Browsing Like Human: A Multimodal Web Agent With Experiential Fast-And-Slow Thinking,
2025
Singapore Management University
Browsing Like Human: A Multimodal Web Agent With Experiential Fast-And-Slow Thinking, Haohao Luo, Jiayi Kuang, Wei Liu, Ying Shen, Jian Luan, Yang Deng
Research Collection School Of Computing and Information Systems
Automating web navigation which aims to build a web agent that follows user instructions to complete tasks like booking flights by interacting with websites, has received increasing attention due to its practical value. Although existing web agents are mostly equipped with visual perception, planning, and memory abilities, their reasoning process are still deviate from human cognition. In this work, we study the human thought pattern to empower agent with more human-like abilities in web navigation. To tackle this problem, we propose a novel multimodal web agent framework called WebExperT, which is designed to emulate the human planning process of “thinking …
Mpo: Multilingual Safety Alignment Via Reward Gap Optimization,
2025
Singapore Management University
Mpo: Multilingual Safety Alignment Via Reward Gap Optimization, Weixiang Zhao, Yulin Hu, Yang Deng, Tongtong Wu, Wenxuan Zhang, Jiahe Guo, An Zhang, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu
Research Collection School Of Computing and Information Systems
Large language models (LLMs) have become increasingly central to AI applications worldwide, necessitating robust multilingual safety alignment to ensure secure deployment across diverse linguistic contexts. Existing preference learning methods for safety alignment, such as RLHF and DPO, are primarily monolingual and struggle with noisy multilingual data. To address these limitations, we introduce Multilingual reward gaP Optimization (MPO), a novel approach that leverages the well-aligned safety capabilities of the dominant language (e.g., English) to improve safety alignment across multiple languages. MPO directly minimizes the reward gap difference between the dominant language and target languages, effectively transferring safety capabilities while preserving the …
Think Both Ways: Teacher-Student Bidirectional Reasoning Enhances Mcq Generation And Distractor Quality,
2025
Singapore Management University
Think Both Ways: Teacher-Student Bidirectional Reasoning Enhances Mcq Generation And Distractor Quality, Yimiao Qiu, Yang Deng, Quanming Yao, Zhimeng Zhang, Zhiang Dong, Chang Yao, Jingyuan Chen
Research Collection School Of Computing and Information Systems
Generating high-quality Multiple Choice Questions (MCQs) remains challenging for educational tools due to the need for contextual relevance and plausible distractors. Existing methods still struggle with these dual requirements, leading to questions that lack depth and distractors that are either too obvious or irrelevant. In this paper, we propose BiFlow, a novel framework that integrates bidirectional reasoning perspectives: teacher reasoning generates contextually relevant questions and plausible distractors, while student reasoning evaluates question clarity and the misleading nature of the distractors. To further enhance reasoning, we introduce PathFinder, a mechanism that employs breadth-first search and Chainof-Thought (CoT) strategies to explore diverse …
Bhvit: Binarized Hybrid Vision Transformer,
2025
Singapore Management University
Bhvit: Binarized Hybrid Vision Transformer, Tian Gao, Yu Zhang, Zhiyuan Zhang, Huajun Liu, Kaijie Yin, Chengzhong Xu, Hui Kong
Research Collection School Of Computing and Information Systems
Model binarization has made significant progress in enabling real-time and energy-efficient computation for con-volutional neural networks (CNN), offering a potential solution to the deployment challenges faced by Vision Transformers (ViTs) on edge devices. However, due to the structural differences between CNN and Transformer architectures, simply applying binary CNN strategies to the ViT models will lead to a significant performance drop. To tackle this challenge, we propose BHViT, a binarization-friendly hybrid ViT architecture and its full binarization model with the guidance of three important observations. Initially, BHViT utilizes the local information interaction and hierarchical feature aggregation technique from coarse to fine …
Other Orienteering Problem Variants,
2025
Singapore Management University
