arXiv subjects

Qixin Wang

Publications and source records attributed to Qixin Wang.

16 recordsLinked to original sources

arXiv2026

SAFE-Cascade: Cost-Adaptive Vision-Language Routing for Chart Question Answering

Vision-language models (VLMs) are powerful for chart question answering, but invoking a VLM for every query can be unnecessarily expensive when many questions are answerable from OCR text and lightweight language reasoning. We demonstrate SAFE-Cascade, an interactive system for cost-adaptive chart question answering. Given a chart image and a natural-language question, SAFE-Cascade first extracts chart text with OCR, obtains a provisional answer from a text-only language model, and then uses a learned router to decide whether to accept the text answer or escalate to a VLM. The demo exposes this decision process to users: OCR evidence, text-only answer, routing probability, escalation decision, final answer, estimated cost, and estimated latency are shown side by side. SAFE-Cascade is designed as a transparent interface for understanding when visual grounding is actually needed. Users can upload or select charts, ask questions, inspect the evidence used by each pathway, compare text-only and VLM answers, and adjust the escalation threshold to explore the accuracy-cost frontier. The system is implemented with Azure Document Intelligence for OCR, gpt-5-mini as the text-only model, gemini-2.5-flash-image as the VLM, and a Random Forest router trained on inference-time features. On a held-out ChartQA test split of 375 examples from a 2,500-example experiment, SAFE-Cascade achieves 69.1% unified accuracy with 73.1% VLM invocation, compared with 67.7% accuracy and 100% VLM invocation for the full-VLM baseline. The observed +1.4 percentage-point difference is statistically uncertain, so we interpret SAFE-Cascade as matching full-VLM performance while reducing VLM calls by 26.9% and estimated cost by 9.3%. The demonstration shows how selective modality routing can make multimodal knowledge systems more transparent, tunable, and cost-aware.

cs.IR↗

arXiv2026

LoReC: Rethinking Large Language Models for Graph Data Analysis

The advent of Large Language Models (LLMs) has fundamentally reshaped the way we interact with graphs, giving rise to a new paradigm called GraphLLM. As revealed in recent studies, graph learning can benefit from LLMs. However, we observe limited benefits when we directly utilize LLMs to make predictions for graph-related tasks within GraphLLM paradigm, which even yields suboptimal results compared to conventional GNN-based approaches. Through in-depth analysis, we find this failure can be attributed to LLMs' limited capability for processing graph data and their tendency to overlook graph information. To address this issue, we propose LoReC (Look, Remember, and Contrast), a novel plug-and-play method for GraphLLM paradigm, which enhances LLM's understanding of graph data through three stages: (1) Look: redistributing attention to graph; (2) Remember: re-injecting graph information into the Feed-Forward Network (FFN); (3) Contrast: rectifying the vanilla logits produced in the decoding process. Extensive experiments demonstrate that LoReC brings notable improvements over current GraphLLM methods and outperforms GNN-based approaches across diverse datasets. The implementation is available at https://github.com/Git-King-Zhan/LoReC.

cs.LG↗

arXiv2026

Long-Run Conditional Value-at-Risk Reinforcement Learning

Conditional value-at-risk (CVaR) is a prominent risk measure in financial engineering, energy systems, and supply chain management. In these domains, Markov decision processes (MDPs) with a long-run CVaR criterion effectively mitigate cost variability over a specified horizon. However, implementing MDPs relies on known transition models, which are typically unavailable in practice. This necessitates a model-free approach to risk-sensitive dynamic optimization. To tackle this challenge, we propose a reinforcement learning algorithm that simultaneously conducts policy evaluation and improvement based on a CVaR-specific Bellman local optimality equation. This algorithm employs a nonparametric incremental learning approach for policy improvement, relying on a single sample trajectory to identify the optimal policy. Under appropriate technical conditions, we prove almost sure convergence of the algorithm and derive its convergence rate. Our analysis reveals that the optimal convergence rate, measured by the mean absolute error of policy estimators, is of order O(1/n). Our main algorithm and results are further extended to solving the mean-CVaR optimization problem. Numerical experiments corroborate these results.

math.OC↗

arXiv2025

AdaptJobRec: Enhancing Conversational Career Recommendation through an LLM-Powered Agentic System

