arXiv subjects

Jue Hou

Publications and source records attributed to Jue Hou.

At least 19 recordsLinked to original sources

arXiv2026

Martingale R-learner: Estimating Time-varying Heterogeneous Treatment Effects for Time-to-event Outcomes

Biological research and clinical evidence suggest that treatment response may vary substantially along characteristics, such as comorbidities, genetic variants, environmental, or socio-economic factors. Future precision medicine requires accurate assessment of heterogeneous treatment effects (HTE) to guide optimal clinical decisions at the individual level. We introduce a functional score framework that extends the traditional estimating equations for survival data to nonparametric HTE and generalize the Neyman orthogonality accordingly, thus filling a methodological as well as theoretical gap. Under the Neyman orthogonal functional score framework, we developed the martingale R-learner based on a decomposition of the conditional martingale residuals into residuals of the risk-set propensity score and the marginal martingale, thereby reducing the impact of estimation bias in HTE from nuisance models including (1) marginal survival, and (2) risk-set propensity scores. This enables leveraging advances in machine learning and incorporates flexible estimators for the nuisance functions and attaining the standard optimal nonparametric estimation rate with the oracle property. Numerical experiments demonstrated empirical performance consistent with the theory. We applied the martingale R-learner to estimate the effect of alcohol on dementia using the Honolulu-Asia Aging Study data.

stat.ME↗

arXiv2026

Translation as Augmentation: Effect of Translated Data on Assessment of Difficulty

Reliable Text Difficulty Assessment is a prerequisite for valid text simplification workflows and personalized learning applications. However, the development of robust assessment models is severely hindered by a critical bottleneck: the scarcity of expert-annotated corpora containing fine-grained difficulty levels (e.g., CEFR), particularly for lower-resource languages. This paper addresses this data scarcity problem in the context of a low-resource European language. We propose a cross-lingual data augmentation strategy that leverages machine translation to transfer labeled resources from high-resource languages to the target low-resource language. We train BERT-based regression models to predict difficulty scores and investigate whether synthetic, translated data can effectively supplement native training sets. Our experiments demonstrate that augmenting scarce native data with machine-translated corpora significantly improves the accuracy of difficulty estimation, offering a viable solution for languages lacking extensive expert annotations.

cs.CL↗

arXiv2026

An Instrumental Variable Approach to Account for Informative Treatment Switching in Real-world Evidence

Reproducible and generalizable assessment of treatment decisions requires principled handling of subsequent treatment switching that may inform expected outcomes and shift across cohorts and over time. To effectively account for informative treatment switching, we propose an instrumental variable approach that characterizes the poorly documented expected outcomes at switching as unmeasured confounding. After establishing the baseline treatment as a viable instrumental variable, we constructed an estimating equation based on the association between the centered instrumental variable and a martingale style residual process that identifies the treatment effect under structural cumulative survival model. Our proposed method is doubly robust, i.e., valid whenever either of baseline propensity model or no-switching outcome model is consistently estimated. A co-training of treatment effect parameter and survival outcome regression model eliminated the requirement of observing a no-switching subset under semi-parametric additive hazards models. We further developed an baseline-survival-corrected cross-fitting approach to incorporate general machine learning models for estimating nuisance models. Numerical results demonstrated the validity of our method in various settings when a basket of benchmark solutions produced biased or contradictory results. We applied our method to comparison of high-efficacy vs standard efficacy disease modifying treatments as the second line therapy of multiple sclerosis.

stat.ME↗

arXiv2026

Exact Relevant Stress-Tensor Flows and a Causality No-Go in Self-Dual Electrodynamics

Can a classically relevant stress-tensor deformation be exactly solvable, duality preserving, and physically causal? We construct an exact power-law family of nonlinear electrodynamics preserving electromagnetic duality, together with a parallel two-dimensional Lax-integrable realization. Its auxiliary geometry yields the full characteristic-cone phase diagram and a universal finite-energy fold. For the Maxwell seed, every nonzero relevant branch is acausal, whereas every causal branch is caustic-free; undeformed Maxwell theory is the only causal point in the relevant regime.

