arXiv subjects

Siwen Wang

Publications and source records attributed to Siwen Wang.

At least 19 recordsLinked to original sources

arXiv2026

ARTEMIS: Agent-guided Reliability-aware Temporal Mask Evolution for Imperfectly Supervised Video Polyp Segmentation

Imperfectly supervised video polyp segmentation (VPS) aims to learn dense, temporally consistent masks from inexpensive supervision, including weak annotations (points, scribbles) and semi-supervision with few densely labeled frames. This setting is clinically valuable but challenging due to weak contrast, ambiguous boundaries, motion blur, and specular highlights, compounded by sparse pixel-level guidance. While SAM2 can generate dense masks from sparse inputs, direct pseudo-labeling often yields geometry-degraded masks with boundary leakage, underutilizes temporal consistency, and ignores reliability. To address these issues, we propose ARTEMIS, a unified framework for imperfectly supervised VPS driven by agent-guided reliability-aware temporal mask evolution. ARTEMIS initializes coarse masks from available supervision: SAM2 converts points/scribbles, while dense labels serve as reliable anchors. A debate-and-judge vision-language agent selects reliable temporal anchors under weak supervision, which are propagated bidirectionally with SAM2 to refine unreliable or unlabeled frames. Finally, ARTEMIS trains the segmenter using temporal reliability-aware robust learning, incorporating reliability-guided reference selection, a Reference Prototype Transport Module, and reliability-aware robust loss. These components assess mask reliability, evolve anchors over time, transport target identity across frames, and down-weight noisy supervision instead of discarding difficult samples. Experiments on SUN-SEG and CVC-ClinicDB-612 under scribble, point, and limited-label settings demonstrate that ARTEMIS achieves state-of-the-art performance. Code will be released at https://github.com/wangtong627/ARTEMIS.

cs.CV↗

arXiv2026

Comparing Human Gaze and Vision-Language Model Attention in Safety-Relevant Environments

Human visual attention plays an important role in how people perceive and respond to environments containing potential risks. This study investigates whether large vision-language models can identify the same regions of a scene that attract human attention in safety-relevant environments. Eye-tracking data were collected from ten participants viewing 33 scene images representing environments with varying levels of potential risk using Pupil Invisible wearable glasses. Gaze coordinates were mapped onto stimulus images to generate population-averaged human gaze heatmaps. In parallel, GPT-4o was prompted through the OpenAI Vision Application Programming Interface (API) to generate spatial predictions of visual attention, which were converted into saliency maps for comparison with human gaze patterns. Spatial alignment between human gaze heatmaps and model-generated saliency maps was evaluated using four complementary metrics: Pearson correlation (r = 0.515 +- 0.117), Normalised Scanpath Saliency (NSS = 0.988 +- 0.323), Kullback-Leibler divergence (KL = 1.766 +- 0.844), and Area Under the Receiver Operating Characteristic Curve using the Judd formulation (AUC-Judd = 0.806 +- 0.076). A cross-model comparison with Gemini Pro, Gemini Flash, and Claude showed that all models exceeded the AUC-Judd chance baseline of 0.5 and achieved positive NSS scores. Gemini Pro demonstrated the strongest spatial localisation according to three of the four metrics, whereas GPT-4o produced the closest distributional match to human attention as measured by KL divergence. These findings suggest that large vision-language models can identify regions that broadly correspond to where humans direct visual attention in safety-relevant scenes without requiring eye-tracking training data. The results highlight the potential of vision-language models as a scalable tool for approximating human attentional patterns.

cs.CV↗

arXiv2026

Boundary Stabilization for the Rayleigh Beam System under Event-triggered Controls

In this paper, we propose two event-triggered control laws incorporating an eventtriggering mechanism to tackle the boundary stabilization for the Rayleigh beam system. Under this event-triggered controls, a sufficient condition for parameter determination is constructed to guarantee the exponential stability of the closed-loop system by using the integral multiplier technique and energy perturbation method, wherein the desired exponential decay rate can be precisely determined. Numerical examples are presented to demonstrate the efficacy of the event-triggered control methodology.

math.OC↗

arXiv2026

CMSA-Net: Causal Multi-scale Aggregation with Adaptive Multi-source Reference for Video Polyp Segmentation

