arXiv subjects

Quan Zhou

Publications and source records attributed to Quan Zhou.

At least 37 records · Page 2Linked to original sources

arXiv2026

Online Learning with Multiple Fairness Regularizers via Graph-Structured Feedback

There is an increasing need to enforce multiple, often competing, measures of fairness within automated decision systems. The appropriate weighting of these fairness objectives is typically unknown a priori, may change over time and, in our setting, must be learned adaptively through sequential interactions. In this work, we address this challenge in a bandit setting, where decisions are made with graph-structured feedback.

cs.LG↗

arXiv2026

Closed-Loop Sim-to-Real Reinforcement Learning for Deformable Microfiber Shape Control

Autonomous contact-based micromanipulation is challenging because surface and interfacial interactions at the microscale are difficult to model accurately, limiting the use of conventional model-based control and sim-to-real learning. We present a closed-loop sim-to-real reinforcement learning (RL) approach for microfiber shape control on a surface. The central idea is to train geometric shape regulation in a simplified frictionless simulator and rely on real-time visual feedback during deployment to iteratively correct the observed effects of unmodeled surface interactions. An RL policy trained entirely in simulation is transferred directly to a physical dual-gripper micromanipulation system operating at 40 Hz, without retraining or domain adaptation. Using silk microfibers as a testbed, the policy achieves a mean point-wise shape error of 270 $\pm$ 80 $μ$m across twenty-four diverse initial configurations. Across nine specimens covering all combinations of three fiber diameters (50, 80, and 120 $μ$m) and three manipulated lengths (10 mm, 15mm, and 20 mm), the same policy achieves sub-millimeter final shape error without any retraining or retuning. These results show that a policy learned in a simplified simulator can achieve repeatable real-world microfiber shape regulation under surface contact, provided that the task-relevant effects of the sim-to-real mismatch remain observable and correctable within the closed feedback loop.

cs.RO↗

arXiv2026

Representative Action Selection for Large Action Space Bandit Families

We study the problem of selecting a subset from a large action space shared by a family of bandits. In many natural situations, while the nominal set of actions is large, actions are highly correlated: many yield similar rewards across environments, making it wasteful to maintain the full set. Our aim is to understand whether it is possible -- and how -- to select a smaller set of representative actions that performs nearly as well as the full action space. Our main contribution is a surprisingly simple algorithm: repeatedly sample a bandit instance at random, solve it, and collect the optimal action. This algorithm can significantly reduce the action space when such correlations are present, without the need to know a-priori the correlation structure. We provide theoretical guarantees on the performance of the algorithm and demonstrate its practical effectiveness through empirical comparisons with Combinatorial Bandit, Meta Learning Bandit and Zooming baselines.

cs.LG↗

arXiv2026

Scenario-Guided LLM-based Mobile App GUI Testing

The assurance of mobile app GUI has become increasingly important, as the GUI serves as the primary medium of interaction between users and apps. Although numerous automated GUI testing approaches have been developed with diverse strategies, a substantial gap remains between these approaches and the underlying app business logic. Most existing approaches focus on general exploration rather than the completion of specific testing scenarios, often resulting in missed coverage of critical functionalities. Inspired by the manual testing process, which treats business logic, driven testing scenarios as the fundamental unit of testing, this paper introduces an approach that leverages large language models (LLMs) to comprehend the semantics expressed in app GUIs and their contextual relevance to given testing scenarios. Building upon this capability, we propose ScenGen, a novel scenario-guided LLM-based GUI testing framework that employs a multi-agent collaboration mechanism to simulate and automate the phases of manual testing. ScenGen integrates five agents. The Observer perceives the app GUI state by extracting and structuring GUI widgets and layouts, thereby interpreting the semantic information presented in the GUI. This information is then passed to the Decider, which makes scenario-driven decisions with the guidance of LLMs to identify target widgets and determine appropriate actions toward fulfilling specific testing goals. The Executor executes the decided operations on the app, while the Supervisor verifies whether the execution results align with the intended testing scenario completion, ensuring traceability and consistency in test generation and execution. Finally, the Recorder records the corresponding GUI operations into the context memory as a knowledge base for subsequent decision-making and concurrently monitors runtime bug occurrences.

