arXiv subjects

Richard Huang

Publications and source records attributed to Richard Huang.

9 recordsLinked to original sources

arXiv2026

NVAITC AI Scientist: A Governed End-to-End Research System -- A Hypertension GWAS Case Study

Agentic research systems are emerging as a new paradigm for coordinating scientific workflows beyond isolated model inference, code generation, or statistical analysis. However, deployment in institutional biomedical environments requires governed mechanisms for research planning, data access, workflow orchestration, evidence tracking, reproducibility, and human oversight. We present NVAITC AI Scientist (NAIS), a governed end-to-end agentic research system designed to support domain-general scientific workflows while keeping protected data within institutional privacy boundaries. NAIS integrates proposal review, execution planning, governed computational routing, reproducible workflow orchestration, evidence generation, and scientist-in-the-loop oversight. We validate NAIS in a real-world hypertension genome-wide association study (GWAS) using hospital-linked genotype and electronic health record (EHR) data from 286,422 individuals under an aggregate-only data policy. The agent planned cohort extraction, orchestrated GWAS execution, generated quality-control summaries, and drafted publication-oriented outputs. Human-AI review identified phenotype discrepancies and enabled iterative refinement of the hypertension definition. After reconciliation, the agent-orchestrated GWAS reproduced established hypertension loci, including FGF5, ATP2B1, CNNM2, FTO, and GRB14, with the strongest signal at FGF5 reaching $-\log_{10}(p) \sim 70$. As a secondary demonstration, NAIS also supported a drug-induced liver injury prediction workflow, achieving a multimodal graph neural network AUC of 0.842. These results demonstrate that governed agentic research systems can support scalable AI-assisted biomedical discovery while producing outputs comparable to expert-led workflows.

cs.AI↗

arXiv2026

Banded non-Hermitian random matrices, neural networks, and eigenvalue degeneracies

We study two-banded, non-Hermitian random matrices inspired by sparse neural networks with a circular, 1d topology. We focus on two paradigmatic models, an SSH chain and a ladder model, which have both non-Hermitian directional bias and random sign disorder in the hoppings. The random sign disorder, which follows Dale's Law, leads to localization of the eigenstates, while the directional bias drives a delocalization transition in these states. The competition between disorder and directional bias results in rich eigenspectra with loops of extended states in the complex plane surrounded by regions of localized ones, and the eigenvalues are all confined to an annular region. Furthermore, the distinct band structures of the SSH chain and ladder model lead to different delocalization phenomena. Even in the absence of disorder, tuning the directional bias can lead to an eigenvalue degeneracy, which is an exceptional point for the SSH chain but a diabolic point for the ladder. In the presence of the disorder, these special eigenvalue degeneracies are preserved and also highlight key stages in the delocalization process. For both models, increasing the directional bias initially delocalizes states starting from within the bands. For the SSH chain, for large enough directional bias, the delocalized states open up a hole in the spectrum in the complex plane, similar to prior results for single band systems. But for the ladder model, as the directional bias is increased, the states delocalize in two stages, leading to two separate loops of extended states with localized states in between. The precise contours on which the extended states reside can be predicted from the Lyapunov exponents associated with products of random transfer matrices, in agreement with direct numerical diagonalization. Although we focus on periodic boundaries, results are discussed for open boundaries as well.

cond-mat.dis-nn↗

arXiv2026

Agent Skills: A Data-Driven Analysis of Claude Skills for Extending Large Language Model Functionality

