arXiv subjects

Yao Li

Publications and source records attributed to Yao Li.

At least 55 records · Page 3Linked to original sources

arXiv2026

Privacy Control in Conversational LLM Platforms: A Walkthrough Study

Large language models (LLMs) are increasingly integrated into daily life through conversational interfaces, processing user data via natural language inputs and exhibiting advanced reasoning capabilities, which raises new concerns about user control over privacy. While much research has focused on potential privacy risks, less attention has been paid to the data control mechanisms these platforms provide. This study examines six conversational LLM platforms, analyzing how they define and implement features for users to access, edit, delete, and share data. Our analysis reveals an emerging paradigm of data control in conversational LLM platforms, where user data is generated and derived through interaction itself, natural language enables flexible yet often ambiguous control, and multi-user interactions with shared data raise questions of co-ownership and governance. Based on these findings, we offer practical insights for platform developers, policymakers, and researchers to design more effective and usable privacy controls in LLM-powered conversational interactions.

cs.HC↗

arXiv2026

Single Index Bandits: Generalized Linear Contextual Bandits with Unknown Reward Functions

Generalized linear bandits have been extensively studied due to their broad applicability in real-world online decision-making problems. However, these methods typically assume that the expected reward function is known to the users, an assumption that is often unrealistic in practice. Misspecification of this link function can lead to the failure of all existing algorithms. In this work, we address this critical limitation by introducing a new problem of generalized linear bandits with unknown reward functions, also known as single index bandits. We first consider the case where the unknown reward function is monotonically increasing, and propose two novel and efficient algorithms, STOR and ESTOR, that achieve decent regrets under standard assumptions. Notably, our ESTOR can obtain the nearly optimal regret bound $\tilde{O}_T(\sqrt{T})$ in terms of the time horizon $T$. We then extend our methods to the high-dimensional sparse setting and show that the same regret rate can be attained with the sparsity index. Next, we introduce GSTOR, an algorithm that is agnostic to general reward functions, and establish regret bounds under a Gaussian design assumption. Finally, we validate the efficiency and effectiveness of our algorithms through experiments on both synthetic and real-world datasets.

stat.ML↗

arXiv2026

A Human-Centred AI System for Multi-Actor Planning and Collaboration in Family Learning

Family learning takes place in everyday routines where children and caregivers read, practice, and develop new skills together. Despite growing interest in AI tutors, most existing systems are designed for single learners or classroom settings and do not address the distributed planning, coordination, and execution demands of learning at home. This paper introduces ParPal, a human-centred, LLM-powered system that supports multi-actor family learning by decomposing learning goals into actionable subtasks, allocating them across caregivers under realistic availability and expertise constraints, and providing caregiver-in-the-loop tutoring support with visibility into individual and collective contributions. Through expert evaluation of generated weekly learning plans and a one-week field deployment with 11 families, we identify systematic failure modes in current LLM-based planning, including misalignment with role expertise, unnecessary or costly collaboration, missing pedagogical learning trajectories, and physically or temporally infeasible tasks. While ParPal improves coordination clarity and recognition of caregiving effort, these findings expose fundamental limitations in how current LLMs operationalize pedagogical knowledge, reason about collaboration, and account for real-world, embodied constraints. We discuss implications for human-centred AI design and AI methodology, positioning multi-actor family learning as a critical testbed for advancing planning, adaptation, and pedagogical structure in next-generation AI systems.

cs.HC↗

arXiv2026

SymCode: A Neurosymbolic Approach to Mathematical Reasoning via Verifiable Code Generation

Large Language Models (LLMs) often struggle with complex mathematical reasoning, where prose-based generation leads to unverified and arithmetically unsound solutions. Current prompting strategies like Chain of Thought still operate within this unreliable medium, lacking a mechanism for deterministic verification. To address these limitations, we introduce SymCode, a neurosymbolic framework that reframes mathematical problem-solving as a task of verifiable code generation using the SymPy library. We evaluate SymCode on challenging benchmarks, including MATH-500 and OlympiadBench, demonstrating significant accuracy improvements of up to 13.6 percentage points over baselines. Our analysis shows that SymCode is not only more token-efficient but also fundamentally shifts model failures from opaque logical fallacies towards transparent, programmatic errors. By grounding LLM reasoning in a deterministic symbolic engine, SymCode represents a key step towards more accurate and trustworthy AI in formal domains.

cs.CL↗

arXiv2026

Unveiling the jet angular broadening with photon-tagged jets in high-energy nuclear collisions

