Searcharxiv⌕ Search

arXiv subjects

Trang Nguyen

Publications and source records attributed to Trang Nguyen.

At least 37 records · Page 2Linked to original sources
arXiv2025

Safety challenges of AI in medicine in the era of large language models

Recent advancements in artificial intelligence (AI), particularly in large language models (LLMs), have unlocked significant potential to enhance the quality and efficiency of medical care. By introducing a novel way to interact with AI and data through natural language, LLMs offer new opportunities for medical practitioners, patients, and researchers. However, as AI and LLMs become more powerful and especially achieve superhuman performance in some medical tasks, public concerns over their safety have intensified. These concerns about AI safety have emerged as the most significant obstacles to the adoption of AI in medicine. In response, this review examines emerging risks in AI utilization during the LLM era. First, we explore LLM-specific safety challenges from functional and communication perspectives, addressing issues across data collection, model training, and real-world application. We then consider inherent safety problems shared by all AI systems, along with additional complications introduced by LLMs. Last, we discussed how safety issues of using AI in clinical practice and healthcare system operation would undermine trust among patient, clinicians and the public, and how to build confidence in these systems. By emphasizing the development of safe AI, we believe these technologies can be more rapidly and reliably integrated into everyday medical practice to benefit both patients and clinicians.

cs.CY↗
arXiv2025

Adaptive Prompting for Continual Relation Extraction: A Within-Task Variance Perspective

To address catastrophic forgetting in Continual Relation Extraction (CRE), many current approaches rely on memory buffers to rehearse previously learned knowledge while acquiring new tasks. Recently, prompt-based methods have emerged as potent alternatives to rehearsal-based strategies, demonstrating strong empirical performance. However, upon analyzing existing prompt-based approaches for CRE, we identified several critical limitations, such as inaccurate prompt selection, inadequate mechanisms for mitigating forgetting in shared parameters, and suboptimal handling of cross-task and within-task variances. To overcome these challenges, we draw inspiration from the relationship between prefix-tuning and mixture of experts, proposing a novel approach that employs a prompt pool for each task, capturing variations within each task while enhancing cross-task variances. Furthermore, we incorporate a generative model to consolidate prior knowledge within shared parameters, eliminating the need for explicit data storage. Extensive experiments validate the efficacy of our approach, demonstrating superior performance over state-of-the-art prompt-based and rehearsal-free methods in continual relation extraction.

cs.CL↗
arXiv2025

Mixture of Experts Meets Prompt-Based Continual Learning

Exploiting the power of pre-trained models, prompt-based approaches stand out compared to other continual learning solutions in effectively preventing catastrophic forgetting, even with very few learnable parameters and without the need for a memory buffer. While existing prompt-based continual learning methods excel in leveraging prompts for state-of-the-art performance, they often lack a theoretical explanation for the effectiveness of prompting. This paper conducts a theoretical analysis to unravel how prompts bestow such advantages in continual learning, thus offering a new perspective on prompt design. We first show that the attention block of pre-trained models like Vision Transformers inherently encodes a special mixture of experts architecture, characterized by linear experts and quadratic gating score functions. This realization drives us to provide a novel view on prefix tuning, reframing it as the addition of new task-specific experts, thereby inspiring the design of a novel gating mechanism termed Non-linear Residual Gates (NoRGa). Through the incorporation of non-linear activation and residual connection, NoRGa enhances continual learning performance while preserving parameter efficiency. The effectiveness of NoRGa is substantiated both theoretically and empirically across diverse benchmarks and pretraining paradigms. Our code is publicly available at https://github.com/Minhchuyentoancbn/MoE_PromptCL

