Showing 1–50 of 128 results for author: Ng, M

RecPFN: Prior-Fitted Networks for In-Context-Based Recommendations

Authors: En Zhi Tan, Jia Xiang Lim, Bryan Lijie Chew, Tze Minh Ng, Benjamin Yan Han Yap

Abstract: We introduce RecPFN, a prior-fitted network that brings in-context learning to sequential recommendation. RecPFN is pretrained entirely on synthetic clickstream environments sampled from a broad structural causal prior, enabling it to amortize Bayesian-style inference from a small support set. At inference, a lightweight decoder-only transformer conditions on a handful of domain sequences and prod… ▽ More We introduce RecPFN, a prior-fitted network that brings in-context learning to sequential recommendation. RecPFN is pretrained entirely on synthetic clickstream environments sampled from a broad structural causal prior, enabling it to amortize Bayesian-style inference from a small support set. At inference, a lightweight decoder-only transformer conditions on a handful of domain sequences and produces next-item predictions for queries in a single forward pass, without any weight updates. Across eight public benchmarks, RecPFN achives state-of-the-art zero-shot performance while remaining strongly competitive with supervised methods in low-compute and low-data regimes. It is deployment-efficient and robust to domain shift, outperforming strong zero-shot baselines that rely on large real-interaction corpora. RecPFN provides a practical path toward generalizable, data-efficient recommenders and opens avenues for richer priors, longer-context ICL, and multimodal extensions. Code for training and evaluation is publicly available at https://github.com/SAP-samples/tabular-ai-recpfn/. △ Less

Submitted 20 August, 2026; originally announced August 2026.

Comments: 12 pages, 4 figures, 8 tables

Journal ref: In Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1731-1742. 2026

HoloAegis: Frozen Representation, Topological Inference: Minimally Parametric Safety Manifolds for Zero-Shot LLM Guardrails

Authors: Tak Ho Alex Li, Kaijie Liu, Lik-Hang Lee, Kin Chung Ho, Ping Shum, Michael K. Ng

Abstract: Current LLM safety guardrails face a fundamental tension: fine-tuning distorts pre-trained representations while generative judges incur prohibitive inference costs. We challenge the prevailing paradigm by asking: can safety be achieved through pure geometric reasoning over frozen semantic representations? We present HoloAegis, a minimally parametric topological inference framework that decouples… ▽ More Current LLM safety guardrails face a fundamental tension: fine-tuning distorts pre-trained representations while generative judges incur prohibitive inference costs. We challenge the prevailing paradigm by asking: can safety be achieved through pure geometric reasoning over frozen semantic representations? We present HoloAegis, a minimally parametric topological inference framework that decouples representation from reasoning. We term our approach minimally parametric because the only free parameters are the anchor count K and the temperature tau, both fixed after construction and requiring no gradient-based training. An un-fine-tuned encoder maps text to a unit sphere, after which all decisions are purely geometric. We formalize safety evaluation as a Gibbs-Boltzmann Free Energy computation over a pre-computed System Topology Anchor Bank, and we introduce Dual Time-Scale Exponential Moving Averages to detect progressive multi-turn semantic drift. Our key theoretical insight is a Topological Boundary Stability Conjecture: we provide theoretical motivation and strong empirical evidence that sparse anchor centroids stabilize the decision boundary against high-frequency lexical perturbations far better than full vector space methods. Evaluated across 8 benchmarks, HoloAegis achieves state-of-the-art accuracy (1.0000 AUC on AuthenHallu, 0.9802 on HarmBench) with sub-millisecond latency, zero cold-start data, and cross-lingual transfer (0.9758 AUC on Chinese CHIFRAUD). △ Less

Submitted 9 August, 2026; originally announced August 2026.

Comments: Preprint, August 2026. 10 tables, 2 figures

MSC Class: 68T05; 68T99 ACM Class: I.2.0; I.2.6

TREK: A Travel Reasoning and Evaluation Kit for LLM Agents in Complex Trip Planning

Authors: Jinhu Qi, Wentao Zhang, Siu Man Ng, Feiyang Xu, Yanyu Chen, Yaoman Li, Irwin King

