jointly affecting AFL convergence. This paper develops a theoretical model to characterize the interplay among sparsification, model staleness and mobility-induced contact patterns, and their joint impact on AFL convergence. Based on the analysis, we propose a mobility-aware dynamic sparsification (MADS) algorithm that optimizes the sparsification degree based on contact time and model staleness. Closed-form solutions are derived, showing that under low-speed conditions, MADS increases the sparsification degree to enhance convergence, while under high-speed conditions, it reduces the sparsification degree to guarantee reliable uploads within limited contact time. Experimental results validate the theoretical findings. Compared with the state-of-the-art benchmarks, the MADS algorithm increases the image classification accuracy on the CIFAR-10 dataset by 8.76% and reduces the average displacement error in the Argoverse trajectory prediction dataset by 9.46%.

cs.LG↗

arXiv2025

RoboMoRe: LLM-based Robot Co-design via Joint Optimization of Morphology and Reward

Robot co-design, jointly optimizing morphology and control policy, remains a longstanding challenge in the robotics community, where many promising robots have been developed. However, a key limitation lies in its tendency to converge to sub-optimal designs due to the use of fixed reward functions, which fail to explore the diverse motion modes suitable for different morphologies. Here we propose RoboMoRe, a large language model (LLM)-driven framework that integrates morphology and reward shaping for co-optimization within the robot co-design loop. RoboMoRe performs a dual-stage optimization: in the coarse optimization stage, an LLM-based diversity reflection mechanism generates both diverse and high-quality morphology-reward pairs and efficiently explores their distribution. In the fine optimization stage, top candidates are iteratively refined through alternating LLM-guided reward and morphology gradient updates. RoboMoRe can optimize both efficient robot morphologies and their suited motion behaviors through reward shaping. Results demonstrate that without any task-specific prompting or predefined reward/morphology templates, RoboMoRe significantly outperforms human-engineered designs and competing methods across eight different tasks.

cs.RO↗

arXiv2025

AAAR-1.0: Assessing AI's Potential to Assist Research

Numerous studies have assessed the proficiency of AI systems, particularly large language models (LLMs), in facilitating everyday tasks such as email writing, question answering, and creative content generation. However, researchers face unique challenges and opportunities in leveraging LLMs for their own work, such as brainstorming research ideas, designing experiments, and writing or reviewing papers. In this study, we introduce AAAR-1.0, a benchmark dataset designed to evaluate LLM performance in three fundamental, expertise-intensive research tasks: (i) EquationInference, assessing the correctness of equations based on the contextual information in paper submissions; (ii) ExperimentDesign, designing experiments to validate research ideas and solutions; (iii) PaperWeakness, identifying weaknesses in paper submissions; and (iv) REVIEWCRITIQUE, identifying each segment in human reviews is deficient or not. AAAR-1.0 differs from prior benchmarks in two key ways: first, it is explicitly research-oriented, with tasks requiring deep domain expertise; second, it is researcher-oriented, mirroring the primary activities that researchers engage in on a daily basis. An evaluation of both open-source and proprietary LLMs reveals their potential as well as limitations in conducting sophisticated research tasks. We will keep iterating AAAR-1.0 to new versions.

cs.CL↗

arXiv2025

MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark

This paper introduces MMMU-Pro, a robust version of the Massive Multi-discipline Multimodal Understanding and Reasoning (MMMU) benchmark. MMMU-Pro rigorously assesses multimodal models' true understanding and reasoning capabilities through a three-step process based on MMMU: (1) filtering out questions answerable by text-only models, (2) augmenting candidate options, and (3) introducing a vision-only input setting where questions are embedded within images. This setting challenges AI to truly "see" and "read" simultaneously, testing a fundamental human cognitive skill of seamlessly integrating visual and textual information. Results show that model performance is substantially lower on MMMU-Pro than on MMMU, ranging from 16.8% to 26.9% across models. We explore the impact of OCR prompts and Chain of Thought (CoT) reasoning, finding that OCR prompts have minimal effect while CoT generally improves performance. MMMU-Pro provides a more rigorous evaluation tool, closely mimicking real-world scenarios and offering valuable directions for future research in multimodal AI.