hep-th↗

arXiv2026

The Triple $T\bar{T}$-Like Flow in Quantum Field Theories: Irrelevant, Marginal, and Relevant

We introduce a one-parameter root-$T\bar T$-like flow, $ \partial_\lambda \mathcal{L}=\mathcal{R}_\lambda^{1/\alpha}$, which organizes stress-tensor deformations into irrelevant, marginal, and relevant branches. Within duality-invariant electrodynamics in four dimensions, and equivalently within two-dimensional integrable sigma models, the flow admits a closed-form solution controlled by an auxiliary equation. The marginal point $\alpha=1$ reproduces the root-$T\bar T$ / ModMax branch, while $\alpha<1$ gives irrelevant deformations distinct from the standard Born-Infeld $T\bar T$ flow. For $\alpha>1$, the same construction yields explicit relevant $T\bar T$-like Lagrangians. These results suggest that root-$T\bar T$ flows provide a common organizing principle for duality-invariant and integrable deformations.

hep-th↗

arXiv2026

Beyond Hagedorn: A Harmonic Approach to $T\bar{T}$-deformation

We apply harmonic analysis to study the $T\bar{T}$-deformed torus partition function. We first express the CFT partition functions in terms of Maass waveforms, including the Eisenstein series and cusp forms. These basis functions turn out to deform in a very simple way under the $T\bar{T}$-deformation. The spectral decomposition provides a numerically stable and efficient method to compute the partition function at finite values of the deformation parameter $\lambda$, allowing us to clearly resolve the analytic structure of the partition function as a function of $\lambda$. The resulting deformed partition function exhibits a Hagedorn singularity. Building on harmonic analysis approach, we propose a natural analytic continuation beyond the Hagedorn singularity, which enables us to compute the full partition function for any value of $\lambda$.

hep-th↗

arXiv2026

Heterogeneous readmission prediction with hierarchical effect decomposition and regularization

Accurately predicting hospital readmission risks using electronic health records (EHRs) is critical for effective patient management and healthcare resource allocation. Patient populations in health systems are highly heterogeneous across different primary diagnoses, necessitating tailored yet interpretable prediction models. We propose a hierarchical modeling framework incorporating hierarchical nested re-parameterization and structured regularization methods, which we call hierNest. Specifically, our approach leverages the inherent hierarchical structure present in primary diagnoses and groupings of these diagnoses into major diagnostic categories. Our methodology facilitates information borrowing across related patient subgroups and preserves interpretability at different hierarchical levels. Simulation studies demonstrate superior predictive accuracy of the proposed method, particularly with small subgroup sample sizes and varying degrees of hierarchical effects. We apply our methods to a large EHR dataset comprising Medicare patients.

stat.ME↗

arXiv2026

AirNav: A Large-Scale UAV Vision-and-Language Navigation Dataset with Natural and Diverse Instructions

Existing UAV vision-and-language navigation (VLN) benchmarks rarely provide realistic aerial scenes, natural process-level instructions, and sufficient scale simultaneously, making it difficult to systematically train and evaluate UAV VLN agents under realistic settings. To address this, we propose \textbf{AirNav}, a large-scale benchmark built on real urban aerial data, comprising 137K navigation samples with natural and diverse instructions generated via a human--LLM collaborative pipeline with 10 user personas. We conduct a systematic evaluation of representative approaches on AirNav, ranging from traditional models to multimodal large language models (MLLMs), under unified metrics with open-source implementations. We further propose \textbf{AirVLN-R1}, trained via supervised fine-tuning (SFT) and reinforcement fine-tuning (RFT), achieving state-of-the-art performance with a 51.82\% success rate on the test-unseen split. Real-world experiments on a physical UAV platform provide preliminary evidence of sim-to-real transferability, and our dataset and code are publicly available.