cs.LG↗
arXiv2024

Attack On Prompt: Backdoor Attack in Prompt-Based Continual Learning

Prompt-based approaches offer a cutting-edge solution to data privacy issues in continual learning, particularly in scenarios involving multiple data suppliers where long-term storage of private user data is prohibited. Despite delivering state-of-the-art performance, its impressive remembering capability can become a double-edged sword, raising security concerns as it might inadvertently retain poisoned knowledge injected during learning from private user data. Following this insight, in this paper, we expose continual learning to a potential threat: backdoor attack, which drives the model to follow a desired adversarial target whenever a specific trigger is present while still performing normally on clean samples. We highlight three critical challenges in executing backdoor attacks on incremental learners and propose corresponding solutions: (1) \emph{Transferability}: We employ a surrogate dataset and manipulate prompt selection to transfer backdoor knowledge to data from other suppliers; (2) \emph{Resiliency}: We simulate static and dynamic states of the victim to ensure the backdoor trigger remains robust during intense incremental learning processes; and (3) \emph{Authenticity}: We apply binary cross-entropy loss as an anti-cheating factor to prevent the backdoor trigger from devolving into adversarial noise. Extensive experiments across various benchmark datasets and continual learners validate our continual backdoor framework, achieving up to $100\%$ attack success rate, with further ablation studies confirming our contributions' effectiveness.

cs.LG↗
arXiv2024

Well-posedness and Stability of Discrete Approximations for Controlled Sweeping Processes with Time Delay

This paper addresses, for the first time in the literature, optimal control problems for dynamic systems governed by a novel class of sweeping processes with time delay. We establish well-posedness of such processes, in the sense of the existence and uniqueness of feasible trajectories corresponding to feasible controls under fairly unrestrictive assumptions. Then we construct a well-posed family of discrete approximations and find efficient conditions under the discretized time-delayed sweeping process exhibits stability with respect to strong convergence of feasible and optimal solutions. This creates a bridge between optimization of continuous-time and discrete-time sweeping control systems and justifies the effective use of discrete approximations in deriving optimality conditions and numerical techniques to solve the original time-delayed sweeping control problems via discrete approximations.

math.OC↗
arXiv2024

Optimal control of perturbed sweeping processes with applications to general robotics models

This paper primarily focuses on the practical applications of optimal control theory for perturbed sweeping processes within the realm of robotics dynamics. By describing these models as controlled sweeping processes with pointwise control and state constraints and by employing necessary optimality conditions for such systems, we formulate optimal control problems suitable to these models and develop numerical algorithms for their solving. Subsequently, we use the Python Dynamic Optimization library GEKKO to simulate solutions to the posed robotics problems in the case of any fixed number of robots under different initial conditions.

math.OC↗
arXiv2023

Optimal control of sweeping processes in unmanned surface vehicle and nanoparticle modeling

This paper addresses novel applications to practical modeling of the newly developed theory of necessary optimality conditions in controlled sweeping/Moreau processes with free time and pointwise control and state constraints. Problems of this type appear, in particular, in dynamical models dealing with unmanned surface vehicles (USVs) and nanoparticles. We formulate optimal control problems for a general class of such dynamical systems and show that the developed necessary optimality conditions for constrained free-time controlled sweeping processes lead us to designing efficient procedures to solve practical models of this class. Moreover, the paper contains numerical calculations of optimal solutions to marine USVs and nanoparticle models in specific situations. Overall, this study contributes to the advancement of optimal control theory for constrained sweeping processes and its practical applications in the fields of marine USVs and nanoparticle modeling.

math.OC↗
arXiv2023

Reusable Slotwise Mechanisms

Agents with the ability to comprehend and reason about the dynamics of objects would be expected to exhibit improved robustness and generalization in novel scenarios. However, achieving this capability necessitates not only an effective scene representation but also an understanding of the mechanisms governing interactions among object subsets. Recent studies have made significant progress in representing scenes using object slots. In this work, we introduce Reusable Slotwise Mechanisms, or RSM, a framework that models object dynamics by leveraging communication among slots along with a modular architecture capable of dynamically selecting reusable mechanisms for predicting the future states of each object slot. Crucially, RSM leverages the Central Contextual Information (CCI), enabling selected mechanisms to access the remaining slots through a bottleneck, effectively allowing for modeling of higher order and complex interactions that might require a sparse subset of objects. Experimental results demonstrate the superior performance of RSM compared to state-of-the-art methods across various future prediction and related downstream tasks, including Visual Question Answering and action planning. Furthermore, we showcase RSM's Out-of-Distribution generalization ability to handle scenes in intricate scenarios.

cs.AI↗
arXiv2023

Discrete Approximations and Optimality Conditions for Controlled Free-Time Sweeping Processes