Abstract: Travel planning is a demanding stress test for tool-using LLM agents: a usable itinerary is a single artifact that must be right along many axes at once - every flight, hotel, and attraction must exist and be bookable, the days must be physically traversable, the total must clear a budget, and the plan must serve a traveler whose needs are only partly stated. Existing agent benchmarks reward these… ▽ More Travel planning is a demanding stress test for tool-using LLM agents: a usable itinerary is a single artifact that must be right along many axes at once - every flight, hotel, and attraction must exist and be bookable, the days must be physically traversable, the total must clear a budget, and the plan must serve a traveler whose needs are only partly stated. Existing agent benchmarks reward these properties one at a time and grade the final output with soft or LLM-judged rubrics, which cannot certify that a returned plan is executable and are neither reproducible nor auditable. We introduce TREK (Travel Reasoning and Evaluation Kit), a benchmark for feasible itinerary synthesis: producing a single plan that is jointly constraint-correct, hallucination-free, spatio-temporally executable, budget-valid, and responsive to the traveler's unstated persona needs. TREK comprises 800 multi-constraint tasks - 533 feasible and 267 provably infeasible with typed route/entity/budget causes - over a synthetic, internally consistent knowledge base of 212,530 records across 375 cities and 13 personas, served through a production-style tool sandbox of validated RESTful APIs. Every task is scored by a fully deterministic, rule-based evaluator with no LLM judge and ships a human-verified gold reference that scores a perfect 1.0 under that same evaluator, so the ceiling is demonstrably achievable and every remaining gap is an agent limitation rather than scorer strictness. Evaluating 15 LLM agents across nine constraint dimensions, we find that even the strongest (GPT-5.6) produces a fully-feasible plan on only 46.2% of solvable tasks, with a median of 6.6% and a floor of 0.0%; satisfying travelers' unstated needs emerges as the universal bottleneck, unsolved even at the frontier. We release the dataset, tool sandbox, deterministic evaluator, and agent code as a fully reproducible benchmark. △ Less

Submitted 9 August, 2026; v1 submitted 29 July, 2026; originally announced July 2026.

Comments: Code, data, and evaluator: https://github.com/TonyQJH/TREK-A-Travel-Reasoning-and-Evaluation-Kit-for-LLM-Agents-in-Complex-Trip-Planning

GeoThreat: Transferable Targeted Adversarial Attacks on Large Vision-Language Models for Remote Sensing Image Interpretation

Authors: Yimin Fu, Yuefeng Bai, Baicheng Pan, Zhunga Liu, Michael K. Ng

Abstract: Adversarial attacks against large vision-language models (LVLMs) serve as an effective means of assessing their robustness in cross-modal semantic understanding. Existing studies mainly focus on corrupting visual inputs to induce predefined erroneous responses in general vision-language tasks, whereas corresponding investigations in remote sensing fields remain largely underexplored. Compared with… ▽ More Adversarial attacks against large vision-language models (LVLMs) serve as an effective means of assessing their robustness in cross-modal semantic understanding. Existing studies mainly focus on corrupting visual inputs to induce predefined erroneous responses in general vision-language tasks, whereas corresponding investigations in remote sensing fields remain largely underexplored. Compared with natural image understanding, remote sensing image interpretation requires joint reasoning over local discriminative cues and global scene context. This poses additional challenges to achieving transferable semantic manipulation toward specified responses under black-box settings. To tackle these challenges, we propose GeoThreat, a transferable targeted adversarial attack method against LVLMs for remote sensing image interpretation. Specifically, GeoThreat modulates adversarial representations in accordance with the target content at both conceptual and perceptual levels. The class tokens from surrogate image encoders are employed as conceptual representations, while perceptual representations are distilled from patch tokens of the adversarial example through collaborative importance estimation. Beyond merely rolling out attention scores across layers, we incorporate adversarial-target similarity gradients to more faithfully characterize the relevance of local visual cues to the intended semantic manipulation. The perceptual representations are then dynamically aligned with target patch tokens in a cross-attentive manner, facilitating the adaptation of local cues toward designated semantic details. Finally, adversarial perturbations are iteratively updated via ensemble-based joint optimization of conceptual calibration and perceptual adaptation. Extensive experiments across diverse LVLMs demonstrate the superiority of GeoThreat in both transferability and controllability. △ Less

Submitted 23 July, 2026; originally announced July 2026.

Comments: The code will be released at https://github.com/fuyimin96/GeoThreat upon acceptance

Enhancing the KidSat Model: Integrating Geographical Encoding and Data Quality Assessment for Childhood Poverty Prediction

Authors: Hou Hin Ip, Ka Nam Lam, Joshua Man Yu Ng, Makkunda Sharma, Seth Flaxman, Codie Gerlach-Wood, H Juliette T Unwin