cs.CL↗

arXiv2025

62.6 GHz ScAlN Solidly Mounted Acoustic Resonators

We demonstrate a record-high 62.6 GHz solidly mounted acoustic resonator (SMR) incorporating a 67.6 nm scandium aluminum nitride (Sc0.3Al0.7N) piezoelectric layer on a 40 nm buried platinum (Pt) bottom electrode, positioned above an acoustic Bragg reflector composed of alternating SiO2 (28.2 nm) and Ta2O5 (24.3 nm) layers in 8.5 pairs. The Bragg reflector and piezoelectric stack above are designed to confine a third-order thickness-extensional (TE) bulk acoustic wave (BAW) mode, while efficiently transducing with thickness-field excitation. The fabricated SMR exhibits an extracted piezoelectric coupling coefficient (k2) of 0.8% and a maximum Bode quality factor (Q) of 51 at 63 GHz, representing the highest operating frequency reported for an SMR to date. These results establish a pathway toward mmWave SMR devices for filters and resonators in next-generation RF front ends.

eess.SP↗

arXiv2025

Reasoning-Enhanced Large Language Models for Molecular Property Prediction

Molecular property prediction is crucial for drug discovery and materials science, yet existing approaches suffer from limited interpretability, poor cross-task generalization, and lack of chemical reasoning capabilities. Traditional machine learning models struggle with task transferability, while specialized molecular language models provide little insight into their decision-making processes. To address these limitations, we propose \textbf{MPPReasoner}, a multimodal large language model that incorporates chemical reasoning for molecular property prediction. Our approach, built upon Qwen2.5-VL-7B-Instruct, integrates molecular images with SMILES strings to enable comprehensive molecular understanding. We develop a two-stage training strategy: supervised fine-tuning (SFT) using 16,000 high-quality reasoning trajectories generated through expert knowledge and multiple teacher models, followed by Reinforcement Learning from Principle-Guided Rewards (RLPGR). RLPGR employs verifiable, rule-based rewards that systematically evaluate chemical principle application, molecular structure analysis, and logical consistency through computational verification. Extensive experiments across 8 datasets demonstrate significant performance improvements, with MPPReasoner outperforming the best baselines by 7.91\% and 4.53\% on in-distribution and out-of-distribution tasks respectively. MPPReasoner exhibits exceptional cross-task generalization and generates chemically sound reasoning paths that provide valuable insights into molecular property analysis, substantially enhancing both interpretability and practical utility for chemists. Code is available at https://anonymous.4open.science/r/MPPReasoner-12687.

cs.LG↗

arXiv2025

Doc2SAR: A Synergistic Framework for High-Fidelity Extraction of Structure-Activity Relationships from Scientific Documents

Extracting molecular structure-activity relationships (SARs) from scientific literature and patents is essential for drug discovery and materials research. However, this task remains challenging due to heterogeneous document formats and limitations of existing methods. Specifically, rule-based approaches relying on rigid templates fail to generalize across diverse document layouts, while general-purpose multimodal large language models (MLLMs) lack sufficient accuracy and reliability for specialized tasks, such as layout detection and optical chemical structure recognition (OCSR). To address these challenges, we introduce DocSAR-200, a rigorously annotated benchmark of 200 scientific documents designed specifically for evaluating SAR extraction methods. Additionally, we propose Doc2SAR, a novel synergistic framework that integrates domain-specific tools with MLLMs enhanced via supervised fine-tuning (SFT). Extensive experiments demonstrate that Doc2SAR achieves state-of-the-art performance across various document types, significantly outperforming leading end-to-end baselines. Specifically, Doc2SAR attains an overall Table Recall of 80.78% on DocSAR-200, exceeding end2end GPT-4o by 51.48%. Furthermore, Doc2SAR demonstrates practical usability through efficient inference and is accompanied by a web app.

cs.CL↗

arXiv2025

MM-R5: MultiModal Reasoning-Enhanced ReRanker via Reinforcement Learning for Document Retrieval

