Selected work

Representative Papers

Brain-to-Text Decoding: A Non-invasive Approach via Typing

Feb 18, 2025

This study addresses the need for non-invasive neural decoding in individuals with aphasia or motor impairments. We propose a novel sentence-level brain signal decoding paradigm—“covert rehearsal–tapping”—and introduce Brain2Qwerty, an end-to-end deep learning architecture that jointly processes MEG and EEG signals to directly predict character sequences. Our contributions are threefold: (1) we establish the first non-invasive sentence decoding paradigm anchored on typing behavior; (2) we demonstrate that decoding performance is synergistically driven by both motor execution and high-level language cognition; and (3) we infer underlying cognitive mechanisms via systematic error pattern analysis. Evaluation on healthy participants shows a mean character error rate (CER) of 32% for MEG (best individual: 19%), substantially outperforming EEG (67% CER) and significantly narrowing the performance gap with invasive approaches.

1 citations1 influentialRead paper

Propensity Straight-Through Gradients for Discrete Stochastic Systems

Aug 26, 2026

研究解决了连续时间马尔可夫链与梯度机器学习结合的问题，通过区分归一化反应倾向性来获得精确一步条件均值敏感性，定义了倾向直通估计器。

0 citationsRead paper

Learning in Markovian bandits with non-observable states and constrained decision epochs

Jun 25, 2026

This study addresses the Markovian multi-armed bandit problem under partial observability and decision-time constraints by investigating a class of self-restarting models. It establishes, for the first time in the absence of state observations, a regret bound independent of the number of states and proves the asymptotic optimality of optimal pure strategies. The authors propose UCB-NOM, an optimistic principle-based algorithm that achieves a near-logarithmic expected regret bound of ω(log T) without prior knowledge, and attains O(log T) expected regret alongside O(√(T log T)) worst-case regret when a prior bound on the bias function is available. This work demonstrates that even when strict logarithmic regret is unattainable, effective approximation remains possible, offering a novel analytical framework for Markov bandits with unobservable states.

0 citationsRead paper

Bayesian Variable Selection in Generalized Linear Models

Jun 23, 2026

This work proposes the first fully Bayesian hierarchical approach for covariate selection in generalized linear models that simultaneously achieves full conjugacy, posterior consistency, and broad applicability across exponential family distributions. By introducing binary inclusion indicators to explicitly model whether each covariate enters the linear predictor, the method unifies variable selection and parameter estimation within a single coherent framework, effectively accounting for model uncertainty. Built upon conjugate priors, the approach enables efficient Gibbs sampling and is accompanied by an R package for practical implementation. Theoretical analysis establishes posterior consistency for both the inclusion indicators and the active regression coefficients. Extensive experiments on synthetic and real-world datasets demonstrate superior performance in terms of predictive accuracy and statistical inference.

0 citationsRead paper

ProvenanceGuard: Source-Aware Factuality Verification for MCP-Based LLM Agents

Jun 16, 2026

This work addresses the problem of cross-source confusion in large language model agents under the Model-Context-Prompt (MCP) architecture, where factual errors in responses are incorrectly attributed to irrelevant evidence sources. The paper introduces the first source-aware factuality verification framework, which parses MCP execution traces to decompose responses into atomic claims, routes each claim to its corresponding evidence source, and evaluates claim support through natural language inference and token alignment. Crucially, it compares the claimed source against the actual evidence source, enabling per-claim and holistic allow/block decisions. By treating source attribution as an independent dimension of factuality, the framework supports detection of misattribution and enables an automated retrieval-augmented repair loop. Evaluated on 281 medical MCP trajectories, it achieves a held-out blocking F1 of 0.802 and source accuracy of 0.858; in multi-source settings, blocking F1 improves to 0.846, with 100% detection and correction of injected attribution manipulations.

0 citationsRead paper

Recent publications

Latest Papers

Propensity Straight-Through Gradients for Discrete Stochastic Systems

Aug 26, 2026

研究解决了连续时间马尔可夫链与梯度机器学习结合的问题，通过区分归一化反应倾向性来获得精确一步条件均值敏感性，定义了倾向直通估计器。

0 citationsRead paper

Learning in Markovian bandits with non-observable states and constrained decision epochs

Jun 25, 2026

This study addresses the Markovian multi-armed bandit problem under partial observability and decision-time constraints by investigating a class of self-restarting models. It establishes, for the first time in the absence of state observations, a regret bound independent of the number of states and proves the asymptotic optimality of optimal pure strategies. The authors propose UCB-NOM, an optimistic principle-based algorithm that achieves a near-logarithmic expected regret bound of ω(log T) without prior knowledge, and attains O(log T) expected regret alongside O(√(T log T)) worst-case regret when a prior bound on the bias function is available. This work demonstrates that even when strict logarithmic regret is unattainable, effective approximation remains possible, offering a novel analytical framework for Markov bandits with unobservable states.

0 citationsRead paper

Bayesian Variable Selection in Generalized Linear Models

Jun 23, 2026

This work proposes the first fully Bayesian hierarchical approach for covariate selection in generalized linear models that simultaneously achieves full conjugacy, posterior consistency, and broad applicability across exponential family distributions. By introducing binary inclusion indicators to explicitly model whether each covariate enters the linear predictor, the method unifies variable selection and parameter estimation within a single coherent framework, effectively accounting for model uncertainty. Built upon conjugate priors, the approach enables efficient Gibbs sampling and is accompanied by an R package for practical implementation. Theoretical analysis establishes posterior consistency for both the inclusion indicators and the active regression coefficients. Extensive experiments on synthetic and real-world datasets demonstrate superior performance in terms of predictive accuracy and statistical inference.

0 citationsRead paper

ProvenanceGuard: Source-Aware Factuality Verification for MCP-Based LLM Agents

Jun 16, 2026

This work addresses the problem of cross-source confusion in large language model agents under the Model-Context-Prompt (MCP) architecture, where factual errors in responses are incorrectly attributed to irrelevant evidence sources. The paper introduces the first source-aware factuality verification framework, which parses MCP execution traces to decompose responses into atomic claims, routes each claim to its corresponding evidence source, and evaluates claim support through natural language inference and token alignment. Crucially, it compares the claimed source against the actual evidence source, enabling per-claim and holistic allow/block decisions. By treating source attribution as an independent dimension of factuality, the framework supports detection of misattribution and enables an automated retrieval-augmented repair loop. Evaluated on 281 medical MCP trajectories, it achieves a held-out blocking F1 of 0.802 and source accuracy of 0.858; in multi-source settings, blocking F1 improves to 0.846, with 100% detection and correction of injected attribution manipulations.

0 citationsRead paper

Deep Slice Interpolation for Reducing Through-Plane Anisotropy and Noise in Head CT

Jun 08, 2026

This study addresses the significant anisotropy in non-contrast head CT scans caused by large inter-slice spacing (2–5 mm), which adversely affects multiplanar reconstruction, hematoma volume estimation, and downstream algorithm performance. The authors propose the first deep slice interpolation approach tailored for head CT, leveraging a neural network to synthesize intermediate axial slices from neighboring ones, thereby simultaneously mitigating anisotropy and noise in a single inference pass. Through systematic evaluation of various loss function combinations, they identify MS-SSIM+L1 as optimal and uncover training instabilities associated with SSIM-based losses along with effective mitigation strategies. Experiments demonstrate that the proposed method substantially outperforms conventional interpolation techniques and state-of-the-art video frame interpolation models—such as RIFE and FILM—on both internal test sets and external datasets, while also enhancing 3D visualization quality and achieving implicit denoising.

0 citationsRead paper