cs.SE↗

arXiv2026

Filament: Denning-Style Information Flow Control for Rust

Existing language-based information-flow control (IFC) tools face a fundamental tension: Denning-style systems that track explicit and implicit flows at the variable level typically require compiler modifications, while more coarse-grained approaches, including recent work Cocoon, avoid compiler changes but impose more restrictive programming models. We present Filament, a Denning-style static IFC library for Rust that requires no compiler modifications. Filament addresses three key challenges in building a practical IFC library for Rust. First, it enables fine-grained explicit-flow checking with minimal annotation overhead by leveraging Rust's type inference. Second, it introduces pc_block!, a lightweight construct for enforcing implicit flows via a compile-time program counter label, without requiring compiler support. Third, it provides fcall! and mcall! macros to support seamless and safe interoperability with standard and third-party libraries. Our evaluation shows that Filament incurs negligible compile-time overhead and requires only modest annotations. Moreover, compared to Cocoon, Filament offers a more permissive programming model, reducing the need for frequent escape hatches that bypass security checks.

cs.PL↗

arXiv2026

DCP-CLIP:A Coarse-to-Fine Framework for Open-Vocabulary Semantic Segmentation with Dual Interaction

The recent years have witnessed the remarkable development for open-vocabulary semantic segmentation (OVSS) using visual-language foundation models, yet still suffer from following fundamental challenges: (1) insufficient cross-modal communications between textual and visual spaces, and (2) significant computational costs from the interactions with massive number of categories. To address these issues, this paper describes a novel coarse-to-fine framework, called DCP-CLIP, for OVSS. Unlike prior efforts that mainly relied on pre-established category content and the inherent spatial-class interaction capability of CLIP, we dynamic constructing category-relevant textual features and explicitly models dual interactions between spatial image features and textual class semantics. Specifically, we first leverage CLIP's open-vocabulary recognition capability to identify semantic categories relevant to the image context, upon which we dynamically generate corresponding textual features to serve as initial textual guidance. Subsequently, we conduct a coarse segmentation by cross-modally integrating semantic information from textual guidance into the visual representations and achieve refined segmentation by integrating spatially enriched features from the encoder to recover fine-grained details and enhance spatial resolution. In final, we leverage spatial information from the segmentation side to refine category predictions for each mask, facilitating more precise semantic labeling. Experiments on multiple OVSS benchmarks demonstrate that DCP-CLIP outperforms existing methods by delivering both higher accuracy and greater efficiency.

cs.CV↗

arXiv2026

A quickest detection problem with false negatives

We formulate and solve a variant of the quickest detection problem which features false negatives. A standard Brownian motion acquires a drift at an independent exponential random time which is not directly observable. Based on the observation in continuous time of the sample path of the process, an optimizer must detect the drift as quickly as possible after it has appeared. The optimizer can inspect the system multiple times upon payment of a fixed cost per inspection. If a test is performed on the system before the drift has appeared then, naturally, the test will return a negative outcome. However, if a test is performed after the drift has appeared, then the test may fail to detect it and return a false negative with probability $ε\in(0,1)$. The optimisation ends when the drift is eventually detected. The problem is formulated mathematically as an optimal multiple stopping problem, and it is shown to be equivalent to a recursive optimal stopping problem. Exploiting such connection and free boundary methods we find explicit formulae for the expected cost and the optimal strategy. We also show that when $ε= 0$ our expected cost is an affine transformation of the one in Shiryaev's classical optimal detection problem with a rescaled model parameter.

