Artificial Intelligence and Robotics Commons^™

Task Complexity Matters: An Empirical Study Of Reasoning In Llms For Sentiment Analysis, Donghao Huang, Zhaoxia Wang

Research Collection School Of Computing and Information Systems

Large language models (LLMs) with reasoning capabilities have fueled a compelling narrative that reasoning universally improves performance across language tasks. We test this claim through a comprehensive evaluation of 504 configurations across seven model families—including adaptive, conditional, and reinforcement learning-based reasoning architectures—on sentiment analysis datasets of varying granularity (binary, five-class, and 27-class emotion). Our findings reveal that reasoning effectiveness is strongly task-dependent, challenging prevailing assumptions: (1) Reasoning shows task-complexity dependence—binary classification degrades up to -19.9 F1% points (pp), while 27-class emotion recognition gains up to  +16.0 pp; (2) Distilled reasoning variants underperform base models by 3–18 pp on simpler tasks, …

Ai In Healthcare: Regulatory Guidelines And Judge-Made Negligence Principles For Ai Implementers, Gary K. Y. Chan

Research Collection Yong Pung How School Of Law

The use of artificial intelligence (AI) in healthcare may, notwithstanding its potential benefits, result in harm to patients from allegedly negligent acts or omissions by hospitals and medical doctors. In such circumstances, how should the principles in the tort of negligence (duty of care, breach, causation, remoteness of damage, and defences) respond to AI innovations in healthcare? In particular, how may the standard of care expected of hospitals and medical doctors be informed by regulatory guidelines? We refer to case law precedents and regulatory guidelines on the roles and responsibilities of doctors and hospitals as AI implementers. Importantly, they prompt …

Rode: Linear Rectified Mixture Of Diverse Experts For Food Large Multi-Modal Models, Pengkun Jiao, Xinlan Wu, Bin Zhu, Jingjing Chen, Chong-Wah Ngo, Yu-Gang

Research Collection School Of Computing and Information Systems

Large Multi-modal Models (LMMs) have significantly advanced a variety of vision-language tasks. The scalability and availability of high-quality training data play a pivotal role in the success of LMMs. In the realm of food, while comprehensive food datasets such as Recipe1M offer an abundance of ingredient and recipe information, they often fall short of providing ample data for nutritional analysis. The Recipe1M+ dataset, despite offering a subset for nutritional evaluation, is limited in the scale and accuracy of nutrition information. To bridge this gap, we introduce Uni-Food, a unified food dataset that comprises over 100,000 images with various food labels, …

Benchmarking Gaslighting Negation Attacks Against Multimodal Large Language Models, Bin Zhu, Yinxuan Gui, Huiyan Qi, Jingjing Chen, Chong-Wah Ngo, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Multimodal Large Language Models (MLLMs) have exhibited remarkable advancements in integrating different modalities, excelling in complex understanding and generation tasks. Despite their success, MLLMs remain vulnerable to conversational adversarial inputs. In this paper, we systematically study gaslighting negation attacks—a phenomenon where models, despite initially providing correct answers, are persuaded by user-provided negations to reverse their outputs, often fabricating justifications. We conduct extensive evaluations of state-of-the-art MLLMs across diverse benchmarks and observe substantial performance drops when negation is introduced. Notably, we introduce the first benchmark GaslightingBench, specifically designed to evaluate the vulnerability of MLLMs to negation arguments. GaslightingBench consists of multiple-choice …

Sam3-Litetext: An Anatomical Study Of The Sam3 Text Encoder For Efficient Vision-Language Segmentation, Chengxi Zeng, Yuxuan Jiang, Ge Gao, Shuai Wang, Duolikun Danier, Bin Zhu, Stevan Rudinac, David Bull, Fan Zhang

Research Collection School Of Computing and Information Systems

Vision-language segmentation models such as SAM3 enable flexible, prompt-driven visual grounding, but inherit large, general-purpose text encoders originally designed for open-ended language understanding. In practice, segmentation prompts are short, structured, and semantically constrained, leading to substantial over-provisioning in text encoder capacity and persistent computational and memory overhead. In this paper, we perform a large-scale anatomical analysis of text prompting in vision–language segmentation, covering 404,796 real prompts across multiple benchmarks. Our analysis reveals severe redundancy: most context windows are underutilized, vocabulary usage is highly sparse, and text embeddings lie on a low-dimensional manifold despite high-dimensional representations. Motivated by these findings, we …

