Searcharxiv⌕ Search

arXiv subjects

Shu Yang

Publications and source records attributed to Shu Yang.

At least 37 records · Page 2Linked to original sources

A Spectral Confounder Adjustment for Spatial Regression with Multiple Exposures and Outcomes

Characterizing social vulnerability is fundamental to disaster response planning. Numerous vulnerability indicators have been developed, but they are typically not validated for their predictive power over the outcomes of interest. As with many environmental health studies where interventions are impractical or unethical, validation of social vulnerability against public health outcomes is observational and relies on spatially-dependent data. Observational studies are susceptible to bias induced by unmeasured confounders. This problem is exacerbated in spatial studies with multiple health outcomes and environmental exposure variables, as the source and magnitude of confounding bias may differ by spatial scale and across exposure/outcome pairs. We propose to mitigate confounding effects in multivariate spatial studies using a tensor-regression model that allows exposure effects to vary by exposure, outcome, and spatial scale. By extracting exposure effects that correspond to local spatial scales, we replace the strict causal assumption of no unmeasured confounders with a more realistic assumption of local unconfoundedness i.e., differences between nearby regions are unconfounded, allowing for causal interpretation. Our study of the Southern United States shows that economic resilience (Theme 1) demonstrates the strongest positive effect on diabetes and negative effect on hyperlipidemia. Our analysis reveals a concise representation of the effects of social vulnerability indices on an array of chronic health outcomes, offering interpretable epidemiological insights that adjust for multivariate spatial confounding.

stat.ME↗

Power and Sample Size Calculations for Hybrid Controlled Trials

Hybrid controlled trials (HCTs) augment randomized controls with external controls (ECs) to address practical challenges in randomized controlled trials (RCTs) and improve statistical power in settings such as rare diseases, oncology, and pediatrics. However, prospective sample-size determination is challenging because the required RCT sample size depends on the comparability of ECs with RCT controls, which are unavailable at the planning stage. We propose a 5+3 design for HCT sample-size determination based on an inverse probability weighting estimator of the average treatment effect. The framework uses five conventional RCT design parameters and three additional scalar parameters characterizing EC comparability: the number of outcome-drift-free ECs, an overlap coefficient for the covariate distributions of the RCT and ECs, and a correlation coefficient linking the sampling mechanism to the control potential outcome. We establish the asymptotic distribution of the estimator and prove that its variance is determined by these design parameters under the proposed working models, yielding sample-size calculations for both continuous and binary outcomes. Simulation studies evaluate finite-sample performance, and a real clinical application illustrates its practical use. The method is implemented in the hctdesign R package.

stat.ME↗

Mitigating Reasoning-Induced Misalignment via Safety-Direction Penalty

Reasoning-Induced Misalignment, where fine-tuning on reasoning data containing no harmful content, including mathematics, code, and problem-solving with chain-of-thought traces can induce harmful behaviors of LLM, posing a serious challenge to the safety of LLM reasoning. Cross-architecture, cross-scale, and cross-dataset checks show that RIM does not always emerge. Previous work attributed RIM to neuron-level entanglement, but did not identify the geometry of the representation space underlying this entanglement or propose a training-time fix. We provide both: a representation-space analysis of RIM and the Safety-Direction Penalty (SDP), which penalizes movement along a learned safety direction during reasoning fine-tuning. The analysis extracts two activation-space directions, one encoding reasoning ability and the other safety behavior. These directions are coupled: fine-tuning that improves reasoning shifts safety representations, and prompts with larger shifts show larger safety degradation. CKA distance ratios and probes locate the safety-decision layers where this shift is most relevant. These findings guide the design of SDP: the coupling motivates penalizing displacement along the safety direction, and the layer localization sets the initial scope. When the initial scope leaves compensatory shifts beyond the penalized layers, the same diagnostics guide iterative expansion. On Qwen2.5-3B and 7B, SDP restores safety while preserving benchmark reasoning performance.

cs.AI↗

SED-FOD: Scattering-Aware Expert Decomposition for Few-Shot Cross-Sensor SAR Object Detection