math.OC↗

arXiv2026

FilMBot: A High-Speed Soft Parallel Robotic Micromanipulator

Soft robotic manipulators are generally slow despite their great adaptability, resilience, and compliance. This limitation also extends to current soft robotic micromanipulators. Here, we introduce FilMBot, a 3-DOF film-based, electromagnetically actuated, soft kinematic robotic micromanipulator achieving speeds up to 2117 °/s and 2456 °/s in α and \{beta} angular motions, with corresponding linear velocities of 1.61 m/s and 1.92 m/s using a 4-cm needle end-effector, 0.54 m/s along the Z axis, and 1.57 m/s during Z-axis morph switching. The robot can reach ~1.50 m/s in path-following tasks, with an operational bandwidth below ~30 Hz, and remains responsive at 50 Hz. It demonstrates high precision (~6.3 μm, or ~0.05% of its workspace) in path-following tasks, with precision remaining largely stable across frequencies. The novel combination of the low-stiffness soft kinematic film structure and strong electromagnetic actuation in FilMBot opens new avenues for soft robotics. Furthermore, its simple construction and inexpensive, readily accessible components could broaden the application of micromanipulators beyond current academic and professional users.

cs.RO↗

arXiv2026

LegalOne: A Family of Foundation Models for Reliable Legal Reasoning

While Large Language Models (LLMs) have demonstrated impressive general capabilities, their direct application in the legal domain is often hindered by a lack of precise domain knowledge and complexity of performing rigorous multi-step judicial reasoning. To address this gap, we present LegalOne, a family of foundational models specifically tailored for the Chinese legal domain. LegalOne is developed through a comprehensive three-phase pipeline designed to master legal reasoning. First, during mid-training phase, we propose Plasticity-Adjusted Sampling (PAS) to address the challenge of domain adaptation. This perplexity-based scheduler strikes a balance between the acquisition of new knowledge and the retention of original capabilities, effectively establishing a robust legal foundation. Second, during supervised fine-tuning, we employ Legal Agentic CoT Distillation (LEAD) to distill explicit reasoning from raw legal texts. Unlike naive distillation, LEAD utilizes an agentic workflow to convert complex judicial processes into structured reasoning trajectories, thereby enforcing factual grounding and logical rigor. Finally, we implement a Curriculum Reinforcement Learning (RL) strategy. Through a progressive reinforcement process spanning memorization, understanding, and reasoning, LegalOne evolves from simple pattern matching to autonomous and reliable legal reasoning. Experimental results demonstrate that LegalOne achieves state-of-the-art performance across a wide range of legal tasks, surpassing general-purpose LLMs with vastly larger parameter counts through enhanced knowledge density and efficiency. We publicly release the LegalOne weights and the LegalKit evaluation framework to advance the field of Legal AI, paving the way for deploying trustworthy and interpretable foundation models in high-stakes judicial applications.

cs.CL↗

arXiv2025

Dynamical Dark Energy in light of DESI BAO and Full-Shape Data

Recently, the DESI BAO data has reported a preference of dynamical dark energy (DDE) over the \LambdaCDM cosmology. Apart from the BAO data, the DDE model should be also sensitive to low-redshift measurements of the matter power spectrum data. In this study, we address this point by combining the DESI Y1 data about the matter power spectrum, extracted from the DESI Full-Shape data, with the DESI DR2 BAO data among other probes. After building the DESI Y1 likelihood, we carry out a Markov Chain Monte Carlo analysis, showing that the constraints on $w_0$ and $w_a$ with DESI Y1 data included are improved over those without it for three different datasets widely considered, especially in the case of the DESY5 sample.

astro-ph.CO↗

arXiv2025

Teacher, But Also Student: Challenges and Tech Needs of Adult Braille Learners with Sight

Braille literacy is critical for blind individuals' independence and quality of life, yet literacy rates continue to decline. Though braille instructors in integrated K-12 classrooms play a central role in literacy development in blind youth, prior research on braille learning almost exclusively focuses on blind adolescent students. As a result, we still know little about how sighted adult teachers learn braille. To address this, we interviewed 14 educators, including 13 certificated Teachers of Students with Visual Impairments (TVIs) and 1 paraeducator, who learned braille as adults. We found that they: (1) lack consistent braille exposure to reinforce knowledge and skill; (2) have limited time to practice due to myriad responsibilities of adulthood; and thus, (3) seek learning tools that are engaging and efficient. Our research draws attention to the needs of a group of braille learners who have been overlooked and identifies new design opportunities to facilitate braille literacy.