Frozen Lvlms For Micro-Video Recommendation: A Systematic Study Of Feature Extraction And Fusion, Huatuan Sun, Yunshan Ma, Changguang Wu, Yanxin Zhang, Pengfei Wang, Xiaoyu Du

Research Collection School Of Computing and Information Systems

Frozen Large Video Language Models (LVLMs) are increasingly employed in micro-video recommendation (MVR) due to their strong multimodal understanding. However, existing apporches typically deploy LVLMs as fixed black-box feature extractors without systematically comparing alternative representation strategies. To address this gap, we present the first systematic empirical study on various feature extraction paradigms and integration strategies, along with hierarchical representations from frozen LVLMs for MVR. Extensive experiments on representative LVLMs reveal that hidden states from multiple decoder layers provide richer and more effective representations for MVR. Guided by this insight, we propose the Dual Feature Fusion (DFF) Framework, a lightweight approach …

Group Conversational Agents: A Review Of Designs That Support And Shape Group Interaction, Shunyi Yeo, Tianyi Zhang, Scott Bateman, Gary Hsieh, Young-Ho Kim, Simon Tangi Perrault, Jiannan Li, Anthony Tang

Research Collection School Of Computing and Information Systems

Conversational agents that participate in or mediate group interaction introduce challenges that extend beyond supporting individual users, raising new questions about how agents participate in and influence groups. To characterise this emerging design space, we present a systematic review of 53 peer-reviewed studies on group conversational agents (GCAs). We analyse how GCAs intervene in group-level processes, including participation regulation, conflict mediation, task alignment, and execution support. Using concepts from group research as an analytic lens, we organise prior GCA work around recurring group interactional challenges (orientation, conflict, alignment, and execution), and examine the roles agents are designed to play in …

Language Embeddings Meet Shallow Autoencoders, Rodrigo Alves, Vojtěch Vančura, Pavel Kordík, Antoine Ledent

Research Collection School Of Computing and Information Systems

Shallow autoencoders are appealing recommenders due to their simplicity, scalability, and competitive retrieval quality, but they struggle in strict cold-start settings where new items have no interactions. We propose an inductive shallow autoencoder that leverages item side information (language embeddings) by fixing the decoder to item features and learning only an encoder in the same semantic space. To prevent trivial self-reconstruction without enforcing a hard zero diagonal, we introduce diagonal gating: a leave-one-item-out objective that blocks the self-copy shortcut only for the item being updated while retaining context from the rest of the user history. An alternating-style optimization trains the …

Anatomical Domain Shifts: Test-Time Heterogeneous Adaptation For 3d Human Pose Prediction, Qiongjie Cui, Pan Zhou, Jingjing Chen, Na Zhao

Research Collection School Of Computing and Information Systems

The research frontier in human pose prediction (HPP) is advancing toward continual test-time adaptation (TTA), where models must self-adapt to dynamic test distributions. To date, the homeostatic continual TTA remains the sole viable solution, which isolates the model parameters and update domain-sensitive ones. Despite mitigating full-body domain gaps, human anatomical heterogeneity (domain shifts often localize to specific regions) is ignored. This anatomical-agnostic approach forces uniform parameter adaptation across kinematically distinct segments, causing: over-adaptation of stable regions and under-adaptation of shift-prone articulations. To address it, we introduce TT-HA, a novel Test-Time Heterogeneous Adaptation that implicitly estimates domain changes for anatomical segments, …

History To Future: Evolving Agent With Experience And Thought For Zero-Shot Vision-And-Language Navigation, Guangzhao Dai, Shuo Wang, Zihan Wang, Guo-Sen Xie, Yang Yang, Jinshan Pan, Qianru Sun, Xiangbo Shu