In recent years, recommendation systems have evolved from providing a single list of recommendations to offering a comprehensive suite of topic focused services. To better accomplish this task, conversational recommendation systems (CRS) have progressed from basic retrieval augmented LLM generation to agentic systems with advanced reasoning and self correction capabilities. However, agentic systems come with notable response latency, a longstanding challenge for conversational recommendation systems. To balance the trade off between handling complex queries and minimizing latency, we propose AdaptJobRec, the first conversational job recommendation system that leverages autonomous agent to integrate personalized recommendation algorithm tools. The system employs a user query complexity identification mechanism to minimize response latency. For straightforward queries, the agent directly selects the appropriate tool for rapid responses. For complex queries, the agent uses the memory processing module to filter chat history for relevant content, then passes the results to the intelligent task decomposition planner, and finally executes the tasks using personalized recommendation tools. Evaluation on Walmart's real world career recommendation scenarios demonstrates that AdaptJobRec reduces average response latency by up to 53.3% compared to competitive baselines, while significantly improving recommendation accuracy.

cs.IR↗

arXiv2025

V-CASS: Vision-context-aware Expressive Speech Synthesis for Enhancing User Understanding of Videos

Automatic video commentary systems are widely used on multimedia social media platforms to extract factual information about video content. However, current systems may overlook essential para-linguistic cues, including emotion and attitude, which are critical for fully conveying the meaning of visual content. The absence of these cues can limit user understanding or, in some cases, distort the video's original intent. Expressive speech effectively conveys these cues and enhances the user's comprehension of videos. Building on these insights, this paper explores the usage of vision-context-aware expressive speech in enhancing users' understanding of videos in video commentary systems. Firstly, our formatting study indicates that semantic-only speech can lead to ambiguity, and misaligned emotions between speech and visuals may distort content interpretation. To address this, we propose a method called vision-context-aware speech synthesis (V-CASS). It analyzes para-linguistic cues from visuals using a vision-language model and leverages a knowledge-infused language model to guide the expressive speech model in generating context-aligned speech. User studies show that V-CASS enhances emotional and attitudinal resonance, as well as user audio-visual understanding and engagement, with 74.68% of participants preferring the system. Finally, we explore the potential of our method in helping blind and low-vision users navigate web videos, improving universal accessibility.

cs.HC↗

arXiv2025

Emergency-Brake Simplex: Toward A Verifiably Safe Control-CPS Architecture for Abrupt Runtime Reachability Constraint Changes

When a system's constraints change abruptly, the system's reachability safety does no longer sustain. Thus, the system can reach a forbidden/dangerous value. Conventional remedy practically involves online controller redesign (OCR) to re-establish the reachability's compliance with the new constraints, which, however, is usually too slow. There is a need for an online strategy capable of managing runtime changes in reachability constraints. However, to the best of the authors' knowledge, this topic has not been addressed in the existing literature. In this paper, we propose a fast fault tolerance strategy to recover the system's reachability safety in runtime. Instead of redesigning the system's controller, we propose to change the system's reference state to modify the system's reachability to comply with the new constraints. We frame the reference state search as an optimization problem and employ the Karush-Kuhn-Tucker (KKT) method as well as the Interior Point Method (IPM) based Newton's method (as a fallback for the KKT method) for fast solution derivation. The optimization also allows more future fault tolerance. Numerical simulations demonstrate that our method outperforms the conventional OCR method in terms of computational efficiency and success rate. Specifically, the results show that the proposed method finds a solution $10^{2}$ (with the IPM based Newton's method) $\sim 10^{4}$ (with the KKT method) times faster than the OCR method. Additionally, the improvement rate of the success rate of our method over the OCR method is $40.81\%$ without considering the deadline of run time. The success rate remains at $49.44\%$ for the proposed method, while it becomes $0\%$ for the OCR method when a deadline of $1.5 \; seconds$ is imposed.

eess.SY↗

arXiv2024

SpeechCraft: A Fine-grained Expressive Speech Dataset with Natural Language Description

Speech-language multi-modal learning presents a significant challenge due to the fine nuanced information inherent in speech styles. Therefore, a large-scale dataset providing elaborate comprehension of speech style is urgently needed to facilitate insightful interplay between speech audio and natural language. However, constructing such datasets presents a major trade-off between large-scale data collection and high-quality annotation. To tackle this challenge, we propose an automatic speech annotation system for expressiveness interpretation that annotates in-the-wild speech clips with expressive and vivid human language descriptions. Initially, speech audios are processed by a series of expert classifiers and captioning models to capture diverse speech characteristics, followed by a fine-tuned LLaMA for customized annotation generation. Unlike previous tag/templet-based annotation frameworks with limited information and diversity, our system provides in-depth understandings of speech style through tailored natural language descriptions, thereby enabling accurate and voluminous data generation for large model training. With this system, we create SpeechCraft, a fine-grained bilingual expressive speech dataset. It is distinguished by highly descriptive natural language style prompts, containing approximately 2,000 hours of audio data and encompassing over two million speech clips. Extensive experiments demonstrate that the proposed dataset significantly boosts speech-language task performance in stylist speech synthesis and speech style understanding.