cs.HC↗

arXiv2025

Bayesian Synthetic Control with a Soft Simplex Constraint

The challenges posed by high-dimensional data and use of the simplex constraint are two major concerns in the empirical application of the synthetic control method (SCM) in econometric studies. To address both issues simultaneously, we propose a Bayesian SCM that integrates a soft simplex constraint within spike-and-slab variable selection. The hierarchical prior structure captures the extent to which the data supports the simplex constraint, allowing for more efficient and data-adaptive counterfactual estimation. The intractable marginal likelihood induced by the soft simplex constraint presents a major computational challenge, which we resolve by developing a novel Metropolis-within-Gibbs algorithm that updates the regression coefficients of two predictors simultaneously. Our main theoretical contribution is a high-dimensional selection consistency result for the spike-and-slab variable selection under the simplex constraint, which significantly extends the current theory for high-dimensional Bayesian variable selection. Simulation studies demonstrate that our method performs well across diverse settings. To illustrate its practical values, we apply it to two empirical examples for estimating the effect of economic policies.

stat.ME↗

arXiv2025

Representative Action Selection for Large Action Space: From Bandits to MDPs

We study the problem of selecting a small, representative action subset from an extremely large action space shared across a family of reinforcement learning (RL) environments -- a fundamental challenge in applications like inventory management and recommendation systems, where direct learning over the entire space is intractable. Our goal is to identify a fixed subset of actions that, for every environment in the family, contains a near-optimal action, thereby enabling efficient learning without exhaustively evaluating all actions. This work extends our prior results for meta-bandits to the more general setting of Markov Decision Processes (MDPs). We prove that our existing algorithm achieves performance comparable to using the full action space. This theoretical guarantee is established under a relaxed, non-centered sub-Gaussian process model, which accommodates greater environmental heterogeneity. Consequently, our approach provides a computationally and sample-efficient solution for large-scale combinatorial decision-making under uncertainty.

cs.LG↗

arXiv2025

Explore and Establish Synergistic Effects Between Weight Pruning and Coreset Selection in Neural Network Training

Modern deep neural networks rely heavily on massive model weights and training samples, incurring substantial computational costs. Weight pruning and coreset selection are two emerging paradigms proposed to improve computational efficiency. In this paper, we first explore the interplay between redundant weights and training samples through a transparent analysis: redundant samples, particularly noisy ones, cause model weights to become unnecessarily overtuned to fit them, complicating the identification of irrelevant weights during pruning; conversely, irrelevant weights tend to overfit noisy data, undermining coreset selection effectiveness. To further investigate and harness this interplay in deep learning, we develop a Simultaneous Weight and Sample Tailoring mechanism (SWaST) that alternately performs weight pruning and coreset selection to establish a synergistic effect in training. During this investigation, we observe that when simultaneously removing a large number of weights and samples, a phenomenon we term critical double-loss can occur, where important weights and their supportive samples are mistakenly eliminated at the same time, leading to model instability and nearly irreversible degradation that cannot be recovered in subsequent training. Unlike classic machine learning models, this issue can arise in deep learning due to the lack of theoretical guarantees on the correctness of weight pruning and coreset selection, which explains why these paradigms are often developed independently. We mitigate this by integrating a state preservation mechanism into SWaST, enabling stable joint optimization. Extensive experiments reveal a strong synergy between pruning and coreset selection across varying prune rates and coreset sizes, delivering accuracy boosts of up to 17.83% alongside 10% to 90% FLOPs reductions.

cs.LG↗

arXiv2025

Polynomial Mixing Times of Simulated Tempering for Mixture Targets by Conductance Decomposition

We study the theoretical complexity of simulated tempering for sampling from mixtures of log-concave components differing only by location shifts. The main result establishes the first polynomial-time guarantee for simulated tempering combined with the Metropolis-adjusted Langevin algorithm (MALA) with respect to the problem dimension $d$, maximum mode displacement $D$, and logarithmic accuracy $\log ε^{-1}$. The proof builds on a general state decomposition theorem for $s$-conductance, applied to an auxiliary Markov chain constructed on an augmented space. We also obtain an improved complexity estimate for simulated tempering combined with random-walk Metropolis. Our bounds assume an inverse-temperature ladder with smallest value $β_1 = O(D^{-2})$ and spacing $β_{i+1}/β_i = 1 + O( d^{-1/2} )$, both of which are shown to be asymptotically optimal up to logarithmic factors.