cs.CL↗

arXiv2025

FASR-Net: Unsupervised Shadow Removal Leveraging Inherent Frequency Priors

Shadow removal is challenging due to the complex interaction of geometry, lighting, and environmental factors. Existing unsupervised methods often overlook shadow-specific priors, leading to incomplete shadow recovery. To address this issue, we propose a novel unsupervised Frequency Aware Shadow Removal Network (FASR-Net), which leverages the inherent frequency characteristics of shadow regions. Specifically, the proposed Wavelet Attention Downsampling Module (WADM) integrates wavelet-based image decomposition and deformable attention, effectively breaking down the image into frequency components to enhance shadow details within specific frequency bands. We also introduce several new loss functions for precise shadow-free image reproduction: a frequency loss to capture image component details, a brightness-chromaticity loss that references the chromaticity of shadow-free regions, and an alignment loss to ensure smooth transitions between shadowed and shadow-free regions. Experimental results on the AISTD and SRD datasets demonstrate that our method achieves superior shadow removal performance.

cs.CV↗

arXiv2025

Characterizing positroid quotients of uniform matroids

We study two-step flag positroids $(P_1, P_2)$, where $P_1$ is a quotient of $P_{2}$. We provide a complete characterization of all two-step flag positroids that contain a uniform matroid, extending and completing a partial result by Benedetti, Chávez, and Jiménez. To contrast general positroids with the special case of lattice path matroids, we show that the containment relations of Grassmann necklaces and conecklaces fully characterize flag lattice path matroids, but are insufficient for general flag positroids. Additionally, we prove that the decorated permutations of any elementary quotient pair are related by a cyclic shift, resolving a conjecture of Benedetti, Chávez and Jiménez.

math.CO↗

arXiv2025

Hierarchy-Aware and Channel-Adaptive Semantic Communication for Bandwidth-Limited Data Fusion

Obtaining high-resolution hyperspectral images (HR-HSI) is costly and data-intensive, making it necessary to fuse low-resolution hyperspectral images (LR-HSI) with high-resolution RGB images (HR-RGB) for practical applications. However, traditional fusion techniques, which integrate detailed information into the reconstruction, significantly increase bandwidth consumption compared to directly transmitting raw data. To overcome these challenges, we propose a hierarchy-aware and channel-adaptive semantic communication approach for bandwidth-limited data fusion. A hierarchical correlation module is proposed to preserve both the overall structural information and the details of the image required for super-resolution. This module efficiently combines deep semantic and shallow features from LR-HSI and HR-RGB. To further reduce bandwidth usage while preserving reconstruction quality, a channel-adaptive attention mechanism based on Transformer is proposed to dynamically integrate and transmit the deep and shallow features, enabling efficient data transmission and high-quality HR-HSI reconstruction. Experimental results on the CAVE and Washington DC Mall datasets demonstrate that our method outperforms single-source transmission, achieving up to a 2 dB improvement in peak signal-to-noise ratio (PSNR). Additionally, it reduces bandwidth consumption by two-thirds, confirming its effectiveness in bandwidth-constrained environments for HR-HSI reconstruction tasks.

eess.IV↗

arXiv2025

VideoQA-SC: Adaptive Semantic Communication for Video Question Answering

Although semantic communication (SC) has shown its potential in efficiently transmitting multimodal data such as texts, speeches and images, SC for videos has focused primarily on pixel-level reconstruction. However, these SC systems may be suboptimal for downstream intelligent tasks. Moreover, SC systems without pixel-level video reconstruction present advantages by achieving higher bandwidth efficiency and real-time performance of various intelligent tasks. The difficulty in such system design lies in the extraction of task-related compact semantic representations and their accurate delivery over noisy channels. In this paper, we propose an end-to-end SC system, named VideoQA-SC for video question answering (VideoQA) tasks. Our goal is to accomplish VideoQA tasks directly based on video semantics over noisy or fading wireless channels, bypassing the need for video reconstruction at the receiver. To this end, we develop a spatiotemporal semantic encoder for effective video semantic extraction, and a learning-based bandwidth-adaptive deep joint source-channel coding (DJSCC) scheme for efficient and robust video semantic transmission. Experiments demonstrate that VideoQA-SC outperforms traditional and advanced DJSCC-based SC systems that rely on video reconstruction at the receiver under a wide range of channel conditions and bandwidth constraints. In particular, when the signal-to-noise ratio is low, VideoQA-SC can improve the answer accuracy by 5.17% while saving almost 99.5\% of the bandwidth at the same time, compared with the advanced DJSCC-based SC system. Our results show the great potential of SC system design for video applications.