Synthetic aperture radar (SAR) object detection is an important part of remote sensing interpretation. However, because of variations in frequency band, resolution, background clutter, and target scattering responses, the performance of existing detectors often degrades when training and testing data are acquired from different SAR domains. Although domain adaptation methods offer a promising paradigm for solving this problem, most of them mainly pursue domain-invariant feature alignment and suppress sensor-dependent scattering characteristics that are useful for object detection. This problem becomes more challenging in few-shot scenarios, where only a few fully annotated target-domain SAR images are available. To address this issue, we propose a scattering-aware shared-specific feature decomposition framework for few-shot SAR domain adaptation object detection. We decompose detection features into a shared path and several soft-gated scattering-specific expert paths. The shared path learns transferable object structural information and is used for asymmetric domain alignment, while the scattering-specific experts adaptively compensate heterogeneous SAR responses. In addition, routing-domain auxiliary loss is introduced to encourage specific experts to capture sensor-dependent routing preferences, and an expert balancing loss is used to prevent routing collapse. Extensive experiments on four bidirectional heterogeneous SAR detection tasks between FARAD-X/FARAD-Ka and MiniSAR under different few-shot settings have been conducted and experimental results demonstrate that the proposed method achieves superior performance in both forward and reverse adaptation directions.

cs.CV↗

A Versatile Foundation Model for AI-enabled Mammogram Interpretation

Breast cancer is the most commonly diagnosed cancer and the leading cause of cancer-related mortality in women globally. Mammography is essential for the early detection and diagnosis of breast lesions. Despite recent progress in foundation models (FMs) for mammogram analysis, their clinical translation remains constrained by several fundamental limitations, including insufficient diversity in training data, limited model generalizability, and a lack of comprehensive evaluation across clinically relevant tasks. Here, we introduce VersaMammo, a versatile foundation model for mammograms, designed to overcome these limitations. We curated the largest multi-institutional mammogram dataset to date, comprising 706,239 images from 21 sources. To improve generalization, we propose a two-stage pre-training strategy to develop VersaMammo, a mammogram foundation model. First, a teacher model is trained via self-supervised learning to extract transferable features from unlabeled mammograms. Then, supervised learning combined with knowledge distillation transfers both features and clinical knowledge into VersaMammo. To ensure a comprehensive evaluation, we established a benchmark comprising 92 specific tasks, including 68 internal tasks and 24 external validation tasks, spanning 5 major clinical task categories: lesion detection, segmentation, classification, image retrieval, and visual question answering. VersaMammo achieves state-of-the-art performance, ranking first in 50 out of 68 specific internal tasks and 20 out of 24 external validation tasks, with average ranks of 1.5 and 1.2, respectively. These results demonstrate its superior generalization and clinical utility, offering a substantial advancement toward reliable and scalable breast cancer screening and diagnosis.

cs.CV↗

Integrating RCTs, RWD, AI/ML and Statistics: Next-Generation Evidence Synthesis

Randomized controlled trials (RCTs)have been the cornerstone of clinical evidence; however, their cost, duration, and restrictive eligibility criteria limit power and external validity. Studies using real-world data (RWD), historically considered less reliable for establishing causality, are now recognized as an important source of real-world evidence (RWE). In parallel, artificial intelligence and machine learning (AI/ML) are increasingly used throughout the drug development process, providing scalability and flexibility but also presenting challenges in interpretability and statistical rigor. This Perspective argues that the future of evidence generation will not depend on RCTs versus RWD, or statistics versus AI/ML, but on their principled integration under a statistical evidence framework that clarifies estimands, evaluates data fitness, controls bias, quantifies uncertainty, and determines when evidence is strong enough to support decisions. Building on the Causal Roadmap for high-quality real-world evidence, we present a six-step statistical roadmap for integrative evidence synthesis and organize the discussion around five core questions that statisticians must confront: when RWD is fit for causal use and when it is not; what AI genuinely contributes across the evidence lifecycle; what remains distinctly statistical and indispensable; how to build trustworthy end-to-end evidence systems in pharmaceutical, regulatory, and industry settings; and how statistical training should evolve.