The paper is devoted to the study of a new class of optimal control problems governed by discontinuous constrained differential inclusions of the sweeping type with involving the duration of the dynamic process into optimization. We develop a novel version of the method of discrete approximations of its own qualitative and numerical values with establishing its well-posedness and strong convergence to optimal solutions of the controlled sweeping process. Using advanced tools of first-order and second-order variational analysis and generalized differentiation allows us to derive new necessary conditions for optimal solutions of the discrete-time problems and then, by passing to the limit in the discretization procedure, for designated local minimizers in the original problem of sweeping optimal control. The obtained results are illustrated by a numerical example.

math.OC↗
arXiv2023

Causal Reasoning through Two Layers of Cognition for Improving Generalization in Visual Question Answering

Generalization in Visual Question Answering (VQA) requires models to answer questions about images with contexts beyond the training distribution. Existing attempts primarily refine unimodal aspects, overlooking enhancements in multimodal aspects. Besides, diverse interpretations of the input lead to various modes of answer generation, highlighting the role of causal reasoning between interpreting and answering steps in VQA. Through this lens, we propose Cognitive pathways VQA (CopVQA) improving the multimodal predictions by emphasizing causal reasoning factors. CopVQA first operates a pool of pathways that capture diverse causal reasoning flows through interpreting and answering stages. Mirroring human cognition, we decompose the responsibility of each stage into distinct experts and a cognition-enabled component (CC). The two CCs strategically execute one expert for each stage at a time. Finally, we prioritize answer predictions governed by pathways involving both CCs while disregarding answers produced by either CC, thereby emphasizing causal reasoning and supporting generalization. Our experiments on real-life and medical data consistently verify that CopVQA improves VQA performance and generalization across baselines and domains. Notably, CopVQA achieves a new state-of-the-art (SOTA) on PathVQA dataset and comparable accuracy to the current SOTA on VQA-CPv2, VQAv2, and VQA RAD, with one-fourth of the model size.

cs.AI↗
arXiv2023

Causal Inference in Gene Regulatory Networks with GFlowNet: Towards Scalability in Large Systems

Understanding causal relationships within Gene Regulatory Networks (GRNs) is essential for unraveling the gene interactions in cellular processes. However, causal discovery in GRNs is a challenging problem for multiple reasons including the existence of cyclic feedback loops and uncertainty that yields diverse possible causal structures. Previous works in this area either ignore cyclic dynamics (assume acyclic structure) or struggle with scalability. We introduce Swift-DynGFN as a novel framework that enhances causal structure learning in GRNs while addressing scalability concerns. Specifically, Swift-DynGFN exploits gene-wise independence to boost parallelization and to lower computational cost. Experiments on real single-cell RNA velocity and synthetic GRN datasets showcase the advancement in learning causal structure in GRNs and scalability in larger systems.

cs.AI↗
arXiv2023

Spotlight Attention: Robust Object-Centric Learning With a Spatial Locality Prior

The aim of object-centric vision is to construct an explicit representation of the objects in a scene. This representation is obtained via a set of interchangeable modules called \emph{slots} or \emph{object files} that compete for local patches of an image. The competition has a weak inductive bias to preserve spatial continuity; consequently, one slot may claim patches scattered diffusely throughout the image. In contrast, the inductive bias of human vision is strong, to the degree that attention has classically been described with a spotlight metaphor. We incorporate a spatial-locality prior into state-of-the-art object-centric vision models and obtain significant improvements in segmenting objects in both synthetic and real-world datasets. Similar to human visual attention, the combination of image content and spatial constraints yield robust unsupervised object-centric learning, including less sensitivity to model hyperparameters.