The medium modification of jet substructure in hot and dense nuclear matter has garnered significant interest from the heavy-ion physics community in recent years. Measurements of inclusive jets show an angular narrowing in nucleus-nucleus collisions, while recent CMS results for photon-tagged jets ($γ$+jets) suggest evidence of broadening. In this study, we conduct a theoretical analysis of the angular structure of inclusive jets and $γ$+jets using a transport approach that accounts for jet energy loss and the medium response in the quark-gluon plasma. We examine the girth modification of $γ$+jets in $0-30\%$ PbPb collisions at $\sqrt{s_{NN}} = 5.02$ TeV, achieving satisfactory agreement with recent CMS measurements. We explore the relationship between selection bias and jet kinematics by varying the threshold for $x_{jγ} = p_T^{\rm jet}/p_T^γ$. Notably, we quantitatively demonstrate that $γ$+jets significantly reduce selection bias and can effectively select jets that have been sufficiently quenched in PbPb collisions, which is crucial for capture the jet angular broadening. Additionally, we estimate the contributions of medium-induced gluon radiation and the medium response to the broadening of the jet angular substructure. Lastly, we analyze the modification patterns of jet $R_g$ and $ΔR_{\rm axis}$ in PbPb collisions, which indicate slight broadening for $γ$+jets and noticeable narrowing for inclusive jets compared to pp collisions.

hep-ph↗

arXiv2026

Observation of anomalous exciton polariton bands in PEPI perovskite based microcavity at room temperature

Recently anomalous energy bands with negative mass attract intensive attention where non Hermiticity plays an important role. In this work we observe anomalous exciton polariton bands in PEPI perovskite based microcavity at room temperature. We simulate the anomalous band structure using a non-Hermitian coupled oscillator model which agree with experiments very well. Our results offer to study non-Hermitian polariton wave dynamics at room temperature.

physics.optics↗

arXiv2025

Task Vector in TTS: Toward Emotionally Expressive Dialectal Speech Synthesis

Recent advances in text-to-speech (TTS) have yielded remarkable improvements in naturalness and intelligibility. Building on these achievements, research has increasingly shifted toward enhancing the expressiveness of generated speech, such as dialectal and emotional TTS. However, cross-style synthesis combining both dialect and emotion remains challenging and largely unexplored, mainly due to the scarcity of dialectal data with emotional labels. To address this, we propose Hierarchical Expressive Vector (HE-Vector), a two-stage method for Emotional Dialectal TTS. In the first stage, we construct different task vectors to model dialectal and emotional styles independently, and then enhance single-style synthesis by adjusting their weights, a method we refer to as Expressive Vector (E-Vector). For the second stage, we hierarchically integrate these vectors to achieve controllable emotionally expressive dialect synthesis without requiring jointly labeled data, corresponding to Hierarchical Expressive Vector (HE-Vector). Experimental results demonstrate that HE-Vectors achieve superior performance in dialect synthesis, and promising results in synthesizing emotionally expressive dialectal speech in a zero-shot setting.

cs.SD↗

arXiv2025

Inverse Optimal Control for Linear Quadratic Tracking with Unknown Target States

This paper addresses the inverse optimal control for the linear quadratic tracking problem with a fixed but unknown target state, which aims to estimate the possible triplets comprising the target state, the state weight matrix, and the input weight matrix from observed optimal control input and the corresponding state trajectories. Sufficient conditions have been provided for the unique determination of both the linear quadratic cost function as well as the target state. A computationally efficient and numerically reliable parameter identification algorithm is proposed by equating optimal control strategies with a system of linear equations, and the associated relative error upper bound is derived in terms of data volume and signal-to-noise ratio. Moreover, the proposed inverse optimal control algorithm is applied for the joint cluster coordination and intent identification of a multi-agent system. By incorporating the structural constraint of the Laplace matrix, the relative error upper bound can be reduced accordingly. Finally, the algorithm's efficiency and accuracy are validated by a vehicle-on-a-lever example and a multi-agent formation control example.

eess.SY↗

arXiv2025

ZO-ASR: Zeroth-Order Fine-Tuning of Speech Foundation Models without Back-Propagation

Fine-tuning pre-trained speech foundation models for Automatic Speech Recognition (ASR) is prevalent, yet constrained by substantial GPU memory requirements. We introduce ZO-ASR, a memory-efficient Zeroth-Order (ZO) method that avoids Back-Propagation (BP) and activation memory by estimating gradients via forward passes. When combined with SGD optimizer, ZO-ASR-SGD fine-tunes ASR models using only inference memory. Our evaluation spans supervised and unsupervised tasks. For Supervised Domain Adaptation on Whisper-Large-V3, ZO-ASR's multiple query mechanism enhances robustness and achieves up to an 18.9\% relative Word Error Rate reduction over zero-shot baselines, outperforming existing ZO methods. For unsupervised Test-Time Adaptation on Wav2Vec2-Base, ZO-ASR exhibits moderately lower performance compared to first-order optimizer Adam. Our BP-free approach provides a viable solution for fine-tuning ASR models in computationally resource-constrained or gradient-inaccessible scenarios.