Other Orienteering Problem Variants, Pieter Vansteenwegen, Aldy Gunawan
Research Collection School Of Computing and Information Systems
In this chapter, different variants of routing problems with profits will be discussed. Based on what is available in literature, mostly variants of the orienteering problem will be discussed. A first variant considers capacity constraints, since these appear frequently in many practical applications. Next, multi-objective orienteering problems, explicitly considering different types of profits separately are discussed. Time-dependent and stochastic travel times are also relevant for most practical applications. These are considered together with time-dependent and stochastic profits. More and more routing problems are considered together with inventory management. For routing problems with profits, this leads to the inventory orienteering problem, …
Optimal Transport Alignment Of User Preferences From Ratings And Texts,
2025
Singapore Management University
Optimal Transport Alignment Of User Preferences From Ratings And Texts, Nhu Thuat Tran, Hady Wirawan Lauw
Research Collection School Of Computing and Information Systems
Modeling hidden factors driving user preferences is crucial for recommendation yet challenging due to sparse rating data. While aligning preference factors from ratings and texts, as a solution, shows improvements, existing methods impose restrictive one-to-one factor correspondences and underutilize cross-modal interest signals. We propose an optimal transport (OT) approach to address these gaps. By modeling rating- and text-based preference factors as distributions, we compute an OT plan that captures their probabilistic relationships. This plan serves dual roles: 1) to regularize cross-modal preference factors without rigid correspondence assumptions, and 2) to blend preference signals across modalities through barycentric mapping. Experiments on …
Explainable Multimodal Sentiment Analysis Of Social Media Visual Content For Child Safety,
2025
Singapore Management University
Explainable Multimodal Sentiment Analysis Of Social Media Visual Content For Child Safety, Yee Sen Tan, Zhaoxia Wang
Research Collection School Of Computing and Information Systems
Ensuring the safety and well-being of children is increasingly important, especially in a world where visual content is pervasive. This paper proposes a novel multimodal, multilingual, and multiclass sentiment analysis method for social media content, aimed at improving content moderation for child safety. Our approach integrates textual, visual, and audio data from videos, categorizing sentiment into four levels: positive, slightly negative, negative, and strongly negative, enabling granular detection of harmful content. To enhance explainability and trust, we also leverage interpretable mechanisms to analyze the contributions of each modality. Evaluation of our method demonstrates strong generalization across diverse video types, and …
Rl4co: An Extensive Reinforcement Learning For Combinatorial Optimization Benchmark,
2025
Singapore Management University
Rl4co: An Extensive Reinforcement Learning For Combinatorial Optimization Benchmark, Federico Berto, Et. Al
Research Collection School Of Computing and Information Systems
Combinatorial optimization (CO) is fundamental to several real-world applications, from logistics and scheduling to hardware design and resource allocation. Deep reinforcement learning (RL) has recently shown significant benefits in solving CO problems, reducing reliance on domain expertise and improving computational efficiency. However, the absence of a unified benchmarking framework leads to inconsistent evaluations, limits reproducibility, and increases engineering overhead, raising barriers to adoption for new researchers. To address these challenges, we introduce RL4CO, a unified and extensive benchmark with in-depth library coverage of 27 CO problem environments and 23 state-of-the-art baselines. Built on efficient software libraries and best practices in …
Eformer: An Effective Edge-Based Transformer For Vehicle Routing Problems,
2025
Singapore Management University
Eformer: An Effective Edge-Based Transformer For Vehicle Routing Problems, Dian Meng, Zhiguang Cao, Yaoxin Wu, Yaqing Hou, Hongwei Ge, Qiang Zhang
Research Collection School Of Computing and Information Systems