stat.ME↗

AISPA: User-Centric System Prompt Auditing for Large Language Model Applications

System prompts are instructions configured by developers to govern the behaviors of foundation models in AI applications. They are used throughout commercial AI products, but are rarely disclosed to the public or regulators, creating a serious trust and accountability gap in the wide deployment of AI systems. In this paper, we introduce Artificial Intelligence System Prompt Assurance (AISPA), a user-centric framework for systematically auditing system prompts in AI systems. AISPA examines specific parts of a system prompt and evaluates them along eight dimensions that matter to users. We then use this framework to review 3,249 instructions from system prompts in 88 commercial AI products, classifying each instruction as either protective (of users) or problematic. Our audit surfaces four core findings. First, system prompt design varies substantially across products and developers, with some organizations averaging over 60 protective instructions per product while others average fewer than 5. Second, protective instructions are widely adopted but shallow in scope: 98.9% of products contain at least one, yet only 24% cover all eight dimensions of the AISPA taxonomy. Third, system prompts have grown steadily longer and more protective of users, suggesting that user protection is becoming a more visible concern in commercial prompt design. Fourth, despite this progress, problematic instructions remain pervasive: roughly 40% of products contain at least one instruction that works against user interests, and protective and problematic instructions frequently coexist within the same prompt. Our findings highlight the need for greater transparency, standardization, and independent oversight for system prompts in commercial AI products.

cs.AI↗

Word Recovery in Large Language Models Enables Character-Level Tokenization Robustness

Large language models (LLMs) trained with canonical tokenization exhibit surprising robustness to non-canonical inputs such as character-level tokenization, yet the mechanisms underlying this robustness remain unclear. We study this phenomenon through mechanistic interpretability and identify a core process we term word recovery. We first introduce a decoding-based method to detect word recovery, showing that hidden states reconstruct canonical word-level token identities from character-level inputs. We then provide causal evidence by removing the corresponding subspace from hidden states, which consistently degrades downstream task performance. Finally, we conduct a fine-grained attention analysis and show that in-group attention among characters belonging to the same canonical token is critical for word recovery: masking such attention in early layers substantially reduces both recovery scores and task performance. Together, our findings provide a mechanistic explanation for tokenization robustness and identify word recovery as a key mechanism enabling LLMs to process character-level inputs.

cs.CL↗

Humanly: A Configurable and Traceable Environment for Human-AI Collaborative Writing

Teachers, conference chairs, and public readers all judge writing from limited evidence, seeing only a finished document and not the process that produced it. Final text alone cannot reveal whether a document was produced through human typing, AI generation, or mixed human-AI collaboration. Existing process-tracking tools help, but many are tied to host-document histories, provide coarse activity records, and offer limited control over the writing environment. Humanly is a writing platform that makes the writing process itself the evidence. Users configure writing environments for personal documents or assigned tasks and draft in a workspace that records writing activity and in-platform AI assistance. Humanly can package a completed session into a sealed writing certificate with configuration-aware anomaly behavior review. It can support writing scenarios such as course assignments, peer review, and personal certification. Our user study shows that Humanly is helpful across roles, and a red-teaming study shows that the Humanly Typing Detector distinguishes human hand typing from automated typing.

cs.CL↗

SelfMem: Self-Optimizing Memory for AI Agents

While current AI agents support increasingly long context windows, tool use, and skill execution for long-horizon tasks, they still require memory systems to effectively leverage historical experience. Existing memory frameworks typically rely on fixed storage, retrieval, and summarization mechanisms, which can be rigid across different tasks and often require manual tuning. To address this limitation, we propose SelfMem, a self-optimizing memory framework. Inspired by prior work on self-improving AI, we follow the principle of "teaching an agent to fish rather than giving it a fish." Instead of forcing the model to follow a predefined memory strategy or format, SelfMem provides an environment with memory tools and feedback signals that allow the agent to explore, evaluate, and refine its own memory strategy. Our results show that SelfMem consistently outperforms retrieval, compression, and agent-memory baselines on BEAM across conversation scales from 100K to 1M tokens. Compared with the strongest baseline, SelfMem improves the official score by 48.7%, 40.8%, and 41.9% at 100K, 500K, and 1M, respectively. Further question-type analysis shows broad robustness across diverse memory demands, and our optimization study shows that model-guided strategy refinement further improves performance.

