arXiv subjects

Shen Wang

Publications and source records attributed to Shen Wang.

At least 55 records · Page 3Linked to original sources

arXiv2025

A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges

Mathematical reasoning, a core aspect of human cognition, is vital across many domains, from educational problem-solving to scientific advancements. As artificial general intelligence (AGI) progresses, integrating large language models (LLMs) with mathematical reasoning tasks is becoming increasingly significant. This survey provides the first comprehensive analysis of mathematical reasoning in the era of multimodal large language models (MLLMs). We review over 200 studies published since 2021, and examine the state-of-the-art developments in Math-LLMs, with a focus on multimodal settings. We categorize the field into three dimensions: benchmarks, methodologies, and challenges. In particular, we explore multimodal mathematical reasoning pipeline, as well as the role of (M)LLMs and the associated methodologies. Finally, we identify five major challenges hindering the realization of AGI in this domain, offering insights into the future direction for enhancing multimodal reasoning capabilities. This survey serves as a critical resource for the research community in advancing the capabilities of LLMs to tackle complex multimodal reasoning tasks.

cs.CL↗

arXiv2025

MathAgent: Leveraging a Mixture-of-Math-Agent Framework for Real-World Multimodal Mathematical Error Detection

Mathematical error detection in educational settings presents a significant challenge for Multimodal Large Language Models (MLLMs), requiring a sophisticated understanding of both visual and textual mathematical content along with complex reasoning capabilities. Though effective in mathematical problem-solving, MLLMs often struggle with the nuanced task of identifying and categorizing student errors in multimodal mathematical contexts. Therefore, we introduce MathAgent, a novel Mixture-of-Math-Agent framework designed specifically to address these challenges. Our approach decomposes error detection into three phases, each handled by a specialized agent: an image-text consistency validator, a visual semantic interpreter, and an integrative error analyzer. This architecture enables more accurate processing of mathematical content by explicitly modeling relationships between multimodal problems and student solution steps. We evaluate MathAgent on real-world educational data, demonstrating approximately 5% higher accuracy in error step identification and 3% improvement in error categorization compared to baseline models. Besides, MathAgent has been successfully deployed in an educational platform that has served over one million K-12 students, achieving nearly 90% student satisfaction while generating significant cost savings by reducing manual error detection.

cs.CL↗

arXiv2025

Output regulation for a reaction-diffusion system with input delay and unknown frequency

This study solves the output regulation problem for a reaction-diffusion system confronting concurrent input delay and fully unidentified disturbances (encompassing both unknown frequencies and amplitudes) across all channels. The principal innovation emerges from a novel adaptive control architecture that synergizes the modal decomposition technique with a dual-observer mechanism, enabling real-time concurrent estimation of unmeasurable system states and disturbances through a state observer and an adaptive disturbance estimator. Unlike existing approaches limited to either delay compensation or partial disturbance rejection, our methodology overcomes the technical barrier of coordinating these two requirements through a rigorously constructed tracking-error-based controller, achieving exponential convergence of system output to reference signals. Numerical simulations are presented to validate the effectiveness of the proposed output feedback control strategy.

math.OC↗

arXiv2025

Output regulation for an unstable wave equation with output delay and one measurement only

This paper addresses the output regulation problem for a one-dimensional unstable wave equation subject to output delay and all-channel disturbances with unknown frequencies and amplitudes. First, this problem is transformed into a stabilization problem for an unstable wave equation with output delay and disturbances by employing regulator equations. Subsequently, a backstepping-based feedforward regulator is proposed to exponentially stabilize this system. To track the states of the unstable wave equation, the time interval is partitioned into two segments. The observers and predictors are designed at these distinct intervals, respectively. Therein, the observers comprise two components: a state observer proposed via dynamic compensators and an adaptive observer designed by the adaptive internal model method. Finally, a novel error-based feedback controller is derived using a single measurement, ensuring exponential convergence of the tracking error to zero. This work establishes the pioneering solution to the output regulation problem for distributed parameter systems (DPS) with output delay. Numerical simulations are provided to illustrate the results.