stat.CO↗

arXiv2025

Bayesian Nonlinear PDE Inference via Gaussian Process Collocation with Application to the Richards Equation

The estimation of unknown parameters in nonlinear partial differential equations (PDEs) offers valuable insights across a wide range of scientific domains. In this work, we focus on estimating plant root parameters in the Richards equation, which is essential for understanding the soil-plant system in agricultural studies. Since conventional methods are computationally intensive and often yield unstable estimates, we develop a new Gaussian process collocation method for efficient Bayesian inference. Unlike existing Gaussian process-based approaches, our method constructs an approximate posterior distribution using samples drawn from a Gaussian process model fitted to the observed data, which does not require any structural assumption about the underlying PDE. Further, we propose to use an importance sampling procedure to correct for the discrepancy between the approximate and true posterior distributions. As an alternative, we also devise a prior-guided Bayesian optimization algorithm leveraging the approximate posterior. Simulation studies demonstrate that our method yields robust estimates under various settings. Finally, we apply our method on a real agricultural data set and estimate the plant root parameters with uncertainty quantification.

stat.ME↗

arXiv2025

Agora: Trust Less and Open More in Verification for Confidential Computing

Binary verification plays a pivotal role in software security, yet building a verification service that is both open and trustworthy poses a formidable challenge. In this paper, we introduce a novel binary verification service, AGORA, scrupulously designed to overcome the challenge. At the heart of this approach lies a strategic insight: certain tasks can be delegated to untrusted entities, while the corresponding validators are securely housed within the trusted computing base (TCB). AGORA can validate untrusted assertions generated for versatile policies. Through a novel blockchain-based bounty task manager, it also utilizes crowdsourcing to remove trust in theorem provers. These synergistic techniques successfully ameliorate the TCB size burden associated with two procedures: binary analysis and theorem proving. The design of AGORA allows untrusted parties to participate in these complex processes. Moreover, based on running the optimized TCB within trusted execution environments and recording the verification process on a blockchain, the public can audit the correctness of verification results. By implementing verification workflows for software-based fault isolation policy and side-channel mitigation, our evaluation demonstrates the efficacy of AGORA.

cs.CR↗

arXiv2025

ViTs: Teaching Machines to See Time Series Anomalies Like Human Experts

Web service administrators must ensure the stability of multiple systems by promptly detecting anomalies in Key Performance Indicators (KPIs). Achieving the goal of "train once, infer across scenarios" remains a fundamental challenge for time series anomaly detection models. Beyond improving zero-shot generalization, such models must also flexibly handle sequences of varying lengths during inference, ranging from one hour to one week, without retraining. Conventional approaches rely on sliding-window encoding and self-supervised learning, which restrict inference to fixed-length inputs. Large Language Models (LLMs) have demonstrated remarkable zero-shot capabilities across general domains. However, when applied to time series data, they face inherent limitations due to context length. To address this issue, we propose ViTs, a Vision-Language Model (VLM)-based framework that converts time series curves into visual representations. By rescaling time series images, temporal dependencies are preserved while maintaining a consistent input size, thereby enabling efficient processing of arbitrarily long sequences without context constraints. Training VLMs for this purpose introduces unique challenges, primarily due to the scarcity of aligned time series image-text data. To overcome this, we employ an evolutionary algorithm to automatically generate thousands of high-quality image-text pairs and design a three-stage training pipeline consisting of: (1) time series knowledge injection, (2) anomaly detection enhancement, and (3) anomaly reasoning refinement. Extensive experiments demonstrate that ViTs substantially enhance the ability of VLMs to understand and detect anomalies in time series data. All datasets and code will be publicly released at: https://anonymous.4open.science/r/ViTs-C484/.

cs.LG↗