Recent neural heuristics for the Vehicle Routing Problem (VRP) primarily rely on node coordinates as input, which may be less effective in practical scenarios where real cost metrics--such as edge-based distances--are more relevant. To address this limitation, we introduce EFormer, an Edge-based Transformer model that uses edge as the sole input for VRPs. Our approach employs a precoder module with a mixed-score attention mechanism to convert edge information into temporary node embeddings. We also present a parallel encoding strategy characterized by a graph encoder and a node encoder, each responsible for processing graph and node embeddings in distinct feature spaces, …
Use Of A Preliminary Artificial Intelligence-Based Laryngeal Cancer Screening Framework For Low-Resource Settings: Development And Validation Study,
2025
Singapore Management University
Use Of A Preliminary Artificial Intelligence-Based Laryngeal Cancer Screening Framework For Low-Resource Settings: Development And Validation Study, Shao Wei Sean Lam, Min Hun Lee, Michael Dorosan, Samuel Altonji, Hiang Khoon Tan, Walter T. Lee
Research Collection School Of Computing and Information Systems
Background: Early-stage diagnosis of laryngeal cancer significantly improves patient survival and quality of life. However, the scarcity of specialists in low-resource settings hinders the timely review of flexible nasopharyngoscopy (FNS) videos, which are essential for accurate triage of at-risk patients.Objective: We introduce a preliminary AI-based screening framework to address this challenge for the triaging of at-risk patients in low-resource settings. This formative research addresses multiple challenges common in high-dimensional FNS videos: (1) selecting clear, informative images; (2) deriving regions within frames that show an anatomical landmark of interest; and (3) classifying patients into referral grades based on the FNS video …
Ai-Assisted Triage And Decision Support Of Head And Neck Cancer Screening And Diagnosis In Low-Resourced Settings,
2025
Singapore Management University
Ai-Assisted Triage And Decision Support Of Head And Neck Cancer Screening And Diagnosis In Low-Resourced Settings, Min Hun Lee, Sean Shao Wei Lam, Shaun Xin Hong Liew, Michael Dorosan, Nicholas Graves, Jonas Karlström, Hiang Khoon Tan, Walter Tsong Lee
Research Collection School Of Computing and Information Systems
The mortality burden of head and neck cancer (HNC) is increasing globally and disproportionately affects people in low-and middle-income countries with limited medical workforce. To address this issue, artificial intelligence (AI) algorithms are increasingly being explored to process medical imaging data, demonstrating competitive performance. However, the clinical adoption of AI remains challenging as clinicians struggle to understand how complex AI works and trust it to use in practice. In addition, AI may not perform well on varying data qualities of endoscopy videos for HNC screening and diagnosis from multiple sites.In this project, our international and interdisciplinary team will collaborate with …
Faithfulrag: Fact-Level Conflict Modeling For Context-Faithful Retrieval-Augmented Generation,
2025
Singapore Management University
Faithfulrag: Fact-Level Conflict Modeling For Context-Faithful Retrieval-Augmented Generation, Qinggang Zhang, Zhishang Xiang, Yilin Xiao, Le Wang, Junhui Li, Xinrun Wang, Jinsong Su
Research Collection School Of Computing and Information Systems
Large language models (LLMs) augmented with retrieval systems have demonstrated significant potential in handling knowledge-intensive tasks. However, these models often struggle with unfaithfulness issues, generating outputs that either ignore the retrieved context or inconsistently blend it with the LLM’s parametric knowledge. This issue is particularly severe in cases of knowledge conflict, where the retrieved context conflicts with the model’s parametric knowledge. While existing faithful RAG approaches enforce strict context adherence through well-designed prompts or modified decoding strategies, our analysis reveals a critical limitation: they achieve faithfulness by forcibly suppressing the model’s parametric knowledge, which undermines the model’s internal knowledge structure …
Debate, Reflect, And Distill: Multi-Agent Feedback With Tree-Structured Preference Optimization For Efficient Language Model Enhancement,