cs.MM↗

arXiv2025

MAC-SLU: Multi-Intent Automotive Cabin Spoken Language Understanding Benchmark

Spoken Language Understanding (SLU), which aims to extract user semantics to execute downstream tasks, is a crucial component of task-oriented dialog systems. Existing SLU datasets generally lack sufficient diversity and complexity, and there is an absence of a unified benchmark for the latest Large Language Models (LLMs) and Large Audio Language Models (LALMs). This work introduces MAC-SLU, a novel Multi-Intent Automotive Cabin Spoken Language Understanding Dataset, which increases the difficulty of the SLU task by incorporating authentic and complex multi-intent data. Based on MAC-SLU, we conducted a comprehensive benchmark of leading open-source LLMs and LALMs, covering methods like in-context learning, supervised fine-tuning (SFT), and end-to-end (E2E) and pipeline paradigms. Our experiments show that while LLMs and LALMs have the potential to complete SLU tasks through in-context learning, their performance still lags significantly behind SFT. Meanwhile, E2E LALMs demonstrate performance comparable to pipeline approaches and effectively avoid error propagation from speech recognition. Code\footnote{https://github.com/Gatsby-web/MAC\_SLU} and datasets\footnote{huggingface.co/datasets/Gatsby1984/MAC\_SLU} are released publicly.

cs.CL↗

arXiv2025

Data-driven computation for periodic stochastic differential equations

Many stochastic differential equations in various applications like coupled neuronal oscillators are driven by time-periodic forces. In this paper, we extend several data-driven computational tools from autonomous Fokker-Planck equation to the time-periodic setting. This allows us to efficiently compute the time-periodic invariant probability measure using either grid-base method or artificial neural network solver, and estimate the speed of convergence towards the time-periodic invariant probability measure. We analyze the convergence of our algorithms and test their performances with several numerical examples.

math.NA↗

arXiv2025

Toward generic control for soft robotic systems

Soft robotics has advanced rapidly, yet its control methods remain fragmented: different morphologies and actuation schemes still require task-specific controllers, hindering theoretical integration and large-scale deployment. A generic control framework is therefore essential, and a key obstacle lies in the persistent use of rigid-body control logic, which relies on precise models and strict low-level execution. Such a paradigm is effective for rigid robots but fails for soft robots, where the ability to tolerate and exploit approximate action representations, i.e., control compliance, is the basis of robustness and adaptability rather than a disturbance to be eliminated. Control should thus shift from suppressing compliance to explicitly exploiting it. Human motor control exemplifies this principle: instead of computing exact dynamics or issuing detailed muscle-level commands, it expresses intention through high-level movement tendencies, while reflexes and biomechanical mechanisms autonomously resolve local details. This architecture enables robustness, flexibility, and cross-task generalization. Motivated by this insight, we propose a generic soft-robot control framework grounded in control compliance and validate it across robots with diverse morphologies and actuation mechanisms. The results demonstrate stable, safe, and cross-platform transferable behavior, indicating that embracing control compliance, rather than resisting it, may provide a widely applicable foundation for unified soft-robot control.

cs.RO↗

arXiv2025

PINNsFailureRegion Localization and Refinement through White-box AdversarialAttack

Physics-informed neural networks (PINNs) have shown great promise in solving partial differential equations (PDEs). However, vanilla PINNs often face challenges when solving complex PDEs, especially those involving multi-scale behaviors or solutions with sharp or oscillatory characteristics. To precisely and adaptively locate the critical regions that fail in the solving process we propose a sampling strategy grounded in white-box adversarial attacks, referred to as WbAR. WbAR search for failure regions in the direction of the loss gradient, thus directly locating the most critical positions. WbAR generates adversarial samples in a random walk manner and iteratively refines PINNs to guide the model's focus towards dynamically updated critical regions during training. We implement WbAR to the elliptic equation with multi-scale coefficients, Poisson equation with multi-peak solutions, high-dimensional Poisson equations, and Burgers equation with sharp solutions. The results demonstrate that WbAR can effectively locate and reduce failure regions. Moreover, WbAR is suitable for solving complex PDEs, since locating failure regions through adversarial attacks is independent of the size of failure regions or the complexity of the distribution.

cs.LG↗

arXiv2025

Quantum Lipschitz Bandits

The Lipschitz bandit is a key variant of stochastic bandit problems where the expected reward function satisfies a Lipschitz condition with respect to an arm metric space. With its wide-ranging practical applications, various Lipschitz bandit algorithms have been developed, achieving the cumulative regret lower bound of order $\tilde O(T^{(d_z+1)/(d_z+2)})$ over time horizon $T$. Motivated by recent advancements in quantum computing and the demonstrated success of quantum Monte Carlo in simpler bandit settings, we introduce the first quantum Lipschitz bandit algorithms to address the challenges of continuous action spaces and non-linear reward functions. Specifically, we first leverage the elimination-based framework to propose an efficient quantum Lipschitz bandit algorithm named Q-LAE. Next, we present novel modifications to the classical Zooming algorithm, which results in a simple quantum Lipschitz bandit method, Q-Zooming. Both algorithms exploit the computational power of quantum methods to achieve an improved regret bound of $\tilde O(T^{d_z/(d_z+1)})$. Comprehensive experiments further validate our improved theoretical findings, demonstrating superior empirical performance compared to existing Lipschitz bandit methods.