Abstract: Accurate poverty mapping using satellite imagery is often hindered by (i) noisy and sparse survey-derived supervision, (ii) image quality issues such as cloud cover and image corruption, and (iii) lack of explicit spatial structure in image-only models. Building on the KidSat framework, we develop an enhanced pipeline that improves predictive accuracy via refined data preprocessing, systematic ima… ▽ More Accurate poverty mapping using satellite imagery is often hindered by (i) noisy and sparse survey-derived supervision, (ii) image quality issues such as cloud cover and image corruption, and (iii) lack of explicit spatial structure in image-only models. Building on the KidSat framework, we develop an enhanced pipeline that improves predictive accuracy via refined data preprocessing, systematic image quality assessment, and mathematically defined geographic encoding. First, we refine the fine-tuning target matrix by resolving high-cardinality sparsity and reducing one-hot dimensionality from 103 to 51 via DHS re-aggregation. Second, we introduce a simple two-stage quality-screening procedure to filter heavily clouded or corrupted observations. Third, we fuse DINOv2 visual embeddings with Spherical Harmonics (SH) location features. Across extensive experiments, these changes reduce MAE from 0.2167 to 0.1759, corresponding to an 18.83% relative reduction on the cluster-level severe-deprivation proportion scale. When extended from 16 to 33 African countries, the best-performing configuration achieves an overall MAE of 0.1658. We find that SH features consistently improve performance over the image-only backbone, whereas higher-capacity coordinate Multi Layer Perception augmentation (SH+SIREN) can underperform without carefully designed objectives. Finally, gradient-boosted tree heads (XGBoost/LightGBM) most effectively exploit nonlinear interactions in the fused visual-geographic representation. These findings provide a scalable and principled recipe for improving satellite-based socioeconomic predictions using only publicly accessible data. △ Less

Submitted 9 July, 2026; originally announced July 2026.

Transferable Self-Evolving Playbooks for Agentic Security Auditing

Authors: Ziyue Wang, Cheuk Wang Maurice Ng, Chenchen Yu, Strick Sheng, Kaihua Qin, Liyi Zhou

Abstract: An LLM agent for vulnerability discovery and validation is more than a model. It combines three components: an LLM for code analysis, an agent harness such as Codex or OpenCode for navigation, tool use, and execution, and an audit playbook, domain-specific procedural knowledge that guides the LLM and harness toward vulnerability discovery. Prior work relies on human-supplied playbooks, including p… ▽ More An LLM agent for vulnerability discovery and validation is more than a model. It combines three components: an LLM for code analysis, an agent harness such as Codex or OpenCode for navigation, tool use, and execution, and an audit playbook, domain-specific procedural knowledge that guides the LLM and harness toward vulnerability discovery. Prior work relies on human-supplied playbooks, including prompt engineering, manual workflows, knowledge bases, and heuristics. This raises two research questions: Acquisition - is human curation necessary, and can playbook creation be automated? Transfer - can an evolved playbook transfer the audit procedure to weaker agents, improving their capability? We present EvoHunt, a playbook evolution environment over open-source repositories for security auditing. Three agents drive the evolution loop: an audit agent rolls out the current playbook and produces findings; an evaluator scores outcomes against ground truth; and a reviser commits updates to the playbook based on failure analysis. The playbook format is unconstrained: starting empty, EvoHunt adds or removes workflows, heuristics, vulnerability knowledge, or domain-specific content. The evolved playbook requires only minor adaptation to run under a different LLM or harness. We evaluate EvoHunt on open-source security advisories. For acquisition, playbook evolution raises end-to-end exploits for Codex/GPT5.4-xhigh 6x, from 1.1% to 6.2%, and the evolved OpenCode/GLM5.1 playbook surpasses OpenAI Codex Security on every metric, with 11.3% vs. 9.2% target-match rate, showing open-source evolution can outperform a dedicated commercial product. For transfer, the GLM-evolved playbook gives the strongest student lift: Qwen3.6-27B improves from 2.4% to 6.5%, Qwen3.6-35B-A3B from 1.1% to 4.6%, and A3B obtains 2.4x more matches than GPT transfer. △ Less

Submitted 15 June, 2026; originally announced June 2026.

Hardware-accelerated Aggregation: Unification and Specialization

Authors: Alireza Shateri, Hongshi Tan, Michael Ng, Bingsheng He, Qizhen Zhang

Abstract: The high efficiency of domain-specific hardware has sparked substantial interest in adopting accelerators in data analytics systems. Among many choices, GPUs and FPGAs thrived as two popular solutions due to their prevalent deployments in cloud data centers. This paper investigates hardware acceleration solutions for aggregation, a critical data analytics operation. Specifically, we implement aggr… ▽ More The high efficiency of domain-specific hardware has sparked substantial interest in adopting accelerators in data analytics systems. Among many choices, GPUs and FPGAs thrived as two popular solutions due to their prevalent deployments in cloud data centers. This paper investigates hardware acceleration solutions for aggregation, a critical data analytics operation. Specifically, we implement aggregation with a unified hardware acceleration framework, which trades efficiency for ease of programming and portability, and then further develop hardware-specific optimizations. We evaluate these solutions on three recent computing hardware platforms: a CPU, a GPU, and an FPGA, with metrics that cover both the performance and energy consumption of on-device and end-to-end processing. △ Less

Submitted 8 June, 2026; originally announced June 2026.