Video polyp segmentation (VPS) is an important task in computer-aided colonoscopy, as it helps doctors accurately locate and track polyps during examinations. However, VPS remains challenging because polyps often look similar to surrounding mucosa, leading to weak semantic discrimination. In addition, large changes in polyp position and scale across video frames make stable and accurate segmentation difficult. To address these challenges, we propose a robust VPS framework named CMSA-Net. The proposed network introduces a Causal Multi-scale Aggregation (CMA) module to effectively gather semantic information from multiple historical frames at different scales. By using causal attention, CMA ensures that temporal feature propagation follows strict time order, which helps reduce noise and improve feature reliability. Furthermore, we design a Dynamic Multi-source Reference (DMR) strategy that adaptively selects informative and reliable reference frames based on semantic separability and prediction confidence. This strategy provides strong multi-frame guidance while keeping the model efficient for real-time inference. Extensive experiments on the SUN-SEG dataset demonstrate that CMSA-Net achieves state-of-the-art performance, offering a favorable balance between segmentation accuracy and real-time clinical applicability.

cs.CV↗

arXiv2025

DevPiolt: Operation Recommendation for IoT Devices at Xiaomi Home

Operation recommendation for IoT devices refers to generating personalized device operations for users based on their context, such as historical operations, environment information, and device status. This task is crucial for enhancing user satisfaction and corporate profits. Existing recommendation models struggle with complex operation logic, diverse user preferences, and sensitive to suboptimal suggestions, limiting their applicability to IoT device operations. To address these issues, we propose DevPiolt, a LLM-based recommendation model for IoT device operations. Specifically, we first equip the LLM with fundamental domain knowledge of IoT operations via continual pre-training and multi-task fine-tuning. Then, we employ direct preference optimization to align the fine-tuned LLM with specific user preferences. Finally, we design a confidence-based exposure control mechanism to avoid negative user experiences from low-quality recommendations. Extensive experiments show that DevPiolt significantly outperforms baselines on all datasets, with an average improvement of 69.5% across all metrics. DevPiolt has been practically deployed in Xiaomi Home app for one quarter, providing daily operation recommendations to 255,000 users. Online experiment results indicate a 21.6% increase in unique visitor device coverage and a 29.1% increase in page view acceptance rates.

cs.AI↗

arXiv2025

Structural Mutation Based Differential Testing for FPGA Logic Synthesis Compilers

Field Programmable Gate Arrays (FPGAs) play a crucial role in Electronic Design Automation (EDA) applications, which have been widely used in safety-critical environments, including aerospace, chip manufacturing, and medical devices. A critical step in FPGA development is logic synthesis, which enables developers to translate their software designs into hardware net lists, which facilitates the physical implementation of the chip, detailed timing and power analysis, gate-level simulation, test vector generation, and optimization and consistency checking. However, bugs or incorrect implementations in FPGA logic synthesis compilers may lead to unexpected behaviors in target wapplications, posing security risks. Therefore, it is crucial to eliminate such bugs in FPGA logic synthesis compilers. The effectiveness of existing works is still limited by its simple, blind mutation strategy. To address this challenge, we propose a guided mutation strategy based on Bayesian optimization called LSC-Fuzz to detect bugs in FPGA logic synthesis compilers. Specifically, LSC-Fuzz consists of three components: the test-program generation component, the Bayesian diversity selection component, and the equivalent check component. By performing test-program generation and Bayesian diversity selection, LSC-Fuzz generates diverse and complex HDL code, thoroughly testing the FPGA logic synthesis compilers using equivalent check to detect bugs. Through three months, LSC-Fuzz has found 16 bugs, 12 of these has been confirmed by official technical support.

cs.SE↗

arXiv2025

Compiler Bugs Detection in Logic Synthesis Tools via Linear Upper Confidence Bound

Field-Programmable Gate Arrays (FPGAs) play an indispensable role in Electronic Design Automation (EDA), translating Register-Transfer Level (RTL) designs into gate-level netlists. The correctness and reliability of FPGA logic synthesis tools are critically important, as unnoticed bugs in these tools may infect the final hardware implementations. However, recent approaches often rely heavily on random selection strategies, limiting the structural diversity of the generated HDL test cases and resulting in inadequate exploration of the tool's feature space. To address this limitation, we propose Lin-Hunter, a novel testing framework designed to systematically enhance the diversity of HDL test cases and the efficiency of FPGA logic synthesis tool validation. Specifically, Lin-Hunter introduces a principled set of metamorphic transformation rules to generate functionally equivalent yet structurally diverse HDL test case variants, effectively addressing the limited diversity of existing test inputs. To further enhance bug discovery efficiency, Lin-Hunter integrates an adaptive strategy selection mechanism based on the Linear Upper Confidence Bound (LinUCB) method. This method leverages feedback from synthesis logs of previously executed test cases to dynamically prioritize transformation strategies that have empirically demonstrated a higher likelihood of triggering synthesis bugs. Comprehensive experiments conducted over a three-month period demonstrate the practical effectiveness of Lin-Hunter. Our method has discovered 18 unique bugs, including 10 previously unreported defects, which have been confirmed by official developers. Moreover, our method outperforms state-of-the-art testing methods in both test-case diversity and bug-discovery efficiency.