cs.CV↗
arXiv2023

The 2022 NIST Language Recognition Evaluation

In 2022, the U.S. National Institute of Standards and Technology (NIST) conducted the latest Language Recognition Evaluation (LRE) in an ongoing series administered by NIST since 1996 to foster research in language recognition and to measure state-of-the-art technology. Similar to previous LREs, LRE22 focused on conversational telephone speech (CTS) and broadcast narrowband speech (BNBS) data. LRE22 also introduced new evaluation features, such as an emphasis on African languages, including low resource languages, and a test set consisting of segments containing between 3s and 35s of speech randomly sampled and extracted from longer recordings. A total of 21 research organizations, forming 16 teams, participated in this 3-month long evaluation and made a total of 65 valid system submissions to be evaluated. This paper presents an overview of LRE22 and an analysis of system performance over different evaluation conditions. The evaluation results suggest that Oromo and Tigrinya are easier to detect while Xhosa and Zulu are more challenging. A greater confusability is seen for some language pairs. When speech duration increased, system performance significantly increased up to a certain duration, and then a diminishing return on system performance is observed afterward.

cs.CL↗
arXiv2023

On Cross-Layer Alignment for Model Fusion of Heterogeneous Neural Networks

Layer-wise model fusion via optimal transport, named OTFusion, applies soft neuron association for unifying different pre-trained networks to save computational resources. While enjoying its success, OTFusion requires the input networks to have the same number of layers. To address this issue, we propose a novel model fusion framework, named CLAFusion, to fuse neural networks with a different number of layers, which we refer to as heterogeneous neural networks, via cross-layer alignment. The cross-layer alignment problem, which is an unbalanced assignment problem, can be solved efficiently using dynamic programming. Based on the cross-layer alignment, our framework balances the number of layers of neural networks before applying layer-wise model fusion. Our experiments indicate that CLAFusion, with an extra finetuning process, improves the accuracy of residual networks on the CIFAR10, CIFAR100, and Tiny-ImageNet datasets. Furthermore, we explore its practical usage for model compression and knowledge distillation when applying to the teacher-student setting.

cs.LG↗
arXiv2022

Fast Approximation of the Generalized Sliced-Wasserstein Distance

Generalized sliced Wasserstein distance is a variant of sliced Wasserstein distance that exploits the power of non-linear projection through a given defining function to better capture the complex structures of the probability distributions. Similar to sliced Wasserstein distance, generalized sliced Wasserstein is defined as an expectation over random projections which can be approximated by the Monte Carlo method. However, the complexity of that approximation can be expensive in high-dimensional settings. To that end, we propose to form deterministic and fast approximations of the generalized sliced Wasserstein distance by using the concentration of random projections when the defining functions are polynomial function, circular function, and neural network type function. Our approximations hinge upon an important result that one-dimensional projections of a high-dimensional random vector are approximately Gaussian.

stat.ML↗
arXiv2021

Applications of Controlled Sweeping Processes to Nonlinear Crowd Motion Models with Obstacles

This paper mainly focuses on solving the dynamic optimization of the planar controlled crowd motion models with obstacles which is an application of a class of optimal control problems governed by a general perturbed nonconvex sweeping process. This can be considered as a significant extension of the previous work regarding the controlled crowd motion models, where the obstacles have not been considered. The necessary optimality conditions for the problem under consideration are established and illustrated by a nontrivial example of practical importance.

math.OC↗
arXiv2018

A New Vehicle Localization Scheme Based on Combined Optical Camera Communication and Photogrammetry

The demand for autonomous vehicles is increasing gradually owing to their enormous potential benefits. However, several challenges, such as vehicle localization, are involved in the development of autonomous vehicles. A simple and secure algorithm for vehicle positioning is proposed herein without massively modifying the existing transportation infrastructure. For vehicle localization, vehicles on the road are classified into two categories: host vehicles (HVs) are the ones used to estimate other vehicles' positions and forwarding vehicles (FVs) are the ones that move in front of the HVs. The FV transmits modulated data from the tail (or back) light, and the camera of the HV receives that signal using optical camera communication (OCC). In addition, the streetlight (SL) data are considered to ensure the position accuracy of the HV. Determining the HV position minimizes the relative position variation between the HV and FV. Using photogrammetry, the distance between FV or SL and the camera of the HV is calculated by measuring the occupied image area on the image sensor. Comparing the change in distance between HV and SLs with the change in distance between HV and FV, the positions of FVs are determined. The performance of the proposed technique is analyzed, and the results indicate a significant improvement in performance. The experimental distance measurement validated the feasibility of the proposed scheme.

cs.NI↗