math.OC↗

arXiv2025

LLM-Alignment Live-Streaming Recommendation

In recent years, integrated short-video and live-streaming platforms have gained massive global adoption, offering dynamic content creation and consumption. Unlike pre-recorded short videos, live-streaming enables real-time interaction between authors and users, fostering deeper engagement. However, this dynamic nature introduces a critical challenge for recommendation systems (RecSys): the same live-streaming vastly different experiences depending on when a user watching. To optimize recommendations, a RecSys must accurately interpret the real-time semantics of live content and align them with user preferences.

cs.IR↗

arXiv2025

Linear Attention Modeling for Learned Image Compression

Recent years, learned image compression has made tremendous progress to achieve impressive coding efficiency. Its coding gain mainly comes from non-linear neural network-based transform and learnable entropy modeling. However, most studies focus on a strong backbone, and few studies consider a low complexity design. In this paper, we propose LALIC, a linear attention modeling for learned image compression. Specially, we propose to use Bi-RWKV blocks, by utilizing the Spatial Mix and Channel Mix modules to achieve more compact feature extraction, and apply the Conv based Omni-Shift module to adapt to two-dimensional latent representation. Furthermore, we propose a RWKV-based Spatial-Channel ConTeXt model (RWKV-SCCTX), that leverages the Bi-RWKV to modeling the correlation between neighboring features effectively. To our knowledge, our work is the first work to utilize efficient Bi-RWKV models with linear attention for learned image compression. Experimental results demonstrate that our method achieves competitive RD performances by outperforming VTM-9.1 by -15.26%, -15.41%, -17.63% in BD-rate on Kodak, CLIC and Tecnick datasets. The code is available at https://github.com/sjtu-medialab/RwkvCompress .

cs.CV↗

arXiv2025

Enhancing Vehicle Platooning Safety via Control Node Placement and Sizing under State and Input Bounds

Vehicle platooning with Cooperative Adaptive Cruise Control improves traffic efficiency, reduces energy consumption, and enhances safety but remains vulnerable to cyber-attacks that disrupt communication and cause unsafe actions. To address these risks, this paper investigates control node placement and input bound optimization to balance safety and defense efficiency under various conditions. We propose a two-stage actuator placement and actuator saturation approach, which focuses on identifying key actuators that maximize the system's controllability while operating under state and input constraints. By strategically placing and limiting the input bounds of critical actuators, we ensure that vehicles maintain safe distances even under attack. Simulation results show that our method effectively mitigates the impact of attacks while preserving defense efficiency, offering a robust solution to vehicle platooning safety challenges.

eess.SY↗

arXiv2025

Leveraging Sequence Purification for Accurate Prediction of Multiple Conformational States with AlphaFold2

AlphaFold2 (AF2) has transformed protein structure prediction by harnessing co-evolutionary constraints embedded in multiple sequence alignments (MSAs). MSAs not only encode static structural information, but also hold critical details about protein dynamics, which underpin biological functions. However, these subtle co-evolutionary signatures, which dictate conformational state preferences, are often obscured by noise within MSA data and thus remain challenging to decipher. Here, we introduce AF-ClaSeq, a systematic framework that isolates these co-evolutionary signals through sequence purification and iterative enrichment. By extracting sequence subsets that preferentially encode distinct structural states, AF-ClaSeq enables high-confidence predictions of alternative conformations. Our findings reveal that the successful sampling of alternative states depends not on MSA depth but on sequence purity. Intriguingly, purified sequences encoding specific structural states are distributed across phylogenetic clades and superfamilies, rather than confined to specific lineages. Expanding upon AF2's transformative capabilities, AF-ClaSeq provides a powerful approach for uncovering hidden structural plasticity, advancing allosteric protein and drug design, and facilitating dynamics-based protein function annotation.

q-bio.BM↗

arXiv2025

MIML: Multiplex Image Machine Learning for High Precision Cell Classification via Mechanical Traits within Microfluidic Systems