Multimodal document retrieval systems enable information access across text, images, and layouts, benefiting various domains like document-based question answering, report analysis, and interactive content summarization. Rerankers improve retrieval precision by reordering retrieved candidates. However, current multimodal reranking methods remain underexplored, with significant room for improvement in both training strategies and overall effectiveness. Moreover, the lack of explicit reasoning makes it difficult to analyze and optimize these methods further. In this paper, We propose MM-R5, a MultiModal Reasoning-Enhanced ReRanker via Reinforcement Learning for Document Retrieval, aiming to provide a more effective and reliable solution for multimodal reranking tasks. MM-R5 is trained in two stages: supervised fine-tuning (SFT) and reinforcement learning (RL). In the SFT stage, we focus on improving instruction-following and guiding the model to generate complete and high-quality reasoning chains. To support this, we introduce a novel data construction strategy that produces rich, high-quality reasoning data. In the RL stage, we design a task-specific reward framework, including a reranking reward tailored for multimodal candidates and a composite template-based reward to further refine reasoning quality. We conduct extensive experiments on MMDocIR, a challenging public benchmark spanning multiple domains. MM-R5 achieves state-of-the-art performance on most metrics and delivers comparable results to much larger models on the remaining ones. Moreover, compared to the best retrieval-only method, MM-R5 improves recall@1 by over 4%. These results validate the effectiveness of our reasoning-enhanced training pipeline. Our code is available at https://github.com/i2vec/MM-R5 .

cs.AI↗

arXiv2025

Self-Dual Electrodynamics via the Characteristic Method: Relativistic and Carrollian Perspectives

Electric-magnetic duality plays a pivotal role in understanding the structure of nonlinear electrodynamics (NED). The Gaillard-Zumino (GZ) criterion provides a powerful constraint for identifying self-dual theories. In this work, we systematically explore solutions to the GZ self-duality condition by applying the method of characteristics, a robust tool for solving nonlinear partial differential equations. Our approach enables the construction of new classes of Lagrangians that respect duality symmetry, both in the relativistic and Carrollian frameworks. In the relativistic setting, we not only recover well-known examples such as Born-Infeld and ModMax theories, but also identify novel models. We then generalize the GZ formalism to the Carrollian case and construct several classes of Carrollian self-dual non-linear electrodynamic models. Remarkably, we demonstrate that the characteristic flow exhibits an attractor behavior, in the sense that different seed theories that may not be self-dual can generate the same descendant self-dual Lagrangian. These findings broaden the landscape of self-dual theories and open new directions for exploring duality in ultra-relativistic regimes.

hep-th↗

arXiv2025

Generalized Linear Markov Decision Process

Offline reinforcement learning for longitudinal studies often faces two linked challenges: rewards may be binary or bounded, and reward observations may be available only for a subset of trajectories or time points even when the corresponding state-action-next-state histories are available. Linear Markov decision process methods are tractable because Bellman backups remain linear, but they require linear rewards and do not indicate how transition-only observations should be used. We introduce GRASP-MDP, Generalized Reward And Semi-supervised Pessimism for Markov Decision Processes, a reward-transition separated framework addressing both issues through one Bellman decomposition. It preserves linear transition dynamics while modeling reward means through generalized linear models. Although this breaks the usual linear Bellman form, the backup remains explicit as a nonlinear reward component plus a linear continuation component, yielding a nonlinear-plus-linear Bellman-complete class. In the resulting recursion, observed rewards estimate the generalized reward component, while all available transitions estimate the continuation component. The resulting pessimistic value iteration controls the two estimation errors separately without reward imputation. Finite-sample guarantees show that transition-only observations reduce transition-estimation error while reward uncertainty remains governed by observed rewards. Simulations and a multiple sclerosis electronic health record application illustrate the empirical benefit of retaining transition-only observations.

stat.ML↗

arXiv2025

DrKGC: Dynamic Subgraph Retrieval-Augmented LLMs for Knowledge Graph Completion across General and Biomedical Domains