cs.SE↗

arXiv2025

Modeling Relational Logic Circuits for And-Inverter Graph Convolutional Network

The automation of logic circuit design enhances chip performance, energy efficiency, and reliability, and is widely applied in the field of Electronic Design Automation (EDA).And-Inverter Graphs (AIGs) efficiently represent, optimize, and verify the functional characteristics of digital circuits, enhancing the efficiency of EDA development.Due to the complex structure and large scale of nodes in real-world AIGs, accurate modeling is challenging, leading to existing work lacking the ability to jointly model functional and structural characteristics, as well as insufficient dynamic information propagation capability.To address the aforementioned challenges, we propose AIGer.Specifically, AIGer consists of two components: 1) Node logic feature initialization embedding component and 2) AIGs feature learning network component.The node logic feature initialization embedding component projects logic nodes, such as AND and NOT, into independent semantic spaces, to enable effective node embedding for subsequent processing.Building upon this, the AIGs feature learning network component employs a heterogeneous graph convolutional network, designing dynamic relationship weight matrices and differentiated information aggregation approaches to better represent the original structure and information of AIGs.The combination of these two components enhances AIGer's ability to jointly model functional and structural characteristics and improves its message passing capability. Experimental results indicate that AIGer outperforms the current best models in the Signal Probability Prediction (SSP) task, improving MAE and MSE by 18.95\% and 44.44\%, respectively. In the Truth Table Distance Prediction (TTDP) task, AIGer achieves improvements of 33.57\% and 14.79\% in MAE and MSE, respectively, compared to the best-performing models.

cs.AI↗

arXiv2025

Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunities

AI agents have experienced a paradigm shift, from early dominance by reinforcement learning (RL) to the rise of agents powered by large language models (LLMs), and now further advancing towards a synergistic fusion of RL and LLM capabilities. This progression has endowed AI agents with increasingly strong abilities. Despite these advances, to accomplish complex real-world tasks, agents are required to plan and execute effectively, maintain reliable memory, and coordinate smoothly with other agents. Achieving these capabilities involves contending with ever-present intricate information, operations, and interactions. In light of this challenge, data structurization can play a promising role by transforming intricate and disorganized data into well-structured forms that agents can more effectively understand and process. In this context, graphs, with their natural advantage in organizing, managing, and harnessing intricate data relationships, present a powerful data paradigm for structurization to support the capabilities demanded by advanced AI agents. To this end, this survey presents a first systematic review of how graphs can empower AI agents. Specifically, we explore the integration of graph techniques with core agent functionalities, highlight notable applications, and identify prospective avenues for future research. By comprehensively surveying this burgeoning intersection, we hope to inspire the development of next-generation AI agents equipped to tackle increasingly sophisticated challenges with graphs. Related resources are collected and continuously updated for the community in the Github link.

cs.AI↗

arXiv2025

PokéAI: A Goal-Generating, Battle-Optimizing Multi-agent System for Pokemon Red

We introduce PokéAI, the first text-based, multi-agent large language model (LLM) framework designed to autonomously play and progress through Pokémon Red. Our system consists of three specialized agents-Planning, Execution, and Critique-each with its own memory bank, role, and skill set. The Planning Agent functions as the central brain, generating tasks to progress through the game. These tasks are then delegated to the Execution Agent, which carries them out within the game environment. Upon task completion, the Critique Agent evaluates the outcome to determine whether the objective was successfully achieved. Once verification is complete, control returns to the Planning Agent, forming a closed-loop decision-making system. As a preliminary step, we developed a battle module within the Execution Agent. Our results show that the battle AI achieves an average win rate of 80.8% across 50 wild encounters, only 6% lower than the performance of an experienced human player. Furthermore, we find that a model's battle performance correlates strongly with its LLM Arena score on language-related tasks, indicating a meaningful link between linguistic ability and strategic reasoning. Finally, our analysis of gameplay logs reveals that each LLM exhibits a unique playstyle, suggesting that individual models develop distinct strategic behaviors.

cs.AI↗

arXiv2025

From Theory to Application: Fine-Tuning Large EEG Model with Real-World Stress Data