Research Collection School Of Computing and Information Systems

Vision-and-Language Navigation in Continuous Environment (VLN-CE) requires an agent to follow language instructions to navigate the target destination. With the advancement of large language models (LLMs), recent efforts have explored adapting them for zero-shot VLN-CE, offering a promising solution in addressing the drawbacks of poor generalization in the training-based paradigm. However, existing LLM-based works primarily perform naive reasoning for decision-making and lack feedback, e.g., reviewing historical errors and predicting future potentials. Consequently, it may suffer from continuous failure for those initial error tasks. In this paper, we rethink LLM-based zero-shot VLN-CE and propose a new paradigm, named EvoNav, to improve …

Adaptive Outlier Detection Over Data Stream, Rui Zhu, Mingyuan Jiang, Xiaochun Yang, Baihua Zheng, Bin Wang, Tao Qiu

Research Collection School Of Computing and Information Systems

Continuous distance-based outlier detection in streaming data poses significant challenges and has a wide range of practical applications. Traditional threshold-based methods perform well under stable streaming conditions, where fixed parameters remain effective. However, they often struggle with dynamic data distributions and high stream speeds, leading to suboptimal performance, limited control over the number of returned outliers, and failure to meet real-time detection requirements. To address these issues, this paper introduces a novel Recall and Proportion-Aware Outlier Detection (RPA-OD) query. In RPA-OD, ρ defines a distance relaxation that enables real-time outlier detection. Specifically, objects with fewer than k neighbors within the …

“Alexa, Do Not Say That In Front Of My Boss!” A Cross-Cultural Comparison Of User And Ai Preferences For Privacy-Aware Smart Speaker Interactions Across Contexts, Lynne Warin, Emily Aurelia, Anthony Tang, Emily Aurelia, Delphine Reinhardt

Research Collection School Of Computing and Information Systems

Due to their limited ability to reason about the social context in which they are used, smart speakers pose significant privacy risks by responding in ways that may violate people's implicit social boundaries. We conducted a cross-cultural vignette study (N = 944) in Germany and Singapore to investigate how situational factors—specifically social context (bystander relationships and closeness), physical context (location), and interaction context (topic and deceptive intent)—regulate user preferences for smart speaker responses. Our results demonstrate that these factors are superior predictors of response preferences than dispositional user traits (i.e., intrinsic personal traits). We identify two distinct social dynamics: a …

Cfalr: Collaborative Filtering-Augmented Large Language Model For Personalized Fashion Outfit Recommendation, Yujuan Ding, Junrong Liao, Yunshan Ma, Yi Bin, Wenqi Fan, Tat-Seng Chua, Qing Li

Research Collection School Of Computing and Information Systems

Personalized outfit recommendation poses a significant challenge in e-commerce and social media platforms, requiring systems that balance user preferences with aesthetic compatibility. Collaborative filtering (CF) provides a traditional solution for this, but it struggles with data-sparse scenarios and complex user-item-outfit relationships. Meanwhile, existing template-based approaches are constrained by rigid pre-designed structures. To bridge these research gaps, we introduce CFALR (Collaborative Filtering-Augmented Large Language Model for Recommendation), a novel framework that synergizes collaborative filtering with large language models for personalized outfit recommendation. Specifically, CFALR describes user-outfit interactions in natural language and leverages LLMs to capture fashion semantics while employing CF-enhanced embeddings …

How Do Machine Learning Models Change?, Joel Castaño, Rafael Cabañas, Antonio Salmerón, David Lo, Silverio Martínez-Fernández

Research Collection School Of Computing and Information Systems

The proliferation of Machine Learning (ML) models and their open source implementations has transformed AI research and applications. Platforms like Hugging Face (HF) enable this evolving ecosystem, yet a large-scale longitudinal study of how these models change is lacking. This study addresses this gap by analyzing over 680,000 commits from 100,000 models and 2,251 releases from 202 of these models on HF using repository mining and longitudinal methods. We apply an extended ML change taxonomy to classify commits and use Bayesian networks to model temporal patterns in commit and release activities. Our findings show that commit activities align with established …

Ai, Medicine, And Social Determinants Of Health Data, Ryan Doyloo, Nicholson Price