Agent skills extend large language model (LLM) agents with reusable, program-like modules that define triggering conditions, procedural logic, and tool interactions. As these skills proliferate in public marketplaces, it is unclear what types are available, how users adopt them, and what risks they pose. To answer these questions, we conduct a large-scale, data-driven analysis of 40,285 publicly listed skills from a major marketplace. Our results show that skill publication tends to occur in short bursts that track shifts in community attention. We also find that skill content is highly concentrated in software engineering workflows, while information retrieval and content creation account for a substantial share of adoption. Beyond content trends, we uncover a pronounced supply-demand imbalance across categories, and we show that most skills remain within typical prompt budgets despite a heavy-tailed length distribution. Finally, we observe strong ecosystem homogeneity, with widespread intent-level redundancy, and we identify non-trivial safety risks, including skills that enable state-changing or system-level actions. Overall, our findings provide a quantitative snapshot of agent skills as an emerging infrastructure layer for agents and inform future work on skill reuse, standardization, and safety-aware design.

cs.SE↗

arXiv2026

Thermalized buckling of extensible, semiflexible polymers

The Euler buckling of rods is a long-studied mechanical instability, and it remains relevant to this day, as the constituent components in many biological and physical systems are linear polymers, such as microtubules or carbon nanotubes. At finite temperature, if a polymer is shorter than its persistence length, the polymer is semiflexible, and its elasticity remains rod-like. But polymers can also stretch due to their finite extensibility, which can couple to energetically cheap bending deformations in nonlinear ways when a load is applied to the system. We show how the interplay between thermal fluctuations and nonlinear elasticity dramatically modifies the Euler buckling instability for compressed semiflexible polymers in a fixed strain ensemble. We identify a Ginzburg-like length scale beyond which thermally excited undulations lead to a softened Young's modulus, while the polymer nevertheless remains semiflexible. Both perturbative calculations and numerical Monte Carlo simulations suggest a qualitative change in several scaling properties of the buckling transition. The critical compressional strain for thermal buckling now increases with system size, in contrast to athermal buckling, where it decreases with system size. Renormalization group calculations confirm this picture, and also show that thermal buckling is controlled by a new fixed point with different critical exponents compared to classical Euler buckling.

cond-mat.stat-mech↗

arXiv2024

Emergent intelligence of buckling-driven elasto-active structures

Active systems of self-propelled agents, e.g., birds, fish, and bacteria, can organize their collective motion into myriad autonomous behaviors. Ubiquitous in nature and across length scales, such phenomena are also amenable to artificial settings, e.g., where brainless self-propelled robots orchestrate their movements into spatio-temportal patterns via the application of external cues or when confined within flexible boundaries. Very much like their natural counterparts, these approaches typically require many units to initiate collective motion such that controlling the ensuing dynamics is challenging. Here, we demonstrate a novel yet simple mechanism that leverages nonlinear elasticity to tame near-diffusive motile particles in forming structures capable of directed motion and other emergent intelligent behaviors. Our elasto-active system comprises two centimeter-sized self-propelled microbots connected with elastic beams. These microbots exert forces that suffice to buckle the beam and set the structure in motion. We first rationalize the physics of the interaction between the beam and the microbots. Then we use reduced order models to predict the interactions of our elasto-active structure with boundaries, e.g., walls and constrictions, and demonstrate how they can exhibit intelligent behaviors such as maze navigation. The findings are relevant to designing intelligent materials or soft robots capable of autonomous space exploration, adaptation, and interaction with the surrounding environment.

cond-mat.soft↗

arXiv2024

Large Language Models for Social Networks: Applications, Challenges, and Solutions

Large Language Models (LLMs) are transforming the way people generate, explore, and engage with content. We study how we can develop LLM applications for online social networks. Despite LLMs' successes in other domains, it is challenging to develop LLM-based products for social networks for numerous reasons, and it has been relatively under-reported in the research community. We categorize LLM applications for social networks into three categories. First is knowledge tasks where users want to find new knowledge and information, such as search and question-answering. Second is entertainment tasks where users want to consume interesting content, such as getting entertaining notification content. Third is foundational tasks that need to be done to moderate and operate the social networks, such as content annotation and LLM monitoring. For each task, we share the challenges we found, solutions we developed, and lessons we learned. To the best of our knowledge, this is the first comprehensive paper about developing LLM applications for social networks.