cs.CL↗

ProACT: Towards Breakdown-Aware Proactive Agent in Multi-User Collaboration

Conversational agents are increasingly embedded in human collaborative work, yet they remain fundamentally passive and reactive: they respond to explicit user requests rather than proactively recognizing moments when a team would benefit from timely intervention as human collaborators often do. This reactive design substantially limits the use of agents as active participants in multi-user collaboration, where disagreements, ambiguous goals, forgotten constraints, underspecified plans, discussion loops, and imbalanced participation can gradually undermine group progress. To move agents from passive assistants toward active participants in multi-user collaboration, we introduce ProACT, a breakdown-aware agent framework grounded in theories of common ground, collaborative planning, and coordination work. ProACT observes the speaker-attributed conversation history, determines whether the current turn contains a collaboration breakdown requiring intervention, decides whether the agent should stay silent or speak, and, when speaking is needed, routes the case to a targeted collaboration skill. We further introduce the first multi-user collaboration benchmark for evaluating proactive agents across project planning, product design, research collaboration, logistics, education, and resource-constrained decision making. Across 3,244 turn-level examples and five LLM backbones, ProACT consistently improves collaborative appropriateness, non-interruptiveness, conciseness, and judged intervention quality over direct chat.

cs.CL↗

Robust Estimation and Inference with Selective Borrowing in Hybrid Controlled Trials: A Tutorial with SelectiveIntegrative and intFRT

Hybrid controlled trials (HCTs) augment randomized controlled trials (RCTs) with external controls (ECs) to improve statistical efficiency when RCTs face limited sample sizes, slow accrual, or ethical constraints. However, valid use of ECs requires careful adjustment for covariate shift and outcome drift, as inappropriate borrowing may introduce bias and compromise inference. This tutorial provides a practical workflow for estimation and inference in HCTs. We first present a statistical analysis roadmap covering estimands, identification assumptions, eligibility alignment, matching, full and selective borrowing strategies, and both asymptotic inference and randomization tests. We then demonstrate step-by-step implementation using the SelectiveIntegrative and intFRT packages. The workflow is illustrated using a synthetic lung cancer dataset included in the intFRT package that mimics the CALGB 9633 trial and ECs from the National Cancer Database. The tutorial aims to help applied statisticians conduct transparent, interpretable, and reproducible HCT analyses that improve efficiency while maintaining valid inference.

stat.ME↗

Pinch-off dynamics for a Newtonian liquid thread draining in a viscoplastic medium

The pinch-off dynamics of a Newtonian liquid thread embedded in a viscoplastic medium is investigated using direct numerical simulations and theory. Thread breakup occurs below a nearly universal threshold set by the balance of capillary and yield stresses, largely independent of the viscosity ratio at low Ohnesorge numbers. Regime maps in the Ohnesorge-plastocapillary number plane reveal distinct boundaries, and scaling analysis captures the minimum thread radius in excellent agreement with simulations. These results provide a predictive framework for thread dynamics in complex fluids and highlight the role of stress localization in viscoplastic environments. The obtained insights are relevant for embedded additive manufacturing and other technologies involving fluid threads in complex media.

physics.flu-dyn↗

Observation of Non-Hermitian Skin Dynamics in the Liouvillian Regime

Open quantum systems generally do not perfectly preserve phase coherence: coupling to uncontrolled environments requires a density-matrix description based on the Liouvillian framework beyond pure-state wave evolution. Realizing and probing such dynamics in a programmable platform is therefore essential for connecting coherent physics to realistic dissipative settings. Here we implement a tunable open-system quantum walk in a photonic mesh lattice, where controlled phase noise produces adjustable dephasing and non-reciprocal gain-loss imbalance provides an independently tunable non-Hermitian drive. This allows us to continuously interpolate between coherent quantum walks and incoherent classical walks, and to observe how directional transport evolves in the Liouvillian regime. Using non-Hermitian skin dynamics as a probe, we measure the center-of-mass drift over both the coherence and non-Hermiticity parameters, revealing a crossover from coherence-enhanced to decoherence-enhanced transport in quantitative agreement with quantum-channel simulations. We further program spatial and temporal interfaces to demonstrate interface accumulation and a long-time drift governed by the instantaneous channel. Our results establish a controllable photonic platform for simulating open quantum dynamics and show that decoherence can actively reshape non-Hermitian transport.

physics.optics↗

iLENS: Interpretable LLM-Guided Mixture-of-Experts for Neuroimaging Survival Analysis