cs.MM↗

arXiv2024

Fuzzy Logic Guided Reward Function Variation: An Oracle for Testing Reinforcement Learning Programs

Reinforcement Learning (RL) has gained significant attention across various domains. However, the increasing complexity of RL programs presents testing challenges, particularly the oracle problem: defining the correctness of the RL program. Conventional human oracles struggle to cope with the complexity, leading to inefficiencies and potential unreliability in RL testing. To alleviate this problem, we propose an automated oracle approach that leverages RL properties using fuzzy logic. Our oracle quantifies an agent's behavioral compliance with reward policies and analyzes its trend over training episodes. It labels an RL program as "Buggy" if the compliance trend violates expectations derived from RL characteristics. We evaluate our oracle on RL programs with varying complexities and compare it with human oracles. Results show that while human oracles perform well in simpler testing scenarios, our fuzzy oracle demonstrates superior performance in complex environments. The proposed approach shows promise in addressing the oracle problem for RL testing, particularly in complex cases where manual testing falls short. It offers a potential solution to improve the efficiency, reliability, and scalability of RL program testing. This research takes a step towards automated testing of RL programs and highlights the potential of fuzzy logic-based oracles in tackling the oracle problem.

cs.SE↗

arXiv2022

Phy-Taylor: Physics-Model-Based Deep Neural Networks

Purely data-driven deep neural networks (DNNs) applied to physical engineering systems can infer relations that violate physics laws, thus leading to unexpected consequences. To address this challenge, we propose a physics-model-based DNN framework, called Phy-Taylor, that accelerates learning compliant representations with physical knowledge. The Phy-Taylor framework makes two key contributions; it introduces a new architectural Physics-compatible neural network (PhN), and features a novel compliance mechanism, we call {\em Physics-guided Neural Network Editing\}. The PhN aims to directly capture nonlinearities inspired by physical quantities, such as kinetic energy, potential energy, electrical power, and aerodynamic drag force. To do so, the PhN augments neural network layers with two key components: (i) monomials of Taylor series expansion of nonlinear functions capturing physical knowledge, and (ii) a suppressor for mitigating the influence of noise. The neural-network editing mechanism further modifies network links and activation functions consistently with physical knowledge. As an extension, we also propose a self-correcting Phy-Taylor framework that introduces two additional capabilities: (i) physics-model-based safety relationship learning, and (ii) automatic output correction when violations of safety occur. Through experiments, we show that (by expressing hard-to-learn nonlinearities directly and by constraining dependencies) Phy-Taylor features considerably fewer parameters, and a remarkably accelerated training process, while offering enhanced model robustness and accuracy.

cs.LG↗

arXiv2019

Non-destructive three-dimensional measurement of hand vein based on self-supervised network

At present, supervised stereo methods based on deep neural network have achieved impressive results. However, in some scenarios, accurate three-dimensional labels are inaccessible for supervised training. In this paper, a self-supervised network is proposed for binocular disparity matching (SDMNet), which computes dense disparity maps from stereo image pairs without disparity labels: In the self-supervised training, we match the stereo images densely to approximate the disparity maps and use them to warp the left and right images to estimate the right and left images; we build the loss function between estimated images and original images for self-supervised training, which adopts perceptual loss to help improve the quality of disparity maps in both detail and structure. Then, we use SDMNet to obtain disparities of hand vein. SDMNet has achieved excellent results on KITTI 2012, KITTI 2015, simulated vein dataset and real vein dataset, outperforming many state-of-the-art supervised matching methods.

cs.CV↗

arXiv2016

Chinese Song Iambics Generation with Neural Attention-based Model

Learning and generating Chinese poems is a charming yet challenging task. Traditional approaches involve various language modeling and machine translation techniques, however, they perform not as well when generating poems with complex pattern constraints, for example Song iambics, a famous type of poems that involve variable-length sentences and strict rhythmic patterns. This paper applies the attention-based sequence-to-sequence model to generate Chinese Song iambics. Specifically, we encode the cue sentences by a bi-directional Long-Short Term Memory (LSTM) model and then predict the entire iambic with the information provided by the encoder, in the form of an attention-based LSTM that can regularize the generation process by the fine structure of the input cues. Several techniques are investigated to improve the model, including global context integration, hybrid style training, character vector initialization and adaptation. Both the automatic and subjective evaluation results show that our model indeed can learn the complex structural and rhythmic patterns of Song iambics, and the generation is rather successful.

