arXiv subjects

Hua Tang

Publications and source records attributed to Hua Tang.

11 recordsLinked to original sources

arXiv2026

An Early Warning of Emerging Biosecurity Risks in Frontier LLMs

Frontier large language models (LLMs) are increasingly integrated into scientific workflows, yet their growing biological capabilities may outpace current safeguards. To assess the biological risks of frontier models, we develop Intern-BioBreaker, a specialized bio-red-teaming model, together with an integrated computational-to-physical framework that couples model-level stress testing with wet-lab validation. Within this framework, Intern-BioBreaker generates targeted jailbreak prompts to test whether aligned models can be induced to provide operational guidance for safety-sensitive biological tasks or produce sequence-level outputs with potentially harmful properties. Selected sequence outputs are then carried forward for DNA synthesis, host expression, and orthogonal protein verification to assess whether model-generated designs can yield the intended biological products. Our evaluation reveals a concerning gap between text-level safeguards and the risks posed by capable scientific models: (i) Intern-BioBreaker outperforms baseline attack models and reveals widespread bio-risk jailbreak vulnerabilities across both open-weight and proprietary frontier LLMs, with several targets reaching near-saturated or 100% task-level attack success rate (ASR); (ii) in sequence-level case studies, GPT-5.5 can be induced to generate modified viral candidate sequences with pathogenic potential; the corresponding translated proteins may exhibit even stronger receptor-binding affinity and thus enhanced infection potential; and (iii) end-to-end verification shows that selected model-generated biological designs are not merely textual artifacts, but can be physically realized under controlled experimental settings. These findings underscore the need for stronger biological red-teaming, nucleic acid synthesis screening, and safety mechanisms that keep pace with model capabilities.

cs.CL↗

arXiv2026

Autonomous Laparoscope Control through Unified Mechanics-Based Representation of Multimodal Intraoperative Information

Laparoscope-holding robots can provide surgeons with a stable laparoscopic field of view (FOV) and reduce the burden on human assistants. To maintain an ideal intraoperative FOV, the robot must continuously adjust the laparoscope pose according to intraoperative information. However, intraoperative multimodal signals, such as position, force/torque, and images, differ markedly in physical meaning and units, making it difficult to build a unified representation and to generate control commands that can be used directly for laparoscope control. To address this issue, we propose a laparoscope-holding robot control method based on unified mechanics modeling of multimodal information. First, we design mapping strategies for multiple intraoperative sources, including position, force/torque, and images, and unify them into an equivalent-wrench representation in the operational space. Then, using a task-priority scheme, we inject the wrenches into the task space and the null space, respectively, and synthesize laparoscope control commands via task-priority projection, thereby achieving consistent representation and coordinated fusion of multimodal information within a single framework. Finally, taking the intraoperative remote center of motion (RCM) position, force/torque sensor readings, and laparoscopic images as examples, we construct an RCM-constraint wrench to enforce the RCM geometric constraint and reduce the contact force at the trocar site, a laparoscope-manipulation wrench to enable compliant dragging, and an instrument-tracking wrench to achieve autonomous visual tracking of the instruments. Experiments on a surgical phantom and in vivo porcine trials demonstrate that the proposed method supports multi-task operation, including compliant laparoscope manipulation and autonomous instrument tracking, while maintaining the RCM constraint and reducing sustained trocar-site loading.

cs.RO↗

arXiv2025

GRAF: Multi-turn Jailbreaking via Global Refinement and Active Fabrication

Large Language Models (LLMs) have demonstrated remarkable performance across diverse tasks. Nevertheless, they still pose notable safety risks due to potential misuse for malicious purposes. Jailbreaking, which seeks to induce models to generate harmful content through single-turn or multi-turn attacks, plays a crucial role in uncovering underlying security vulnerabilities. However, prior methods, including sophisticated multi-turn approaches, often struggle to adapt to the evolving dynamics of dialogue as interactions progress. To address this challenge, we propose \ours (JailBreaking via \textbf{G}lobally \textbf{R}efining and \textbf{A}daptively \textbf{F}abricating), a novel multi-turn jailbreaking method that globally refines the attack trajectory at each interaction. In addition, we actively fabricate model responses to suppress safety-related warnings, thereby increasing the likelihood of eliciting harmful outputs in subsequent queries. Extensive experiments across six state-of-the-art LLMs demonstrate the superior effectiveness of our approach compared to existing single-turn and multi-turn jailbreaking methods. Our code will be released at https://github.com/Ytang520/Multi-Turn_jailbreaking_Global-Refinment_and_Active-Fabrication.