cs.SI↗

arXiv2023

Let AI Entertain You: Increasing User Engagement with Generative AI and Rejection Sampling

While generative AI excels in content generation, it does not always increase user engagement. This can be attributed to two main factors. First, generative AI generates content without incorporating explicit or implicit feedback about user interactions. Even if the generated content seems to be more informative or well-written, it does not necessarily lead to an increase in user activities, such as clicks. Second, there is a concern with the quality of the content generative AI produces, which often lacks the distinctiveness and authenticity that human-created content possesses. These two factors can lead to content that fails to meet specific needs and preferences of users, ultimately reducing its potential to be engaging. This paper presents a generic framework of how to improve user engagement with generative AI by leveraging user feedback. Our solutions employ rejection sampling, a technique used in reinforcement learning, to boost engagement metrics. We leveraged the framework in the context of email notification subject lines generation for an online social network, and achieved significant engagement metric lift including +1% Session and +0.4% Weekly Active Users. We believe our work offers a universal framework that enhances user engagement with generative AI, particularly when standard generative AI reaches its limits in terms of enhancing content to be more captivating. To the best of our knowledge, this represents an early milestone in the industry's successful use of generative AI to enhance user engagement.

cs.HC↗

arXiv2020

A Pathologist-Annotated Dataset for Validating Artificial Intelligence: A Project Description and Pilot Study

Purpose: In this work, we present a collaboration to create a validation dataset of pathologist annotations for algorithms that process whole slide images (WSIs). We focus on data collection and evaluation of algorithm performance in the context of estimating the density of stromal tumor infiltrating lymphocytes (sTILs) in breast cancer. Methods: We digitized 64 glass slides of hematoxylin- and eosin-stained ductal carcinoma core biopsies prepared at a single clinical site. We created training materials and workflows to crowdsource pathologist image annotations on two modes: an optical microscope and two digital platforms. The workflows collect the ROI type, a decision on whether the ROI is appropriate for estimating the density of sTILs, and if appropriate, the sTIL density value for that ROI. Results: The pilot study yielded an abundant number of cases with nominal sTIL infiltration. Furthermore, we found that the sTIL densities are correlated within a case, and there is notable pathologist variability. Consequently, we outline plans to improve our ROI and case sampling methods. We also outline statistical methods to account for ROI correlations within a case and pathologist variability when validating an algorithm. Conclusion: We have built workflows for efficient data collection and tested them in a pilot study. As we prepare for pivotal studies, we will consider what it will take for the dataset to be fit for a regulatory purpose: study size, patient population, and pathologist training and qualifications. To this end, we will elicit feedback from the FDA via the Medical Device Development Tool program and from the broader digital pathology and AI community. Ultimately, we intend to share the dataset, statistical methods, and lessons learned.

q-bio.QM↗

arXiv2020

The $O(N)$ Model in $4<d<6$: Instantons and Complex CFTs

We revisit the scalar $O(N)$ model in the dimension range $4<d<6$ and study the effects caused by its metastability. As shown in previous work, this model formally possesses a fixed point where, perturbatively in the $1/N$ expansion, the operator scaling dimensions are real and above the unitarity bound. Here, we further show that these scaling dimensions do acquire small imaginary parts due to the instanton effects. In $d$ dimensions and for large $N$, we find that they are of order $e^{-N f(d)}$, where, remarkably, the function $f(d)$ equals the sphere free energy of a conformal scalar in $d-2$ dimensions. The non-perturbatively small imaginary parts also appear in other observables, such as the sphere free energy and two and three-point function coefficients, and we present some of their calculations. Therefore, at sufficiently large $N$, the $O(N)$ models in $4<d<6$ may be thought of as complex CFTs. When $N$ is large enough for the imaginary parts to be numerically negligible, the five-dimensional $O(N)$ models may be studied using the techniques of numerical bootstrap.

hep-th↗