Label-free cell classification is advantageous for supplying pristine cells for further use or examination, yet existing techniques frequently fall short in terms of specificity and speed. In this study, we address these limitations through the development of a novel machine learning framework, Multiplex Image Machine Learning (MIML). This architecture uniquely combines label-free cell images with biomechanical property data, harnessing the vast, often underutilized morphological information intrinsic to each cell. By integrating both types of data, our model offers a more holistic understanding of the cellular properties, utilizing morphological information typically discarded in traditional machine learning models. This approach has led to a remarkable 98.3\% accuracy in cell classification, a substantial improvement over models that only consider a single data type. MIML has been proven effective in classifying white blood cells and tumor cells, with potential for broader application due to its inherent flexibility and transfer learning capability. It's particularly effective for cells with similar morphology but distinct biomechanical properties. This innovative approach has significant implications across various fields, from advancing disease diagnostics to understanding cellular behavior.

eess.IV↗

arXiv2025

Corrections Meet Explanations: A Unified Framework for Explainable Grammatical Error Correction

Grammatical Error Correction (GEC) faces a critical challenge concerning explainability, notably when GEC systems are designed for language learners. Existing research predominantly focuses on explaining grammatical errors extracted in advance, thus neglecting the relationship between explanations and corrections. To address this gap, we introduce EXGEC, a unified explainable GEC framework that integrates explanation and correction tasks in a generative manner, advocating that these tasks mutually reinforce each other. Experiments have been conducted on EXPECT, a recent human-labeled dataset for explainable GEC, comprising around 20k samples. Moreover, we detect significant noise within EXPECT, potentially compromising model training and evaluation. Therefore, we introduce an alternative dataset named EXPECT-denoised, ensuring a more objective framework for training and evaluation. Results on various NLP models (BART, T5, and Llama3) show that EXGEC models surpass single-task baselines in both tasks, demonstrating the effectiveness of our approach.

cs.CL↗

arXiv2025

FARM: Frequency-Aware Model for Cross-Domain Live-Streaming Recommendation

Live-streaming services have attracted widespread popularity due to their real-time interactivity and entertainment value. Users can engage with live-streaming authors by participating in live chats, posting likes, or sending virtual gifts to convey their preferences and support. However, the live-streaming services faces serious data-sparsity problem, which can be attributed to the following two points: (1) User's valuable behaviors are usually sparse, e.g., like, comment and gift, which are easily overlooked by the model, making it difficult to describe user's personalized preference. (2) The main exposure content on our platform is short-video, which is 9 times higher than the exposed live-streaming, leading to the inability of live-streaming content to fully model user preference. To this end, we propose a Frequency-Aware Model for Cross-Domain Live-Streaming Recommendation, termed as FARM. Specifically, we first present the intra-domain frequency aware module to enable our model to perceive user's sparse yet valuable behaviors, i.e., high-frequency information, supported by the Discrete Fourier Transform (DFT). To transfer user preference across the short-video and live-streaming domains, we propose a novel preference align before fuse strategy, which consists of two parts: the cross-domain preference align module to align user preference in both domains with contrastive learning, and the cross-domain preference fuse module to further fuse user preference in both domains using a serious of tailor-designed attention mechanisms. Extensive offline experiments and online A/B testing on Kuaishou live-streaming services demonstrate the effectiveness and superiority of FARM. Our FARM has been deployed in online live-streaming services and currently serves hundreds of millions of users on Kuaishou.

cs.IR↗

arXiv2025

Deep Reinforcement Learning for Job Scheduling and Resource Management in Cloud Computing: An Algorithm-Level Review

Cloud computing has revolutionized the provisioning of computing resources, offering scalable, flexible, and on-demand services to meet the diverse requirements of modern applications. At the heart of efficient cloud operations are job scheduling and resource management, which are critical for optimizing system performance and ensuring timely and cost-effective service delivery. However, the dynamic and heterogeneous nature of cloud environments presents significant challenges for these tasks, as workloads and resource availability can fluctuate unpredictably. Traditional approaches, including heuristic and meta-heuristic algorithms, often struggle to adapt to these real-time changes due to their reliance on static models or predefined rules. Deep Reinforcement Learning (DRL) has emerged as a promising solution to these challenges by enabling systems to learn and adapt policies based on continuous observations of the environment, facilitating intelligent and responsive decision-making. This survey provides a comprehensive review of DRL-based algorithms for job scheduling and resource management in cloud computing, analyzing their methodologies, performance metrics, and practical applications. We also highlight emerging trends and future research directions, offering valuable insights into leveraging DRL to advance both job scheduling and resource management in cloud computing.