ACM Class: H.2.2; B.2.4

Beyond Homophily: Towards Generalized Graph Reconstruction Attack and Defense

Authors: Zhanke Zhou, Bo Han, Xuan Li, Jiangchao Yao, Sanmi Koyejo, Michael K. Ng

Abstract: Graph neural networks (GNNs) are widely deployed on relational data, yet they can leak sensitive or proprietary information about the training graph adjacency, e.g., social ties, transactions, and interactions. This work studies graph reconstruction attacks (GRA), a form of model inversion that reconstructs the training adjacency from a trained GNN, given different levels of attacker-side informat… ▽ More Graph neural networks (GNNs) are widely deployed on relational data, yet they can leak sensitive or proprietary information about the training graph adjacency, e.g., social ties, transactions, and interactions. This work studies graph reconstruction attacks (GRA), a form of model inversion that reconstructs the training adjacency from a trained GNN, given different levels of attacker-side information. We first provide a systematic characterization of when and why adjacency becomes recoverable through features, labels, embeddings, and predictions, with leakage modulated by graph homophily, heterophily, and the model's inductive bias. Motivated by these findings, we view GNN inference through a Markov chain approximation lens, treating the layered forward computation as a chain of topology-dependent representations. Building on this view, we develop complementary attack and defense methods. On the attack side, we propose MC-GRA (+), which reconstructs the adjacency by optimizing a surrogate adjacency whose GNN-induced representations align with those of the target model at each layer. On the defense side, we propose MC-GPB (+), which suppresses adjacency-dependent information throughout the representation chain while aiming to preserve classification accuracy under a privacy-utility trade-off. Experiments across homophilic/heterophilic graph benchmarks and GNNs show that our attacks improve reconstruction fidelity over prior methods, while our defenses reduce reconstruction success with only minor accuracy loss. △ Less

Submitted 6 June, 2026; originally announced June 2026.

Complex Diffusion Maps with $ω$-Parameterized Kernels Revealing Inherent Harmonic Representations

Authors: Tongzhen Dang, Weiyang Ding, Michael K. Ng

Abstract: In this paper, we propose Complex Diffusion Maps (CDM), a novel diffusion mapping framework that aims to reveal the dominant complex harmonics of high-dimensional data. Inspired by the local Gaussian kernel relevant to the heat equation and the nonlocal Schrödinger kernel relevant to the Schrödinger equation, we propose a unified family of $ω$-parameterized complex-valued kernels for the trade-off… ▽ More In this paper, we propose Complex Diffusion Maps (CDM), a novel diffusion mapping framework that aims to reveal the dominant complex harmonics of high-dimensional data. Inspired by the local Gaussian kernel relevant to the heat equation and the nonlocal Schrödinger kernel relevant to the Schrödinger equation, we propose a unified family of $ω$-parameterized complex-valued kernels for the trade-off between local and nonlocal connections. We establish the theoretical foundation based on the operator spectrum theory, where the corresponding diffusion operator, diffusion distance, and complex harmonic maps are well-defined. An optimization-based interpretation of the maps is also developed, aiming to preserve angular structure in the complex diffusion space rather than relying solely on real-valued magnitude. We extensively evaluate CDM on both synthetic and real-world datasets. The complex-valued kernel amplifies differences among easily confusable samples, improving discriminative power over both linear and nonlinear methods based on real-valued kernels. CDM remains robust in high-noise settings, yielding a clearer eigengap that enhances spectral separation. For resting-state fMRI data, CDM captures more strongly correlated and nonlocal spatiotemporal dynamics. Without task-specific tuning, CDM achieves competitive performance on a public EEG sleep dataset, while maintaining high computational efficiency compared with both traditional machine learning and deep neural network approaches, highlighting its generality and practical value. △ Less

Submitted 2 May, 2026; originally announced May 2026.

Comments: 27 pages main text, 13 pages appendix, 9 figures, 2 tables. Submitted to IEEE TPAMI. Code will be made publicly available upon acceptance

MSC Class: 68T10; 68R12; 62H30

A Layer Separation Optimization Framework for Cross-Entropy Training in Deep Learning

Authors: Yaru Liu, Michael K. Ng, Yiqi Gu

Abstract: This paper investigates the deep learning optimization problem with softmax cross-entropy loss. We propose a layer separation strategy to alleviate the strong nonconvexity encountered during training deep networks. For cross-entropy models with fully connected and convolutional neural networks, we introduce auxiliary variables associated with hidden layer outputs and construct corresponding layer… ▽ More This paper investigates the deep learning optimization problem with softmax cross-entropy loss. We propose a layer separation strategy to alleviate the strong nonconvexity encountered during training deep networks. For cross-entropy models with fully connected and convolutional neural networks, we introduce auxiliary variables associated with hidden layer outputs and construct corresponding layer separation models, which decompose the original deeply nested optimization problem into a sequence of more manageable subproblems. We also conduct theoretical analyses, proving that the new layer separation loss provides an upper bound for the original cross-entropy loss. Moreover, we design alternating minimization algorithms and prove that, under appropriate conditions, these algorithms exhibit decreasing properties of the loss function. Numerical experiments validate the effectiveness of the proposed methods and indicate improved optimization behavior, especially for fully connected and convolutional neural networks. △ Less

Submitted 25 April, 2026; originally announced April 2026.