cs.CL↗

arXiv2024

What if LLMs Have Different World Views: Simulating Alien Civilizations with LLM-based Agents

This study introduces "CosmoAgent," an innovative artificial intelligence system that utilizes Large Language Models (LLMs) to simulate complex interactions between human and extraterrestrial civilizations. This paper introduces a mathematical model for quantifying the levels of civilization development and further employs a state transition matrix approach to evaluate their trajectories. Through this methodology, our study quantitatively analyzes the growth trajectories of civilizations, providing insights into future decision-making at critical points of growth and saturation. Furthermore, this paper acknowledges the vast diversity of potential living conditions across the universe, which could foster unique cosmologies, ethical codes, and worldviews among different civilizations. Recognizing the Earth-centric bias inherent in current LLM designs, we propose the novel concept of using LLM agents with diverse ethical paradigms and simulating interactions between entities with distinct moral principles. This innovative research not only introduces a novel method for comprehending potential inter-civilizational dynamics but also holds practical value in enabling entities with divergent value systems to strategize, prevent conflicts, and engage in games under conditions of asymmetric information. The accompanying code is available at https://github.com/MingyuJ666/Simulating-Alien-Civilizations-with-LLM-based-Agents.

cs.CL↗

arXiv2024

Time Series Forecasting with LLMs: Understanding and Enhancing Model Capabilities

Large language models (LLMs) have been applied in many fields and have developed rapidly in recent years. As a classic machine learning task, time series forecasting has recently been boosted by LLMs. Recent works treat large language models as \emph{zero-shot} time series reasoners without further fine-tuning, which achieves remarkable performance. However, there are some unexplored research problems when applying LLMs for time series forecasting under the zero-shot setting. For instance, the LLMs' preferences for the input time series are less understood. In this paper, by comparing LLMs with traditional time series forecasting models, we observe many interesting properties of LLMs in the context of time series forecasting. First, our study shows that LLMs perform well in predicting time series with clear patterns and trends, but face challenges with datasets lacking periodicity. This observation can be explained by the ability of LLMs to recognize the underlying period within datasets, which is supported by our experiments. In addition, the input strategy is investigated, and it is found that incorporating external knowledge and adopting natural language paraphrases substantially improve the predictive performance of LLMs for time series. Overall, our study contributes insight into LLMs' advantages and limitations in time series forecasting under different conditions.

cs.CL↗

arXiv2023

A Theoretical Approach to Characterize the Accuracy-Fairness Trade-off Pareto Frontier

While the accuracy-fairness trade-off has been frequently observed in the literature of fair machine learning, rigorous theoretical analyses have been scarce. To demystify this long-standing challenge, this work seeks to develop a theoretical framework by characterizing the shape of the accuracy-fairness trade-off Pareto frontier (FairFrontier), determined by a set of all optimal Pareto classifiers that no other classifiers can dominate. Specifically, we first demonstrate the existence of the trade-off in real-world scenarios and then propose four potential categories to characterize the important properties of the accuracy-fairness Pareto frontier. For each category, we identify the necessary conditions that lead to corresponding trade-offs. Experimental results on synthetic data suggest insightful findings of the proposed framework: (1) When sensitive attributes can be fully interpreted by non-sensitive attributes, FairFrontier is mostly continuous. (2) Accuracy can suffer a \textit{sharp} decline when over-pursuing fairness. (3) Eliminate the trade-off via a two-step streamlined approach. The proposed research enables an in-depth understanding of the accuracy-fairness trade-off, pushing current fair machine-learning research to a new frontier.