2025
Singapore Management University
Debate, Reflect, And Distill: Multi-Agent Feedback With Tree-Structured Preference Optimization For Efficient Language Model Enhancement, Xiaofeng Zhou, Heyan Huang, Lizi Liao
Research Collection School Of Computing and Information Systems
Large Language Models (LLMs) continue to set new standards in knowledge-intensive and complex reasoning tasks, yet their high computational demands limit widespread adoption. While distilling large models into smaller ones offers a sustainable solution, current techniques—such as static knowledge distillation, resource-intensive reinforcement learning from human feedback, or limited self-reflection—struggle to yield substantial and lasting performance gains. In this paper, we present a novel Debate and Reflect (D&R) framework that orchestrates multi-turn debates between smaller models and stronger teacher models, eliciting actionable feedback (e.g., error analysis, corrective strategies) to guide student models. Further, we introduce Tree-structured Direct Preference Optimization (T-DPO) to …
Memotune: A Measure And Moment-Driven Fine-Tuning Framework For Quantized Large Language Models,
2025
Singapore Management University
Memotune: A Measure And Moment-Driven Fine-Tuning Framework For Quantized Large Language Models, Yun Zhang, Xue Geng, Lizi Liao, Jintong Sun, Minghe Yu, Ge Yu
Research Collection School Of Computing and Information Systems
Quantizing large language models (LLMs) is essential for reducing memory and computational costs in natural language processing. Existing methods combine quantization with parameter-efficient fine-tuning but often fail to meet practical performance requirements. This paper introduces MeMoTune, a novel fine-tuning framework for quantized LLMs. By employing a measure and moment approach within a low-rank approximation framework in probability measure space, MeMoTune optimizes the objective function for superior fine-tuning results. The update process is further refined through scaled gradient, enhancing convergence efficiency and noise robustness. Experiments on tasks like text generation, summarization, and understanding show MeMoTune significantly outperforms state-of-the-art methods, e.g. fine-tuning …
Xfinbench: Benchmarking Llms In Complex Financial Problem Solving And Reasoning,
2025
Singapore Management University
Xfinbench: Benchmarking Llms In Complex Financial Problem Solving And Reasoning, Zhihan Zhang, Yixin Cao, Lizi Liao
Research Collection School Of Computing and Information Systems
Solving financial problems demands complex reasoning, multimodal data processing, and a broad technical understanding, presenting unique challenges for current large language models (LLMs). We introduce **XFinBench**, a novel benchmark with 4,235 examples designed to evaluate LLM’s ability in solving comple**X**, knowledge-intensive **Fin**ancial problems across diverse graduate-level finance topics with multi-modal context. We identify five core capabilities of LLMs using XFinBench, i.e., _terminology understanding_, _temporal reasoning_, _future forecasting_, _scenario planning_, and _numerical modelling_. Upon XFinBench, we conduct extensive experiments on 18 leading models. The result shows that o1 is the best-performing text-only model with an overall accuracy of 67.3%, but still …
Connecting Giants: Synergistic Knowledge Transfer Of Large Multimodal Models For Few-Shot Learning,
2025
Singapore Management University
Connecting Giants: Synergistic Knowledge Transfer Of Large Multimodal Models For Few-Shot Learning, Hao Tang, Shengfeng He, Jing Qin
Research Collection School Of Computing and Information Systems
Few-shot learning (FSL) addresses the challenge of classifying novel classes with limited training samples. While some methods leverage semantic knowledge from smaller-scale models to mitigate data scarcity, these approaches often introduce noise and bias due to the data's inherent simplicity. In this paper, we propose a novel framework, Synergistic Knowledge Transfer (SYNTRANS), which effectively transfers diverse and complementary knowledge from large multimodal models to empower the off-the-shelf few-shot learner. Specifically, SYNTRANS employs CLIP as a robust teacher and uses a few-shot vision encoder as a weak student, distilling semantic-aligned visual knowledge via an unsupervised proxy task. Subsequently, a training-free synergistic …