MSC Class: 65K10; 68T07; 90C30

AROMA: Augmented Reasoning Over a Multimodal Architecture for Virtual Cell Genetic Perturbation Modeling

Authors: Zhenyu Wang, Geyan Ye, Wei Liu, Man Tat Alexander Ng

Abstract: Virtual cell modeling predicts molecular state changes under genetic perturbations in silico, which is essential for biological mechanism studies. However, existing approaches suffer from unconstrained reasoning, uninterpretable predictions, and retrieval signals that are weakly aligned with regulatory topology. To address these limitations, we propose AROMA, an Augmented Reasoning Over a Multimod… ▽ More Virtual cell modeling predicts molecular state changes under genetic perturbations in silico, which is essential for biological mechanism studies. However, existing approaches suffer from unconstrained reasoning, uninterpretable predictions, and retrieval signals that are weakly aligned with regulatory topology. To address these limitations, we propose AROMA, an Augmented Reasoning Over a Multimodal Architecture for virtual cell genetic perturbation modeling. AROMA integrates textual evidence, graph-topology information, and protein sequence features to model perturbation-target dependencies, and is trained with a two-stage optimization strategy to yield predictions that are both accurate and interpretable. We also construct two knowledge graphs and a perturbation reasoning dataset, PerturbReason, containing more than 498k samples, as reusable resources for the virtual cell domain. Experiments show that AROMA outperforms existing methods across multiple cell lines, and remains robust under zero-shot evaluation on an unseen cell line, as well as in knowledge-sparse, long-tail scenarios. Overall, AROMA demonstrates that combining knowledge-driven multimodal modeling with evidence retrieval provides a promising pathway toward more reliable and interpretable virtual cell perturbation prediction. Model weights are available at https://huggingface.co/blazerye/AROMA. Code is available at https://github.com/blazerye/AROMA. △ Less

Submitted 22 April, 2026; originally announced April 2026.

Comments: Accepted to ACL 2026 as a Findings paper. Zhenyu Wang and Geyan Ye are equal contributors; Geyan Ye is the corresponding author and project lead

Dialogue based Interactive Explanations for Safety Decisions in Human Robot Collaboration

Authors: Yifan Xu, Xiao Zhan, Akilu Yunusa Kaltungo, Ming Shan Ng, Tsukasa Ishizawa, Kota Fujimoto, Clara Cheung

Abstract: As robots increasingly operate in shared, safety critical environments, acting safely is no longer sufficient robots must also make their safety decisions intelligible to human collaborators. In human robot collaboration (HRC), behaviours such as stopping or switching modes are often triggered by internal safety constraints that remain opaque to nearby workers. We present a dialogue based framewor… ▽ More As robots increasingly operate in shared, safety critical environments, acting safely is no longer sufficient robots must also make their safety decisions intelligible to human collaborators. In human robot collaboration (HRC), behaviours such as stopping or switching modes are often triggered by internal safety constraints that remain opaque to nearby workers. We present a dialogue based framework for interactive explanation of safety decisions in HRC. The approach tightly couples explanation with constraint based safety evaluation, grounding dialogue in the same state and constraint representations that govern behaviour selection. Explanations are derived directly from the recorded decision trace, enabling users to pose causal ("Why?"), contrastive ("Why not?"), and counterfactual ("What if?") queries about safety interventions. Counterfactual reasoning is evaluated in a bounded manner under fixed, certified safety parameters, ensuring that interactive exploration does not relax operational guarantees. We instantiate the framework in a construction robotics scenario and provide a structured operational trace illustrating how constraint aware dialogue clarifies safety interventions and supports coordinated task recovery. By treating explanation as an operational interface to safety control, this work advances a design perspective for interactive, safety aware autonomy in HRC. △ Less

Submitted 10 April, 2026; v1 submitted 7 April, 2026; originally announced April 2026.