Articles

This article examines how medical AI systems are incorporating SDoH data and the governance challenges that follow. The authors show that while SDoH integration can enhance clinical workflows and predictive accuracy — potentially improving outcomes for underserved populations — it also introduces acute risks of proxy discrimination, where facially neutral variables replicate protected characteristics. Surveying U.S., EU, and international frameworks, the authors argue that existing regimes lack clear ex ante guidance to distinguish beneficial from harmful uses of SDoH data. In response, they advance post-market monitoring as a pragmatic and scalable pathway: generating real-world, SDoH-stratified evidence that can support enforcement, …

Principles Of Privacy And Security In Artificial Intelligence And Applications, Khang Tran

Dissertations

Modern artificial intelligence (AI) systems have transformed critical domains such as healthcare, software engineering, finance, and the legal system. Despite their broad impact, concerns about trustworthiness, especially regarding privacy and security, remain major obstacles to wider adoption. Addressing these concerns requires both a systematic understanding of the privacy and security risks inherent in AI systems and the development of principled foundations for trustworthy AI that safeguard client privacy and security. This goal is particularly challenging because of the complexity of modern large-scale AI systems, the trade-offs between privacy and model utility, and the need to simultaneously ensure other important properties …

Holistic Dram Enhancements: From Intrinsic In-Memory Operations To Robust Security Mechanisms, Ranyang Zhou

Dissertations

Dynamic Random-Access Memory (DRAM) is both the performance bottleneck and a critical security boundary of modern computing systems. Its physical properties make it an attractive substrate for near-data computation—yet those same properties expose it to disturbance-based hardware attacks. This dissertation argues that these two dimensions are not independent: the architectural choices that make DRAM efficient also reshape its threat landscape. Addressing both requires a unified approach to memory architecture and security co-design.

The first part of this dissertation attacks the memory wall through four processing-in-DRAM (PIM) frameworks. ReD-LUT and LT-PIM unify lookup-table arithmetic with charge-sharing logic, achieving up to 37.8x …

A Generative Ai-Driven Computational Framework For Industry-Scale Discovery Of Novel Battery Materials, Joy Datta

Dissertations

The growing demand for sustainable, high-energy-density electrochemical storage has motivated the exploration of multivalent-ion batteries based on earth-abundant elements such as aluminum, calcium, magnesium, and zinc. While multivalent charge carriers offer higher theoretical energy density than lithium, their practical deployment is hindered by sluggish ion transport, strong ion-host interactions, and structural degradation of electrode materials. Identifying host materials that can reversibly accommodate multivalent ions while maintaining structural integrity remains a fundamental challenge. The dissertation develops a scalable, end-to-end computational framework that integrates density functional theory (DFT), machine learning (ML), and generative artificial intelligence (GenAI) to accelerate the discovery of next-generation …

Toward Learning-Based Reconstruction And Part Decomposition Of Man-Made 3d Geometry: Neural Implicit Representations And Scalable Supervision, Shen Fan

Dissertations

Digital three-dimensional (3D) models are central to engineering design, analysis, and manufacturing, but learning pipelines for man-made geometry often operate on sampled carriers that do not preserve all of the structure present in exact CAD representations. This dissertation studies learning-based reconstruction and part decomposition for structured man-made 3D geometry, from general object benchmarks to CAD-derived datasets, with a focus on neural implicit representations trained from signed-distance samples, point clouds, and tessellated meshes. The goal is to make these models more accurate, more part-aware, and more consistently supervised.

First, signed distance function (SDF) reconstruction with implicit neural representations is improved through …

Edge Co-Occurrence Regularization For Node Classification, Kadir Altunel

Theses

We propose a simple yet effective regularization technique for node classification on graphs that leverages edge-based label co-occurrence patterns. We first train an MLP on node features to produce class probability distributions, then compute a fixed penalty matrix from edge-based co-occurrence statistics of these predictions. This penalty matrix, which captures unlikely class combinations on connected nodes, is then used to regularize GNN training without further updates. We evaluate this approach across multiple homophilic datasets (Cora, CiteSeer, PubMed, ogbn-arxiv) and heterophilic benchmarks (Chameleon, Squirrel, Actor, Roman-Empire) using three GNN architectures: GCN, GraphSAGE, and H2GCN. Results show consistent improvements on homophilic graphs, …