cs.DC↗

arXiv2024

Guidelines for Correlative Imaging and Analysis of Reactive Lithium Metal Battery Materials

To unlock the full potential of lithium metal batteries, a deep understanding of lithium metal reactivity and its solid electrolyte interphase is essential. Correlative imaging, combining focused ion beam and electron microscopy offers a powerful approach for multi-scale characterization. However, the extreme reactivity of lithium metal and its SEI presents challenges in investigating deposition and stripping mechanisms. In this work, we systematically evaluated the storage stability of lithium metal in glovebox before and after electrochemical deposition. We then assessed different FIB ion sources for their impact on lithium metal lamella preparation for transmission electron microscopy. Furthermore, we examined cryogenic-TEM transfer methods, optimizing for minimal contamination during sample handling. Contrary to prior assumptions, we demonstrate that high resolution imaging of pure lithium metal at room temperature is achievable using inert gas transfer with an electron dose rate exceeding 1000 e/A2/s, without significant detectable damage. In contrast, SEI components, such as Li2CO3 and LiF display much greater sensitivity to electron beams, requiring cryogenic conditions and precise dose control for nano/atomic scale imaging. We quantified electron dose limits for these SEI components to track their structural evolution under irradiation. Based on these findings, we propose a robust protocol for lithium metal sample handling - from storage to atomic-level characterization - minimizing damage and contamination. This work paves the way for more accurate and reproducible studies, accelerating the development of next-generation lithium metal batteries by ensuing the preservation of native material properties during analysis.

cond-mat.mtrl-sci↗

arXiv2024

AsymLLIC: Asymmetric Lightweight Learned Image Compression

Learned image compression (LIC) methods often employ symmetrical encoder and decoder architectures, evitably increasing decoding time. However, practical scenarios demand an asymmetric design, where the decoder requires low complexity to cater to diverse low-end devices, while the encoder can accommodate higher complexity to improve coding performance. In this paper, we propose an asymmetric lightweight learned image compression (AsymLLIC) architecture with a novel training scheme, enabling the gradual substitution of complex decoding modules with simpler ones. Building upon this approach, we conduct a comprehensive comparison of different decoder network structures to strike a better trade-off between complexity and compression performance. Experiment results validate the efficiency of our proposed method, which not only achieves comparable performance to VVC but also offers a lightweight decoder with only 51.47 GMACs computation and 19.65M parameters. Furthermore, this design methodology can be easily applied to any LIC models, enabling the practical deployment of LIC techniques.

eess.IV↗

arXiv2024

AI-Driven Virtual Teacher for Enhanced Educational Efficiency: Leveraging Large Pretrain Models for Autonomous Error Analysis and Correction

Students frequently make mistakes while solving mathematical problems, and traditional error correction methods are both time-consuming and labor-intensive. This paper introduces an innovative \textbf{V}irtual \textbf{A}I \textbf{T}eacher system designed to autonomously analyze and correct student \textbf{E}rrors (VATE). Leveraging advanced large language models (LLMs), the system uses student drafts as a primary source for error analysis, which enhances understanding of the student's learning process. It incorporates sophisticated prompt engineering and maintains an error pool to reduce computational overhead. The AI-driven system also features a real-time dialogue component for efficient student interaction. Our approach demonstrates significant advantages over traditional and machine learning-based error correction methods, including reduced educational costs, high scalability, and superior generalizability. The system has been deployed on the Squirrel AI learning platform for elementary mathematics education, where it achieves 78.3\% accuracy in error analysis and shows a marked improvement in student learning efficiency. Satisfaction surveys indicate a strong positive reception, highlighting the system's potential to transform educational practices.