Comments: This paper has been accepted by the 2nd InterAI workshop, HRI conference 26'

Using LLM-as-a-Judge/Jury to Advance Scalable, Clinically-Validated Safety Evaluations of Model Responses to Users Demonstrating Psychosis

Authors: May Lynn Reese, Markela Zeneli, Mindy Ng, Jacob Haimes, Andreea Damien, Elizabeth Stade

Abstract: General-purpose Large Language Models (LLMs) are becoming widely adopted by people for mental health support. Yet emerging evidence suggests there are significant risks associated with high-frequency use, particularly for individuals suffering from psychosis, as LLMs may reinforce delusions and hallucinations. Existing evaluations of LLMs in mental health contexts are limited by a lack of clinical… ▽ More General-purpose Large Language Models (LLMs) are becoming widely adopted by people for mental health support. Yet emerging evidence suggests there are significant risks associated with high-frequency use, particularly for individuals suffering from psychosis, as LLMs may reinforce delusions and hallucinations. Existing evaluations of LLMs in mental health contexts are limited by a lack of clinical validation and scalability of assessment. To address these issues, this research focuses on psychosis as a critical condition for LLM safety evaluation by (1) developing and validating seven clinician-informed safety criteria, (2) constructing a human-consensus dataset, and (3) testing automated assessment using an LLM as an evaluator (LLM-as-a-Judge) or taking the majority vote of several LLM judges (LLM-as-a-Jury). Results indicate that LLM-as-a-Judge aligns closely with the human consensus (Cohen's $κ_{\text{human} \times \text{gemini}} = 0.75$, $κ_{\text{human} \times \text{qwen}} = 0.68$, $κ_{\text{human} \times \text{kimi}} = 0.56$) and that the best judge slightly outperforms LLM-as-a-Jury (Cohen's $κ_{\text{human} \times \text{jury}} = 0.74$). Overall, these findings have promising implications for clinically grounded, scalable methods in LLM safety evaluations for mental health contexts. △ Less

Submitted 20 March, 2026; originally announced April 2026.

Comments: published at IASEAI 2026, preliminary work presented at GenAI4Health workshop at NeurIPS 2025

Rethinking Representations for Cross-Domain Infrared Small Target Detection: A Generalizable Perspective from the Frequency Domain

Authors: Yimin Fu, Songbo Wang, Feiyan Wu, Jialin Lyu, Zhunga Liu, Michael K. Ng

Abstract: The accurate target-background separation in infrared small target detection (IRSTD) highly depends on the discriminability of extracted representations. However, most existing methods are confined to domain-consistent settings, while overlooking whether such discriminability can generalize to unseen domains. In practice, distribution shifts between training and testing data are inevitable due to… ▽ More The accurate target-background separation in infrared small target detection (IRSTD) highly depends on the discriminability of extracted representations. However, most existing methods are confined to domain-consistent settings, while overlooking whether such discriminability can generalize to unseen domains. In practice, distribution shifts between training and testing data are inevitable due to variations in observational conditions and environmental factors. Meanwhile, the intrinsic indistinctiveness of infrared small targets aggravates overfitting to domain-specific patterns. Consequently, the detection performance of models trained on source domains can be severely degraded when deployed in unseen domains. To address this challenge, we propose a spatial-spectral collaborative perception network (S$^2$CPNet) for cross-domain IRSTD. Moving beyond conventional spatial learning pipelines, we rethink IRSTD representations from a frequency perspective and reveal inconsistencies in spectral phase as the primary manifestation of domain discrepancies. Based on this insight, we develop a phase rectification module (PRM) to derive generalizable target awareness. Then, we employ an orthogonal attention mechanism (OAM) in skip connections to preserve positional information while refining informative representations. Moreover, the bias toward domain-specific patterns is further mitigated through selective style recomposition (SSR). Extensive experiments have been conducted on three IRSTD datasets, and the proposed method consistently achieves state-of-the-art performance under diverse cross-domain settings. △ Less

Submitted 2 April, 2026; originally announced April 2026.

Comments: The code will be released at https://github.com/fuyimin96/S2CPNet upon acceptance

RewardFlow: Topology-Aware Reward Propagation on State Graphs for Agentic RL with Large Language Models

Authors: Xiao Feng, Bo Han, Zhanke Zhou, Jiaqi Fan, Jiangchao Yao, Ka Ho Li, Dahai Yu, Michael Kwok-Po Ng

Abstract: Reinforcement learning (RL) shows promise for enhancing LLM agentic reasoning, yet sparse terminal rewards hinder fine-grained optimization. Process reward modeling offers an alternative but incurs high computational costs, reward hacking risks, and annotation bottlenecks. We introduce RewardFlow, a lightweight method for estimating state-level rewards in agentic reasoning. By constructing state g… ▽ More Reinforcement learning (RL) shows promise for enhancing LLM agentic reasoning, yet sparse terminal rewards hinder fine-grained optimization. Process reward modeling offers an alternative but incurs high computational costs, reward hacking risks, and annotation bottlenecks. We introduce RewardFlow, a lightweight method for estimating state-level rewards in agentic reasoning. By constructing state graphs that capture the intrinsic topological structure of trajectories, RewardFlow performs topology-aware propagation to estimate each state's contribution to success, yielding principled, annotation-free dense rewards. Used for RL optimization, RewardFlow substantially outperforms prior baselines across four agentic benchmarks: +6.2% average success rate on text-based tasks, +29.7% on visual reasoning over the strongest baseline across three model scales, and +10% accuracy on DeepResearch, with superior robustness and training efficiency. The implementation of RewardFlow is publicly available at https://github.com/tmlr-group/RewardFlow. △ Less

Submitted 28 May, 2026; v1 submitted 19 March, 2026; originally announced March 2026.