cs.CV↗

arXiv2025

Crystal Chute Moves on Pipe Dreams

Schubert polynomials represent a basis for the cohomology of the complete flag variety and thus play a central role in geometry and combinatorics. In this context, Schubert polynomials are generating functions over various combinatorial objects, such as rc-graphs or reduced pipe dreams. By restricting Bergeron and Billey's chute moves on rc-graphs, we define a Demazure crystal structure on the monomials of a Schubert polynomial. As a consequence, we provide a method for decomposing Schubert polynomials as sums of key polynomials, complementing related work of Assaf and Schilling via reduced factorizations with cutoff, as well as Lenart's coplactic operators on biwords.

math.CO↗

arXiv2025

3D Printing of Near-Ambient Responsive Liquid Crystal Elastomers with Enhanced Nematic Order and Pluralized Transformation

Liquid Crystal Elastomers with near-ambient temperature-responsiveness (NAT-LCEs) have been extensively studied for building bio-compatible, low-power consumption devices and robotics. However, conventional manufacturing methods face limitations in programmability (e.g., molding) or low nematic order (e.g., DIW printing). Here, a hybrid cooling strategy is proposed for programmable 3D printing of NAT-LCEs with enhanced nematic order, intricate shape forming, and morphing capability. By integrating a low-temperature nozzle and a cooling platform into a 3D printer, the resulting temperature field synergistically facilitates mesogen alignment during extrusion and disruption-free UV cross-linking. This method achieves a nematic order 3000% higher than NAT-LCEs fabricated using traditional room temperature 3D printing. Enabled by shifting of transition temperature during hybrid cooling printing, printed sheets spontaneously turn into 3D structures after release from the platform, exhibiting bidirectional deformation with heating and cooling. By adjusting the nozzle and plate temperatures, NAT-LCEs with graded properties can be fabricated for intricate shape morphing. A wristband system with enhanced heart rate monitoring is also developed based on 3D-printed NAT-LCE. Our method may open new possibilities for soft robotics, biomedical devices, and wearable electronics.

cond-mat.soft↗

arXiv2024

CPath-Omni: A Unified Multimodal Foundation Model for Patch and Whole Slide Image Analysis in Computational Pathology

The emergence of large multimodal models (LMMs) has brought significant advancements to pathology. Previous research has primarily focused on separately training patch-level and whole-slide image (WSI)-level models, limiting the integration of learned knowledge across patches and WSIs, and resulting in redundant models. In this work, we introduce CPath-Omni, the first 15-billion-parameter LMM designed to unify both patch and WSI level image analysis, consolidating a variety of tasks at both levels, including classification, visual question answering, captioning, and visual referring prompting. Extensive experiments demonstrate that CPath-Omni achieves state-of-the-art (SOTA) performance across seven diverse tasks on 39 out of 42 datasets, outperforming or matching task-specific models trained for individual tasks. Additionally, we develop a specialized pathology CLIP-based visual processor for CPath-Omni, CPath-CLIP, which, for the first time, integrates different vision models and incorporates a large language model as a text encoder to build a more powerful CLIP model, which achieves SOTA performance on nine zero-shot and four few-shot datasets. Our findings highlight CPath-Omni's ability to unify diverse pathology tasks, demonstrating its potential to streamline and advance the field of foundation model in pathology.

cs.CV↗

arXiv2024

DiffCP: Ultra-Low Bit Collaborative Perception via Diffusion Model

Collaborative perception (CP) is emerging as a promising solution to the inherent limitations of stand-alone intelligence. However, current wireless communication systems are unable to support feature-level and raw-level collaborative algorithms due to their enormous bandwidth demands. In this paper, we propose DiffCP, a novel CP paradigm that utilizes a specialized diffusion model to efficiently compress the sensing information of collaborators. By incorporating both geometric and semantic conditions into the generative model, DiffCP enables feature-level collaboration with an ultra-low communication cost, advancing the practical implementation of CP systems. This paradigm can be seamlessly integrated into existing CP algorithms to enhance a wide range of downstream tasks. Through extensive experimentation, we investigate the trade-offs between communication, computation, and performance. Numerical results demonstrate that DiffCP can significantly reduce communication costs by 14.5-fold while maintaining the same performance as the state-of-the-art algorithm.