cs.CV↗

arXiv2024

Surface molecular engineering to enable processing of sulfide solid electrolytes in humid ambient air

Sulfide solid state electrolytes are promising candidates to realize all solid state batteries due to their superior ionic conductivity and excellent ductility. However, their hypersensitivity to moisture requires processing environments that are not compatible with todays lithium ion battery manufacturing infrastructure. Herein, we present a reversible surface modification strategy that enables the processability of sulfide SSEs under humid ambient air. We demonstrate that a long chain alkyl thiol, undecanethiol, is chemically compatible with the electrolyte with negligible impact on its ion conductivity. Importantly, the thiol modification extends the amount of time that the sulfide SSE can be exposed to air with 33 percent relative humidity with limited degradation of its structure while retaining a conductivity of above 1 mS per cm for up to 2 days, a more than 100 fold improvement in protection time over competing approaches. Experimental and computational results reveal that the thiol group anchors to the SSE surface, while the hydrophobic hydrocarbon tail provides protection by repelling water. The modified Li6PS5Cl SSE maintains its function after exposure to ambient humidity when implemented in a Li0.5In LiNi0.8Co0.1Mn0.1O2 ASSB. The proposed protection strategy based on surface molecular interactions represents a major step forward towards cost competitive and energy efficient sulfide SSE manufacturing for ASSB applications.

cond-mat.mtrl-sci↗

arXiv2024

An Image Simulator of Lunar Far-Side Impact Flashes Captured from the Earth-Moon L2 Point

Impact flashes on the moon are caused by high-speed collisions of celestial bodies with the lunar surface. The study of the impacts is critical for exploring the evolutionary history and formation of the Moon, and for quantifying the risk posed by the impacts to future human activity. Although the impacts have been monitored from the Earth by a few projects in past 20 years, the events occurring on the lunar far side have not been explored systematically so far. We here present an end-to-end image simulator dedicated to detecting and monitoring the impacts from space, which is useful for future mission design. The simulator is designed for modularity and developed in the Python environment, which is mainly composed of four components: the flash temporal radiation, the background emission, the telescope and the detector used to collect and measure the radiation. Briefly speaking, with a set of input parameters, the simulator calculates the flash radiation in the context of the spherical droplet model and the background emission from the lunar surface. The resulting images are then generated by the simulator after considering a series observational effects, including the stray light, transmission of the instrument, point spread function and multiple kinds of noise caused by a CCD/CMOS detector. The simulator is validated by comparing the calculation with the observations taken on the ground. The modular design enables the simulator to be improved and enhanced by including more complex physical models in the future, and to be flexible for other future space missions.

astro-ph.IM↗

arXiv2024

A Survey on XAI for 5G and Beyond Security: Technical Aspects, Challenges and Research Directions

With the advent of 5G commercialization, the need for more reliable, faster, and intelligent telecommunication systems is envisaged for the next generation beyond 5G (B5G) radio access technologies. Artificial Intelligence (AI) and Machine Learning (ML) are immensely popular in service layer applications and have been proposed as essential enablers in many aspects of 5G and beyond networks, from IoT devices and edge computing to cloud-based infrastructures. However, existing 5G ML-based security surveys tend to emphasize AI/ML model performance and accuracy more than the models' accountability and trustworthiness. In contrast, this paper explores the potential of Explainable AI (XAI) methods, which would allow stakeholders in 5G and beyond to inspect intelligent black-box systems used to secure next-generation networks. The goal of using XAI in the security domain of 5G and beyond is to allow the decision-making processes of ML-based security systems to be transparent and comprehensible to 5G and beyond stakeholders, making the systems accountable for automated actions. In every facet of the forthcoming B5G era, including B5G technologies such as ORAN, zero-touch network management, and end-to-end slicing, this survey emphasizes the role of XAI in them that the general users would ultimately enjoy. Furthermore, we presented the lessons from recent efforts and future research directions on top of the currently conducted projects involving XAI.

cs.NI↗