COACH meets QUORUM: A Framework and Pipeline for Aligning User, Expert and Developer Perspectives in LLM-generated Health Counselling

Authors: Yee Man Ng, Bram van Dijk, Pieter Beynen, Otto Boekesteijn, Joris Jansen, Gerard van Oortmerssen, Max van Duijn, Marco Spruit

Abstract: Systems that collect data on sleep, mood, and activities can provide valuable lifestyle counselling to populations affected by chronic disease and its consequences. Such systems are, however, challenging to develop; besides reliably extracting patterns from user-specific data, systems should also contextualise these patterns with validated medical knowledge to ensure the quality of counselling, an… ▽ More Systems that collect data on sleep, mood, and activities can provide valuable lifestyle counselling to populations affected by chronic disease and its consequences. Such systems are, however, challenging to develop; besides reliably extracting patterns from user-specific data, systems should also contextualise these patterns with validated medical knowledge to ensure the quality of counselling, and generate counselling that is relevant to a real user. We present QUORUM, a new evaluation framework that unifies these developer-, expert-, and user-centric perspectives, and show with a real case study that it meaningfully tracks convergence and divergence in stakeholder perspectives. We also present COACH, a Large Language Model-driven pipeline to generate personalised lifestyle counselling for our Healthy Chronos use case, a diary app for cancer patients and survivors. Applying our framework shows that overall, users, medical experts, and developers converge on the opinion that the generated counselling is relevant, of good quality, and reliable. However, stakeholders also diverge on the tone of the counselling, sensitivity to errors in pattern-extraction, and potential hallucinations. These findings highlight the importance of multi-stakeholder evaluation for consumer health language technologies and illustrate how a unified evaluation framework can support trustworthy, patient-centered NLP systems in real-world settings. △ Less

Submitted 9 March, 2026; originally announced March 2026.

Comments: Under review for the CL4Health workshop

Neural Operator-Grounded Continuous Tensor Function Representation and Its Applications

Authors: Ruoyang Su, Xi-Le Zhao, Sheng Liu, Wei-Hao Wu, Yisi Luo, Michael K. Ng

Abstract: Recently, continuous tensor functions have attracted increasing attention, because they can unifiedly represent data both on mesh grids and beyond mesh grids. However, since mode-$n$ product is essentially discrete and linear, the potential of current continuous tensor function representations is still locked. To break this bottleneck, we suggest neural operator-grounded mode-$n$ operators as a co… ▽ More Recently, continuous tensor functions have attracted increasing attention, because they can unifiedly represent data both on mesh grids and beyond mesh grids. However, since mode-$n$ product is essentially discrete and linear, the potential of current continuous tensor function representations is still locked. To break this bottleneck, we suggest neural operator-grounded mode-$n$ operators as a continuous and nonlinear alternative of discrete and linear mode-$n$ product. Instead of mapping the discrete core tensor to the discrete target tensor, proposed mode-$n$ operator directly maps the continuous core tensor function to the continuous target tensor function, which provides a genuine continuous representation of real-world data and can ameliorate discretization artifacts. Empowering with continuous and nonlinear mode-$n$ operators, we propose a neural operator-grounded continuous tensor function representation (abbreviated as NO-CTR), which can more faithfully represent complex real-world data compared with classic discrete tensor representations and continuous tensor function representations. Theoretically, we also prove that any continuous tensor function can be approximated by NO-CTR. To examine the capability of NO-CTR, we suggest an NO-CTR-based multi-dimensional data completion model. Extensive experiments across various data on regular mesh grids (multi-spectral images and color videos), on mesh girds with different resolutions (Sentinel-2 images) and beyond mesh grids (point clouds) demonstrate the superiority of NO-CTR. △ Less

Submitted 2 March, 2026; originally announced March 2026.