Alzheimer's Disease (AD) is a complex neurodegenerative disorder that continues to impact millions of people worldwide. Predicting AD conversion during the prodromal stage remains critical for disease understanding and patient care. As such, survival models are widely used for AD risk prediction, yet they are typically static predictors with limited interpretability and no capacity for natural language reasoning. In this work, we propose iLENS, an interpretable large language model (LLM) guided framework based on mixture-of-experts (MoE) for survival prediction in AD conversion. Our approach uses LLM to synthesize structured neuroimaging measurements and unstructured information to guide expert routing. Our framework demonstrates competitive predictive performance and capability in patient subtyping. Furthermore, our framework provides transparent, biologically grounded rationales for its routing decisions, bridging the gap between high-performance survival analysis and interpretable clinical decision support.

cs.LG↗

Interpretable Alzheimer's Diagnosis via Multimodal Fusion of Regional Brain Experts

Accurate and early diagnosis of Alzheimer's disease (AD) is critical for effective intervention and requires integrating complementary information from multimodal neuroimaging data. However, conventional fusion approaches often rely on simple concatenation of features, which cannot adaptively balance the contributions of biomarkers such as amyloid PET and MRI across brain regions. In this work, we propose MREF-AD, a Multimodal Regional Expert Fusion model for AD diagnosis. It is a Mixture-of-Experts (MoE) framework that models mesoscopic brain regions within each modality as independent experts and employs a gating network to learn subject-specific fusion weights. Utilizing tabular neuroimaging and demographic information from the Alzheimer's Disease Neuroimaging Initiative (ADNI), MREF-AD achieves competitive performance over strong classic and deep baselines while providing interpretable, modality- and region-level insight into how structural and molecular imaging jointly contribute to AD diagnosis. The source code is available at https://github.com/PennShenLab/mref-ad.

cs.LG↗

nD-RoPE: A Generalized RoPE for n-Dimensional Position Embedding

Rotary Position Embedding (RoPE) is widely adopted in Transformer models, yet its extension to high-dimensional domains lacks a unified theoretical formulation. Most existing approaches either apply rotations independently along each axis or empirically mix frequencies, which limits cross-dimensional interactions and yields direction-dependent representations. To address these limitations, we propose nD-RoPE, a decomposition-free generalization of RoPE to arbitrary dimensions. From a translation-invariant formulation in continuous Hilbert space, we derive a spectral condition for isotropy that requires treating positions and frequencies as coupled \(n\)-dimensional vectors. We instantiate this formulation with a multi-scale regular-simplex wave-vector design, which provides non-degenerate spatial coverage and a symmetric, directionally balanced second-order response. Experiments across images, videos, and point clouds demonstrate consistent performance gains and improved generalization in high-dimensional settings.

cs.LG↗

Fermion sign problem and the structure of Lee-Yang zeros. II. Finite temperature results for a model system without interactions

Beyond the analysis of the Lee-Yang (LY) zero of $ξ$ at $0$ K presented by our previous work [He et. al. Phys. Rev. E 113, 24115 (2026)], it is important but intricate to understand how these zeros evolve with temperature ($T$). Here, we use an analytically solvable noninteracting one-dimensional particle-on-a-ring model to address this. We determine the trajectories of these zeros and analyze how their evolution with $T$ reshapes the analytic structure of the partition function. In particular, the zero originating from $ξ=-1$ at $T=0$ remains close to $-1$ at low $T$, where it governs the sign factor and strongly constrains continuation along the real $ξ$ axis. This explains why both direct extrapolation and implicit schemes such as contour-based fitting can fail in the low-$T$ regime, even at high fitting order, while becoming reasonable again once the relevant zeros move away at higher $T$s. Furthermore, based on the polynomial structure of the partition function, we propose a new fitting strategy for low-$T$ fermionic properties. The key is to first obtain reliable high-$T$ fermionic properties by continuing sign-problem-free data in $ξ\in[0,1]$ to $ξ=-1$, and then extend this information toward lower $T$ through $T$-fitting of the $ξ$-independent remainder $ϕ(β)=Z_{\text{F}}$. These results provide a solvable benchmark for diagnosing the validity of analytic continuation and suggest a possible route toward treating more realistic interacting fermionic systems.

cond-mat.stat-mech↗