Recent advancements in Large Language Models have inspired the development of foundation models across various domains. In this study, we evaluate the efficacy of Large EEG Models (LEMs) by fine-tuning LaBraM, a state-of-the-art foundation EEG model, on a real-world stress classification dataset collected in a graduate classroom. Unlike previous studies that primarily evaluate LEMs using data from controlled clinical settings, our work assesses their applicability to real-world environments. We train a binary classifier that distinguishes between normal and elevated stress states using resting-state EEG data recorded from 18 graduate students during a class session. The best-performing fine-tuned model achieves a balanced accuracy of 90.47% with a 5-second window, significantly outperforming traditional stress classifiers in both accuracy and inference efficiency. We further evaluate the robustness of the fine-tuned LEM under random data shuffling and reduced channel counts. These results demonstrate the capability of LEMs to effectively process real-world EEG data and highlight their potential to revolutionize brain-computer interface applications by shifting the focus from model-centric to data-centric design.

cs.LG↗

arXiv2025

Autoregressive Sequence Modeling for 3D Medical Image Representation

Three-dimensional (3D) medical images, such as Computed Tomography (CT) and Magnetic Resonance Imaging (MRI), are essential for clinical applications. However, the need for diverse and comprehensive representations is particularly pronounced when considering the variability across different organs, diagnostic tasks, and imaging modalities. How to effectively interpret the intricate contextual information and extract meaningful insights from these images remains an open challenge to the community. While current self-supervised learning methods have shown potential, they often consider an image as a whole thereby overlooking the extensive, complex relationships among local regions from one or multiple images. In this work, we introduce a pioneering method for learning 3D medical image representations through an autoregressive pre-training framework. Our approach sequences various 3D medical images based on spatial, contrast, and semantic correlations, treating them as interconnected visual tokens within a token sequence. By employing an autoregressive sequence modeling task, we predict the next visual token in the sequence, which allows our model to deeply understand and integrate the contextual information inherent in 3D medical images. Additionally, we implement a random startup strategy to avoid overestimating token relationships and to enhance the robustness of learning. The effectiveness of our approach is demonstrated by the superior performance over others on nine downstream tasks in public datasets.

cs.CV↗

arXiv2024

Enhanced MRI Representation via Cross-series Masking

Magnetic resonance imaging (MRI) is indispensable for diagnosing and planning treatment in various medical conditions due to its ability to produce multi-series images that reveal different tissue characteristics. However, integrating these diverse series to form a coherent analysis presents significant challenges, such as differing spatial resolutions and contrast patterns meanwhile requiring extensive annotated data, which is scarce in clinical practice. Due to these issues, we introduce a novel Cross-Series Masking (CSM) Strategy for effectively learning MRI representation in a self-supervised manner. Specifically, CSM commences by randomly sampling a subset of regions and series, which are then strategically masked. In the training process, the cross-series representation is learned by utilizing the unmasked data to reconstruct the masked portions. This process not only integrates information across different series but also facilitates the ability to model both intra-series and inter-series correlations and complementarities. With the learned representation, the downstream tasks like segmentation and classification are also enhanced. Taking brain tissue segmentation, breast tumor benign/malignant classification, and prostate cancer diagnosis as examples, our method achieves state-of-the-art performance on both public and in-house datasets.

eess.IV↗

arXiv2024

Neural Signal Operated Intelligent Robot: Human-guided Robot Maze Navigation through SSVEP

Brain-computer Interface (BCI) applications based on steady-state visual evoked potentials (SSVEP) have the advantages of being fast, accurate and mobile. SSVEP is the EEG response evoked by visual stimuli that are presented at a specific frequency, which results in an increase in the EEG at that same frequency. In this paper, we proposed a novel human-guided maze solving robot navigation system based on SSVEP. By integrating human's intelligence which sees the entirety of the maze, maze solving time could be significantly reduced. Our methods involve training an offline SSVEP classification model, implementing the robot self-navigation algorithm, and finally deploy the model online for real-time robot operation. Our results demonstrated such system to be feasible, and it has the potential to impact the life of many elderly people by helping them carrying out simple daily tasks at home with just the look of their eyes.

cs.HC↗

arXiv2024

Cross-Dimensional Medical Self-Supervised Representation Learning Based on a Pseudo-3D Transformation

