arXiv subjects

Xinyue Kang

Publications and source records attributed to Xinyue Kang.

7 recordsLinked to original sources

arXiv2026

Exploiting Intrinsic Duality for Multi-Hop Question Generation

Multi hop question generation (MQG) aims to generate questions from multiple given documents and target answers, whereas question answering (QA) focuses on deriving answers from documents given specific questions. Although MQG and QA are inherently dual tasks, most existing MQG studies largely overlook this intrinsic duality. To address this limitation, we propose QQ, a novel framework that exploits the duality between Question and answer for multi hop Question generation. Specifically, QQ employs a unified architecture functioning simultaneously as both an MQG and a QA model to fully leverage their interdependence. Our framework is driven by two key mechanisms: (i) enforcing bidirectional alignment constraints to ensure strict mutual correspondence between the questions generated by the MQG model and the answers produced by the QA model; and (ii) applying contrastive learning to pull paired question answer representations closer while pushing unpaired ones apart, thereby reinforcing this correspondence. Extensive automatic and human evaluations on the HotpotQA and MuSiQue datasets demonstrate that the QQ framework significantly improves the quality of generated multi hop questions.

cs.CL↗

arXiv2026

Pseudo-Siamese Network for Planning in Target-Oriented Proactive Dialogues

A target-oriented proactive dialogue system is designed to steer conversations toward predefined targets while actively providing suggestions. The core paradigm of such a system is to plan a reasonable dialogue path and subsequently guide language models (e.g., pre-trained or large language models) to generate responses, where dialogue path planning serves as the central component-a novel yet under-explored problem. In this work, we propose a Forward-Focused Bidirectional Pseudo-Siamese Network (FF-BPSN) for dialogue path planning toward predefined dialogue targets. FF-BPSN employs two identical transformer-based decoders for forward and backward planning, together with a forward-focused module that integrates bidirectional information to construct the final forward path. This path benefits from bidirectional planning while prioritizing forward information. We then employ the planned path to guide language models in response generation. Extensive experiments on DuRecDial and DuRecDial 2.0 demonstrate that FF-BPSN achieves state-of-the-art performance in dialogue path planning and significantly enhances the effectiveness of target-oriented proactive dialogue systems.

cs.CL↗

arXiv2025

Two operator splitting methods for three-dimensional stochastic Maxwell equations with multiplicative noise

In this paper, we develop two energy-preserving splitting methods for solving three-dimensional stochastic Maxwell equations driven by multiplicative noise. We use operator splitting methods to decouple stochastic Maxwell equations into simple one-dimensional subsystems and construct two stochastic splitting methods, Splitting Method I and Splitting Method II, through a combination of spatial compact difference methods and the midpoint rule in time discretization for the deterministic parts, and exact unitary analytical solutions for the stochastic parts. Theoretical proofs show that both methods strictly preserve the discrete energy conservation law. Finally, numerical experiments fully verify the energy conservation of the methods and demonstrate that the temporal convergence order of the two splitting methods is first-order.

math.NA↗

arXiv2025

Stochastic positivity-preserving symplectic splitting methods for stochastic Lotka--Volterra predator-prey model

In this paper, we present two stochastic positive-preserving symplectic methods for the stochastic Lotka-Volterra predator-prey model driven by a multiplicative noise. To inherit the intrinsic characteristic of the original system, the stochastic Lie--Trotter splitting method and the stochastic Strang splitting method are introduced, which are proved to preserve the positivity of the numerical solution and possess the discrete stochastic symplectic conservation law as well. By deriving the uniform boundedness of the $p$-th moment of the numerical solution, we prove that the strong convergence orders of these two methods are both one in the $L^2(Ω)$-norm. Finally, we validate the theoretical results through two and four dimensional numerical examples.

math.NA↗

arXiv2025

Model Whisper: Steering Vectors Unlock Large Language Models' Potential in Test-time

It is a critical challenge to efficiently unlock the powerful reasoning potential of Large Language Models (LLMs) for specific tasks or new distributions. Existing test-time adaptation methods often require tuning model parameters, which is not only computationally expensive but also risks degrading the model's pre-existing abilities.To address this, we introduce a lightweight component, Test-Time Steering Vectors (TTSV), which is prepended to the input while keeping the LLM's parameters entirely frozen. By optimizing the TTSV on test data to minimize the model's output entropy, we steer the model towards an internal state of higher confidence, activating its inherent abilities most relevant to the current task. TTSV is both lightweight and highly efficient to optimize, making it a true plug-and-play enhancement. Extensive experiments validate our approach's effectiveness on both base models and reasoning-enhanced models. For instance, on the MATH500 task, TTSV achieves a 45.88% relative performance gain on the Qwen2.5-Math-7B model and a 16.22% relative gain on the Qwen3-4B model. Furthermore, our approach exhibits robust generalization, with its steering vectors proving highly transferable across diverse tasks.

cs.CL↗

arXiv2022

The Magic of Slow-to-Fast and Constant: Evaluating Time Perception of Progress Bars by Bayesian Model

Objective: We aimed to use adaptive psychophysics methods, which is a Bayesian Model, to measure users' time perception of various progress bar quantitatively. Background: Progress bar informs users about the status of ongoing processes. Progress bars frequently display nonuniform speed patterns, such as acceleration and deceleration. However, which progress bar is perceived faster remain unclear. Methods: We measured the point of subject equality (PSE) of the constant progress bar toward four different 5-second progress bars with a non-constant speed. To measure PSE, in each trial, a constant progress bar and a non-constant progress bar were presented to participants. Participants needed to judge which one is shorter. Based on their choice, the model generated the time duration of constant progress bar in next trial. After 40 trials for each non-constant progress bar, the PSE was calculated by the model. Eye tracking was recorded during the experiment.Results: Our results show that the constant progress bar and speed-up progress bar are perceived to be faster. The anchoring effect fits the results of our study, indicating that the final part of the progress bar is more important for time perception. Moreover, the eye-tracking results indicate that the progress bar is perceived to be slower is related to the overload of cognitive resources.Conclusion: The constant progress bar and speed-up progress bar are perceived as the quickest. Application: The results suggest that UX design can use constant or speed-up progress bar, in order to improve user experience in waiting.

cs.HC↗

arXiv2017

Quantum control via a genetic algorithm of the field ionization pathway of a Rydberg electron

Quantum control of the pathway along which a Rydberg electron field ionizes is experimentally and computationally demonstrated. Selective field ionization is typically done with a slowly rising electric field pulse. The $(1/n^*)^4$ scaling of the classical ionization threshold leads to a rough mapping between arrival time of the electron signal and principal quantum number of the Rydberg electron. This is complicated by the many avoided level crossings that the electron must traverse on the way to ionization, which in general leads to broadening of the time-resolved field ionization signal. In order to control the ionization pathway, thus directing the signal to the desired arrival time, a perturbing electric field produced by an arbitrary waveform generator is added to a slowly rising electric field. A genetic algorithm evolves the perturbing field in an effort to achieve the target time-resolved field ionization signal.

physics.atom-ph↗