Starpose: 3d Human Pose Estimation Via Spatial-Temporal Autoregressive Diffusion,
2025
Singapore Management University
Starpose: 3d Human Pose Estimation Via Spatial-Temporal Autoregressive Diffusion, Haoxin Yang, Weihong Chen, Xuemiao Xu, Cheng Xu, Peng Xiao, Cuifeng Sun, Shaoyu Huang, Shengfeng He
Research Collection School Of Computing and Information Systems
Monocular 3D human pose estimation remains a challenging task due to inherent depth ambiguities and occlusions. Compared to traditional methods based on Transformers or Convolutional Neural Networks (CNNs), recent diffusionbased approaches have shown superior performance, leveraging their probabilistic nature and high-fidelity generation capabilities. However, these methods often fail to account for the spatial and temporal correlations across predicted frames, resulting in limited temporal consistency and inferior accuracy in predicted 3D pose sequences. To address these shortcomings, this paper proposes StarPose, an autoregressive diffusion framework that effectively incorporates historical 3D pose predictions and spatialtemporal physical guidance to significantly enhance both the …
Sifar: A Simple Faster Accelerated Variance‑Reduced Gradient Method,
2025
Singapore Management University
Sifar: A Simple Faster Accelerated Variance‑Reduced Gradient Method, Zhize Li
Research Collection School Of Computing and Information Systems
In this paper, we propose a simple faster accelerated gradient method called SIFAR for solving the finite-sum optimization problems. Concretely, we consider both general convex and strongly convex settings: i) For general convex finite-sum problems, SIFAR improves previous state-of-the-art result given by Varag. In particular, for large-scale problems or the convergence error is not very small, SIFAR obtains the first optimal result O(n), matching the lower bound. ii) For strongly convex finite-sum problems, we also show that SIFAR can achieve the optimal convergence rate matching the lower bound. Besides, SIFAR enjoys a simpler loopless algorithmic structure while previous algorithms use …
From Risk To Resilience: Towards Assessing And Mitigating The Risk Of Data Reconstruction Attacks In Federated Learning,
2025
Singapore Management University
From Risk To Resilience: Towards Assessing And Mitigating The Risk Of Data Reconstruction Attacks In Federated Learning, Xiangrui Xu, Zhize Li, Yufei Han, Bin Wang, Jiqiang Liu, Wei Wang
Research Collection School Of Computing and Information Systems
Data Reconstruction Attacks (DRA) pose a significant threat to Federated Learning (FL) systems by enabling adversaries to infer sensitive training data from local clients. Despite extensive research, the question of how to characterize and assess the risk of DRAs in FL systems remains unresolved due to the lack of a theoretically-grounded risk quantification framework. In this work, we address this gap by introducing Invertibility Loss (InvLoss) to quantify the maximum achievable effectiveness of DRAs for a given data instance and FL model. We derive a tight and computable upper bound for InvLoss and explore its implications from three perspectives. First, …
L2m2: A Hierarchical Framework Integrating Large Language Model And Multi‑Agent Reinforcement Learning,
2025
Singapore Management University
L2m2: A Hierarchical Framework Integrating Large Language Model And Multi‑Agent Reinforcement Learning, Minghong Geng, Shubham Pateria, Budhitama Subagdja, Lin Li, Xin Zhao, Ah-Hwee Tan
Research Collection School Of Computing and Information Systems
Multi-agent reinforcement learning (MARL) has demonstrated remarkable success in collaborative tasks, yet faces significant challenges in scaling to complex scenarios requiring sustained planning and coordination across long horizons. While hierarchical approaches help decompose these tasks, they typically rely on hand-crafted subtasks and domain-specific knowledge, limiting their generalizability. We present L2M2, a novel hierarchical framework that leverages large language models (LLMs) for high-level strategic planning and MARL for low-level execution. L2M2 enables zero-shot planning that supports both end-to-end training and direct integration with pre-trained MARL models. Experiments in the VMAS environment demonstrate that L2M2's LLM-guided MARL achieves superior performance while requiring …