Medical image analysis suffers from a shortage of data, whether annotated or not. This becomes even more pronounced when it comes to 3D medical images. Self-Supervised Learning (SSL) can partially ease this situation by using unlabeled data. However, most existing SSL methods can only make use of data in a single dimensionality (e.g. 2D or 3D), and are incapable of enlarging the training dataset by using data with differing dimensionalities jointly. In this paper, we propose a new cross-dimensional SSL framework based on a pseudo-3D transformation (CDSSL-P3D), that can leverage both 2D and 3D data for joint pre-training. Specifically, we introduce an image transformation based on the im2col algorithm, which converts 2D images into a format consistent with 3D data. This transformation enables seamless integration of 2D and 3D data, and facilitates cross-dimensional self-supervised learning for 3D medical image analysis. We run extensive experiments on 13 downstream tasks, including 2D and 3D classification and segmentation. The results indicate that our CDSSL-P3D achieves superior performance, outperforming other advanced SSL methods.

cs.CV↗

arXiv2024

Online Mental Stress Detection Using Frontal-channel EEG Recordings in a Classroom Scenario

Objective: To investigate the effects of different approaches to EEG preprocessing, channel montage selection, and model architecture on the performance of an online-capable stress detection algorithm in a classroom scenario. Methods: This analysis used EEG data from a longitudinal stress and fatigue study conducted among university students. Their self-reported stress ratings during each class session were the basis for classifying EEG recordings into either normal or elevated stress states. We used a data-processing pipeline that combined Artifact Subspace Reconstruction (ASR)and an Independent Component Analysis (ICA)-based method to achieve online artifact removal. We compared the performance of a Linear Discriminant Analysis (LDA) and a 4-layer neural network as classifiers. We opted for accuracy, balanced accuracy, and F1 score as the metrics for assessing performance. We examined the impact of varying numbers of input channels using different channel montages. Additionally, we explored different window lengths and step sizes during online evaluation. Results: Our online artifact removal method achieved performance comparable to the offline ICA method in both offline and online evaluations. A balanced accuracy of 77% and 78% in an imbalanced binary classification were observed when using the 11-frontal-channel LDA model with the proposed artifact removal method. Moreover, the model performance remained intact when changing the channel montage from 30 full-scalp channels to just 11 frontal channels. During the online evaluation, we achieved the highest balanced accuracy (78%) with a window length of 20 seconds and a step size of 1 second. Significance: This study comprehensively investigates the deployment of stress detection in real-world scenarios. The findings of this study provide insight into the development of daily mental stress monitoring.

q-bio.NC↗

arXiv2024

Streamlining Social Media Information Retrieval for COVID-19 Research with Deep Learning

Objective: Social media-based public health research is crucial for epidemic surveillance, but most studies identify relevant corpora with keyword-matching. This study develops a system to streamline the process of curating colloquial medical dictionaries. We demonstrate the pipeline by curating a UMLS-colloquial symptom dictionary from COVID-19-related tweets as proof of concept. Methods: COVID-19-related tweets from February 1, 2020, to April 30, 2022 were used. The pipeline includes three modules: a named entity recognition module to detect symptoms in tweets; an entity normalization module to aggregate detected entities; and a mapping module that iteratively maps entities to Unified Medical Language System concepts. A random 500 entity sample were drawn from the final dictionary for accuracy validation. Additionally, we conducted a symptom frequency distribution analysis to compare our dictionary to a pre-defined lexicon from previous research. Results: We identified 498,480 unique symptom entity expressions from the tweets. Pre-processing reduces the number to 18,226. The final dictionary contains 38,175 unique expressions of symptoms that can be mapped to 966 UMLS concepts (accuracy = 95%). Symptom distribution analysis found that our dictionary detects more symptoms and is effective at identifying psychiatric disorders like anxiety and depression, often missed by pre-defined lexicons. Conclusions: This study advances public health research by implementing a novel, systematic pipeline for curating symptom lexicons from social media data. The final lexicon's high accuracy, validated by medical professionals, underscores the potential of this methodology to reliably interpret and categorize vast amounts of unstructured social media data into actionable medical insights across diverse linguistic and regional landscapes.

cs.CL↗

arXiv2021

Infusing Theory into Deep Learning for Interpretable Reactivity Prediction

Despite recent advances of data acquisition and algorithms development, machine learning (ML) faces tremendous challenges to being adopted in practical catalyst design, largely due to its limited generalizability and poor explainability. Here, we develop a theory-infused neural network (TinNet) approach that integrates deep learning algorithms with the well-established $d$-band theory of chemisorption for reactivity prediction of transition-metal surfaces. With simple adsorbates (e.g., *OH, *O, and *N) at active site ensembles as representative descriptor species, we demonstrate that the TinNet is on par with purely data-driven ML methods in prediction performance, while being inherently interpretable. Incorporation of scientific knowledge of physical interactions into learning from data sheds further light on the nature of chemical bonding and opens up new avenues for ML discovery of novel motifs with desired catalytic properties.

physics.chem-ph↗