cs.CL↗

arXiv2016

Can Machine Generate Traditional Chinese Poetry? A Feigenbaum Test

Recent progress in neural learning demonstrated that machines can do well in regularized tasks, e.g., the game of Go. However, artistic activities such as poem generation are still widely regarded as human's special capability. In this paper, we demonstrate that a simple neural model can imitate human in some tasks of art generation. We particularly focus on traditional Chinese poetry, and show that machines can do as well as many contemporary poets and weakly pass the Feigenbaum Test, a variant of Turing test in professional domains. Our method is based on an attention-based recurrent neural network, which accepts a set of keywords as the theme and generates poems by looking at each keyword during the generation. A number of techniques are proposed to improve the model, including character vector initialization, attention to input and hybrid-style training. Compared to existing poetry generation methods, our model can generate much more theme-consistent and semantic-rich poems.

cs.CL↗

arXiv2013

Poisson-type Multivariate Transfer Function Model Reveals Short-term Effects of Ambient Air Pollutants on Hospital Emergency room Visits for Cerebro-cardiovascular Diseases

Laboratory experiments have shown that cardiovascular diseases are positively correlated to the concentration of ambient air pollutants, such as SO2, NO2, PM10, etc. It has also been repeatedly reported in many countries that increased concentration of ambient air pollutants leads to rise in hospital emergency room visitss for these diseases. These studies mainly adopt either regression analysis or preliminary models in time series analysis, while the multivariable transfer function model, a relatively newly developed model, has multiple advantages over the conventional linear regression on analyzing time series. This study attempts to quantify the association between concentrations ambient air pollutants and hospital emergency room visitss for cerebro-cardiovascular diseases in Beijing using a Poisson-type multivariate transfer function model. The results show that the RR values of SO2, NO2 and PM10 for a 50 g/m3 increase are 1.129, 1.092 and 1.069 respectively. The lags for the three pollutants are estimated to be 2 days, 1 day and 1 day respectively. Compared with the ambient pollutants, daily average temperature and relative humidity do not influence the daily count of hospital emergency room visits significantly.

stat.AP↗

arXiv2013

Genetic analysis of differentiation of T-helper lymphocytes

In the human immune system, T-helper cells are able to differentiate into two lymphocyte subsets: Th1 and Th2. The intracellular signaling pathways of differentiation form a dynamic regulation network by secreting distinctive types of cytokines, while differentiation is regulated by two major gene loci: T-bet and GATA-3. We developed a system dynamics model to simulate the differentiation and re-differentiation process of T-helper cells, based on gene expression levels of T-bet and GATA-3 during differentiation of these cells. We arrived at three ultimate states of the model and came to the conclusion that cell differentiation potential exists as long as the system dynamics is at an unstable equilibrium point; the T-helper cells will no longer have the potential of differentiation when the model reaches a stable equilibrium point. In addition, the time lag caused by expression of transcription factors can lead to oscillations in the secretion of cytokines during differentiation.

q-bio.CB↗

arXiv2013

A quantitative evaluation of health care system in US, China, and Sweden

This study is mainly aimed at evaluating the effectiveness of current health care systems of several representative countries and improving that of the US. To achieve these goals, a people-oriented non-linear evaluation model is designed. It comprises one major evaluation metric and four minor metrics. The major metric is constituted by combining possible factors that most significantly determine or affect the life expectancy of people in this country. The four minor metrics evaluate less important aspects of health care systems and are subordinate to the major one. The authors rank some of the health care systems in the world according to the major metric and detect problems in them with the help of minor ones. It is concluded that the health care system of Sweden scores higher than the US and Chinese system scores lower than that of the US. Especially, the health care system of US lags behind a little bit compared with its economic power. At last, it is reasonable for the American government to optimize the arrangement of funding base on the result of goal programming model.

stat.AP↗

arXiv2012

A Robust Relay Placement Framework for 60GHz mmWave Wireless Personal Area Networks

Multimedia streaming applications with stringent QoS requirements in 60GHz mmWave wireless personal area networks (WPANs) demand high rate and low latency data transfer as well as low service disruption. In this paper, we consider the problem of robust relay placement in 60GHz WPANs. Relays forward traffic from transmitter devices to receiver devices facilitating i) the primary communication path for non-line-of-sight (NLOS) transceiver pairs, and ii) secondary (backup) communication path for line-of-sight (LOS) transceiver pairs. We formulate the robust minimum relay placement problem and the robust maximum utility relay placement problem with the objective to minimize the number of relays deployed and maximize the network utility, respectively. Efficient algorithms are developed to solve both problems and have been shown to incur less service disruption in presence of moving subjects that may block the LOS paths in the environment.

cs.NI↗