cs.LG↗

arXiv2023

Robust inference with GhostKnockoffs in genome-wide association studies

Genome-wide association studies (GWASs) have been extensively adopted to depict the underlying genetic architecture of complex diseases. Motivated by GWASs' limitations in identifying small effect loci to understand complex traits' polygenicity and fine-mapping putative causal variants from proxy ones, we propose a knockoff-based method which only requires summary statistics from GWASs and demonstrate its validity in the presence of relatedness. We show that GhostKnockoffs inference is robust to its input Z-scores as long as they are from valid marginal association tests and their correlations are consistent with the correlations among the corresponding genetic variants. The property generalizes GhostKnockoffs to other GWASs settings, such as the meta-analysis of multiple overlapping studies and studies based on association test statistics deviated from score tests. We demonstrate GhostKnockoffs' performance using empirical simulation and a meta-analysis of nine European ancestral genome-wide association studies and whole exome/genome sequencing studies. Both results demonstrate that GhostKnockoffs identify more putative causal variants with weak genotype-phenotype associations that are missed by conventional GWASs.

stat.ME↗

arXiv2022

Improving genetic risk prediction across diverse population by disentangling ancestry representations

Risk prediction models using genetic data have seen increasing traction in genomics. However, most of the polygenic risk models were developed using data from participants with similar (mostly European) ancestry. This can lead to biases in the risk predictors resulting in poor generalization when applied to minority populations and admixed individuals such as African Americans. To address this bias, largely due to the prediction models being confounded by the underlying population structure, we propose a novel deep-learning framework that leverages data from diverse population and disentangles ancestry from the phenotype-relevant information in its representation. The ancestry disentangled representation can be used to build risk predictors that perform better across minority populations. We applied the proposed method to the analysis of Alzheimer's disease genetics. Comparing with standard linear and nonlinear risk prediction methods, the proposed method substantially improves risk prediction in minority populations, particularly for admixed individuals.

cs.LG↗

arXiv2009

Dark-Sates in Electromagnetically Induced Transparency Controlled by a Microwave Field

The rigorous dark-sate conditions, i.e., two-photon resonance, for a Lambda-type electromagnetically induced transparency (EIT) are extended with the system controlled by a microwave field. The extended dark-states are found to be extremely sensitive to the phase of the microwave field in a narrow interval. However, the dark-state is no longer the requirement for EIT in this scheme and EIT without dark states is present.

quant-ph↗

arXiv2007

Improving population-specific allele frequency estimates by adapting supplemental data: an empirical Bayes approach

Estimation of the allele frequency at genetic markers is a key ingredient in biological and biomedical research, such as studies of human genetic variation or of the genetic etiology of heritable traits. As genetic data becomes increasingly available, investigators face a dilemma: when should data from other studies and population subgroups be pooled with the primary data? Pooling additional samples will generally reduce the variance of the frequency estimates; however, used inappropriately, pooled estimates can be severely biased due to population stratification. Because of this potential bias, most investigators avoid pooling, even for samples with the same ethnic background and residing on the same continent. Here, we propose an empirical Bayes approach for estimating allele frequencies of single nucleotide polymorphisms. This procedure adaptively incorporates genotypes from related samples, so that more similar samples have a greater influence on the estimates. In every example we have considered, our estimator achieves a mean squared error (MSE) that is smaller than either pooling or not, and sometimes substantially improves over both extremes. The bias introduced is small, as is shown by a simulation study that is carefully matched to a real data example. Our method is particularly useful when small groups of individuals are genotyped at a large number of markers, a situation we are likely to encounter in a genome-wide association study.

stat.AP↗

arXiv2007

Complementarity in a macroscopic observation

Complementarity is usually considered as a phenomenon of microscopic systems. In this paper we report an experimental observation of complementarity in the correlated double-slit interference with a pseudothermal light source. The thermal light beam is divided into test and reference beams which are correlated with each other. The double-slit is set in the test arm, and the interference pattern can be observed in the intensity correlation between the two arms. The experimental results show that the disappearance of interference fringe depends on whether which-path information is gained through the reference arm. The experiment therefore witnesses the complementarity occurring in a macroscopic system.

quant-ph↗