cs.CV↗

arXiv2024

IDAT: A Multi-Modal Dataset and Toolkit for Building and Evaluating Interactive Task-Solving Agents

Seamless interaction between AI agents and humans using natural language remains a key goal in AI research. This paper addresses the challenges of developing interactive agents capable of understanding and executing grounded natural language instructions through the IGLU competition at NeurIPS. Despite advancements, challenges such as a scarcity of appropriate datasets and the need for effective evaluation platforms persist. We introduce a scalable data collection tool for gathering interactive grounded language instructions within a Minecraft-like environment, resulting in a Multi-Modal dataset with around 9,000 utterances and over 1,000 clarification questions. Additionally, we present a Human-in-the-Loop interactive evaluation platform for qualitative analysis and comparison of agent performance through multi-turn communication with human annotators. We offer to the community these assets referred to as IDAT (IGLU Dataset And Toolkit) which aim to advance the development of intelligent, interactive AI agents and provide essential resources for further research.

cs.AI↗

arXiv2024

Attention-Challenging Multiple Instance Learning for Whole Slide Image Classification

In the application of Multiple Instance Learning (MIL) methods for Whole Slide Image (WSI) classification, attention mechanisms often focus on a subset of discriminative instances, which are closely linked to overfitting. To mitigate overfitting, we present Attention-Challenging MIL (ACMIL). ACMIL combines two techniques based on separate analyses for attention value concentration. Firstly, UMAP of instance features reveals various patterns among discriminative instances, with existing attention mechanisms capturing only some of them. To remedy this, we introduce Multiple Branch Attention (MBA) to capture more discriminative instances using multiple attention branches. Secondly, the examination of the cumulative value of Top-K attention scores indicates that a tiny number of instances dominate the majority of attention. In response, we present Stochastic Top-K Instance Masking (STKIM), which masks out a portion of instances with Top-K attention values and allocates their attention values to the remaining instances. The extensive experimental results on three WSI datasets with two pre-trained backbones reveal that our ACMIL outperforms state-of-the-art methods. Additionally, through heatmap visualization and UMAP visualization, this paper extensively illustrates ACMIL's effectiveness in suppressing attention value concentration and overcoming the overfitting challenge. The source code is available at \url{https://github.com/dazhangyu123/ACMIL}.

cs.CV↗

arXiv2024

C-MASS: Combinatorial Mobility-Aware Sensor Scheduling for Collaborative Perception with Second-Order Topology Approximation

Collaborative Perception (CP) has been a promising solution to address occlusions in the traffic environment by sharing sensor data among collaborative vehicles (CoV) via vehicle-to-everything (V2X) network. With limited wireless bandwidth, CP necessitates task-oriented and receiver-aware sensor scheduling to prioritize important and complementary sensor data. However, due to vehicular mobility, it is challenging and costly to obtain the up-to-date perception topology, i.e., whether a combination of CoVs can jointly detect an object. In this paper, we propose a combinatorial mobility-aware sensor scheduling (C-MASS) framework for CP with minimal communication overhead. Specifically, detections are replayed with sensor data from individual CoVs and pairs of CoVs to maintain an empirical perception topology up to the second order, which approximately represents the complete perception topology. A hybrid greedy algorithm is then proposed to solve a variant of the budgeted maximum coverage problem with a worst-case performance guarantee. The C-MASS scheduling algorithm adapts the greedy algorithm by incorporating the topological uncertainty and the unexplored time of CoVs to balance exploration and exploitation, addressing the mobility challenge. Extensive numerical experiments demonstrate the near-optimality of the proposed C-MASS framework in both edge-assisted and distributed CP configurations. The weighted recall improvements over object-level CP are 5.8% and 4.2%, respectively. Compared to distance-based and area-based greedy heuristics, the gaps to the offline optimal solutions are reduced by up to 75% and 71%, respectively.

cs.RO↗