cs.LG↗

arXiv2025

PDAC: Efficient Coreset Selection for Continual Learning via Probability Density Awareness

Rehearsal-based Continual Learning (CL) maintains a limited memory buffer to store replay samples for knowledge retention, making these approaches heavily reliant on the quality of the stored samples. Current Rehearsal-based CL methods typically construct the memory buffer by selecting a representative subset (referred to as coresets), aiming to approximate the training efficacy of the full dataset with minimal storage overhead. However, mainstream Coreset Selection (CS) methods generally formulate the CS problem as a bi-level optimization problem that relies on numerous inner and outer iterations to solve, leading to substantial computational cost thus limiting their practical efficiency. In this paper, we aim to provide a more efficient selection logic and scheme for coreset construction. To this end, we first analyze the Mean Squared Error (MSE) between the buffer-trained model and the Bayes-optimal model through the perspective of localized error decomposition to investigate the contribution of samples from different regions to MSE suppression. Further theoretical and experimental analyses demonstrate that samples with high probability density play a dominant role in error suppression. Inspired by this, we propose the Probability Density-Aware Coreset (PDAC) method. PDAC leverages the Projected Gaussian Mixture (PGM) model to estimate each sample's joint density, enabling efficient density-prioritized buffer selection. Finally, we introduce the streaming Expectation Maximization (EM) algorithm to enhance the adaptability of PGM parameters to streaming data, yielding Streaming PDAC (SPDAC) for streaming scenarios. Extensive comparative experiments show that our methods outperforms other baselines across various CL settings while ensuring favorable efficiency.

cs.LG↗

arXiv2025

Enhancing Speech-to-Speech Dialogue Modeling with End-to-End Retrieval-Augmented Generation

End-to-end speech-to-speech (S2S) dialogue systems have recently garnered increasing research attention for their lower latency and more natural integration of nonverbal cues such as emotion and speaker identity. However, these systems face key challenges, particularly in incorporating external knowledge, a capability commonly addressed by Retrieval-Augmented Generation (RAG) in text-based large language models (LLMs). The core difficulty lies in the modality gap between input speech and retrieved textual knowledge, which hinders effective integration of information. To address this issue, we propose a novel end-to-end RAG framework that directly retrieves relevant textual knowledge from speech queries. Experimental results demonstrate that our method significantly improves the performance of end-to-end S2S dialogue systems while achieving higher retrieval efficiency. Although the overall performance still lags behind the SOTA cascaded models, our framework offers a promising direction for enhancing knowledge integration in end-to-end S2S systems. Our code and dataset are released.

cs.CL↗

arXiv2025

"Learning Together": AI-Mediated Support for Parental Involvement in Everyday Learning

Family learning takes place in everyday routines where children and caregivers read, practice, and develop new skills together. Although AI is increasingly present in learning environments, most systems remain child-centered and overlook the collaborative, distributed nature of family education. This paper investigates how AI can mediate family collaboration by addressing tensions of coordination, uneven workloads, and parental mediation. From a formative study with families using AI in daily learning, we identified challenges in responsibility sharing and recognition of contributions. Building on these insights, we designed FamLearn, an LLM-powered prototype that distributes tasks, visualizes contributions, and provides individualized support. A one-week field study with 11 families shows how this prototype can ease caregiving burdens, foster recognition, and enrich shared learning experiences. Our findings suggest that LLMs can move beyond the role of tutor to act as family mediators - balancing responsibilities, scaffolding intergenerational participation, and strengthening the relational fabric of family learning.

cs.HC↗

arXiv2025

Valuative Invariants of Catalan Matroids

We decompose the indicator function of each $(a, b)$-Catalan matroid polytope as a weighted sum of indicator function of matroid polytopes that correspond to direct sums of uniform matroids. Catalan matroids lie in the interior of the convex hull of direct sums of uniform matroids in the polytope of all matroids introduced by Ferroni and Fink. Moreover, we describe combinatorially the coefficients of the convex combination of direct sums of uniform matroid corresponding to an $(a,b)$-Catalan matroid. In particular, this allows us to derive explicit formulas for arbitrary valuative invariants of $(a, b)$-Catalan matroids. Among other applications, we prove that $(a,b)$-Catalan matroids are Ehrhart positive, and we find formulas for the Kazhdan--Lusztig invariants of these matroids.

math.CO↗