Knowledge graph completion (KGC) aims to predict missing triples in knowledge graphs (KGs) by leveraging existing triples and textual information. Recently, generative large language models (LLMs) have been increasingly employed for graph tasks. However, current approaches typically encode graph context in textual form, which fails to fully exploit the potential of LLMs for perceiving and reasoning about graph structures. To address this limitation, we propose DrKGC (Dynamic Subgraph Retrieval-Augmented LLMs for Knowledge Graph Completion). DrKGC employs a flexible lightweight model training strategy to learn structural embeddings and logical rules within the KG. It then leverages a novel bottom-up graph retrieval method to extract a subgraph for each query guided by the learned rules. Finally, a graph convolutional network (GCN) adapter uses the retrieved subgraph to enhance the structural embeddings, which are then integrated into the prompt for effective LLM fine-tuning. Experimental results on two general domain benchmark datasets and two biomedical datasets demonstrate the superior performance of DrKGC. Furthermore, a realistic case study in the biomedical domain highlights its interpretability and practical utility.

cs.AI↗

arXiv2025

Spin-$s$ $Q$-systems: Twist and Open Boundaries

In integrable spin chains, the spectral problem can be solved by the method of Bethe ansatz, which transforms the problem of diagonalization of the Hamiltonian into the problem of solving a set of algebraic equations named Bethe equations. In this work, we systematically investigate the spin-$s$ XXX chain with twisted and open boundary conditions using the rational $Q$-system, which is a powerful tool to solve Bethe equations. We establish basic frameworks of the rational $Q$-system and confirm its completeness numerically in both cases. For twisted boundaries, we investigate the polynomiality conditions of the rational $Q$-system and derive physical conditions for singular solutions of Bethe equations. For open boundaries, we uncover novel phenomena such as hidden symmetries and magnetic strings under specific boundary parameters. Hidden symmetries lead to the appearance of extra degeneracies in the Hilbert space, while the magnetic string is a novel type of exact string configuration, whose length depends on the boundary magnetic fields. These findings, supported by both analytical and numerical evidences, offer new insights into the interplay between symmetries and boundary conditions.

hep-th↗

arXiv2024

${T\overline{T}}$-like Flows of Yang-Mills Theories

We study ${T\overline{T}}$-like deformations of $d>2$ Yang-Mills theories. The standard ${T\overline{T}}$ flows lead to multi-trace Lagrangians, and the non-Abelian gauge structures make it challenging to find Lagrangians in a closed form. However, within the geometric approach to ${T\overline{T}}$, we obtain the closed-form solution to the metric flow and stress-energy tensor, and show that instanton solutions are undeformed. We also introduce new symmetrised single-trace ${T\overline{T}}$-like deformations, whose solutions in $d=4$ include the non-Abelian Born-Infeld Lagrangian proposed by Tseytlin in 1997.

hep-th↗

arXiv2024

Implicit assessment of language learning during practice as accurate as explicit testing

Assessment of proficiency of the learner is an essential part of Intelligent Tutoring Systems (ITS). We use Item Response Theory (IRT) in computer-aided language learning for assessment of student ability in two contexts: in test sessions, and in exercises during practice sessions. Exhaustive testing across a wide range of skills can provide a detailed picture of proficiency, but may be undesirable for a number of reasons. Therefore, we first aim to replace exhaustive tests with efficient but accurate adaptive tests. We use learner data collected from exhaustive tests under imperfect conditions, to train an IRT model to guide adaptive tests. Simulations and experiments with real learner data confirm that this approach is efficient and accurate. Second, we explore whether we can accurately estimate learner ability directly from the context of practice with exercises, without testing. We transform learner data collected from exercise sessions into a form that can be used for IRT modeling. This is done by linking the exercises to {\em linguistic constructs}; the constructs are then treated as "items" within IRT. We present results from large-scale studies with thousands of learners. Using teacher assessments of student ability as "ground truth," we compare the estimates obtained from tests vs. those from exercises. The experiments confirm that the IRT models can produce accurate ability estimation based on exercises.

cs.AI↗