TVWorld: Foundations for Remote-Control TV Agents

Authors: Zhantao Ma, Quanfeng Lu, Shuai Zhong, Dahai Yu, Ping Luo, Michael K. Ng

Abstract: Recent large vision-language models (LVLMs) have demonstrated strong potential for device control. However, existing research has primarily focused on point-and-click (PnC) interaction, while remote-control (RC) interaction commonly encountered in everyday TV usage remains largely underexplored. To fill this gap, we introduce \textbf{TVWorld}, an offline graph-based abstraction of real-world TV na… ▽ More Recent large vision-language models (LVLMs) have demonstrated strong potential for device control. However, existing research has primarily focused on point-and-click (PnC) interaction, while remote-control (RC) interaction commonly encountered in everyday TV usage remains largely underexplored. To fill this gap, we introduce \textbf{TVWorld}, an offline graph-based abstraction of real-world TV navigation that enables reproducible and deployment-free evaluation. On this basis, we derive two complementary benchmarks that comprehensively assess TV-use capabilities: \textbf{TVWorld-N} for topology-aware navigation and \textbf{TVWorld-G} for focus-aware grounding. These benchmarks expose a key limitation of existing agents: insufficient topology awareness for focus-based, long-horizon TV navigation. Motivated by this finding, we propose a \emph{Topology-Aware Training} framework that injects topology awareness into LVLMs. Using this framework, we develop \textbf{TVTheseus}, a foundation model specialized for TV navigation. TVTheseus achieves a success rate of $68.3\%$ on TVWorld-N, surpassing strong closed-source baselines such as Gemini 3 Flash and establishing state-of-the-art (SOTA) performance. Additional analyses further provide valuable insights into the development of effective TV-use agents. △ Less

Submitted 19 January, 2026; originally announced January 2026.

FinForge: Semi-Synthetic Financial Benchmark Generation

Authors: Glenn Matlin, Akhil Theerthala, Anant Gupta, Anirudh JM, Rayan Castilla, Yi Mei Ng, Sudheer Chava

Abstract: Evaluating Language Models (LMs) in specialized, high-stakes domains such as finance remains a significant challenge due to the scarcity of open, high-quality, and domain-specific datasets. Existing general-purpose benchmarks provide broad coverage but lack the depth and domain fidelity needed to assess LMs' capabilities for real-world financial reasoning, which requires both conceptual understand… ▽ More Evaluating Language Models (LMs) in specialized, high-stakes domains such as finance remains a significant challenge due to the scarcity of open, high-quality, and domain-specific datasets. Existing general-purpose benchmarks provide broad coverage but lack the depth and domain fidelity needed to assess LMs' capabilities for real-world financial reasoning, which requires both conceptual understanding and quantitative rigor. To address this gap, we introduce FinForge, a scalable, semi-synthetic pipeline for constructing finance-specific evaluation benchmarks through a hybrid of expert-guided data curation and controlled LM-based synthesis. FinForge combines manual and programmatic corpus construction from authoritative financial sources with structured question generation and validation using Gemini 2.5 Flash. To demonstrate the pipeline's efficacy, we produce FinForge-5k, a snapshot benchmark comprising over 5,000 human-validated question-answer pairs across 11 finance subdomains, derived from a curated corpus of 100,000 verified documents totaling 143M tokens. Evaluation of state-of-the-art open-source and closed-source models on FinForge-5k reveals significant differences in financial reasoning, with leading models achieving accuracy levels near 80%. These findings underscore the framework's utility for diagnosing current model limitations and guiding future improvements in financial domain competence. All code and data are available at https://github.com/gtfintechlab/FinForge. △ Less

Submitted 19 January, 2026; v1 submitted 10 January, 2026; originally announced January 2026.

When Smaller Wins: Dual-Stage Distillation and Pareto-Guided Compression of Liquid Neural Networks for Edge Battery Prognostics

Authors: Dhivya Dharshini Kannan, Wei Li, Wei Zhang, Jianbiao Wang, Zhi Wei Seh, Man-Fai Ng

Abstract: Battery management systems increasingly require accurate battery health prognostics under strict on-device constraints. This paper presents DLNet, a practical framework with dual-stage distillation of liquid neural networks that turns a high-capacity model into compact and edge-deployable models for battery health prediction. DLNet first applies Euler discretization to reformulate liquid dynamics… ▽ More Battery management systems increasingly require accurate battery health prognostics under strict on-device constraints. This paper presents DLNet, a practical framework with dual-stage distillation of liquid neural networks that turns a high-capacity model into compact and edge-deployable models for battery health prediction. DLNet first applies Euler discretization to reformulate liquid dynamics for embedded compatibility. It then performs dual-stage knowledge distillation to transfer the teacher model's temporal behavior and recover it after further compression. Pareto-guided selection under joint error-cost objectives retains student models that balance accuracy and efficiency. We evaluate DLNet on a widely used dataset and validate real-device feasibility on an Arduino Nano 33 BLE Sense using int8 deployment. The final deployed student achieves a low error of 0.0066 when predicting battery health over the next 100 cycles, which is 15.4% lower than the teacher model. It reduces the model size from 616 kB to 94 kB with 84.7% reduction and takes 21 ms per inference on the device. These results support a practical smaller wins observation that a small model can match or exceed a large teacher for edge-based prognostics with proper supervision and selection. Beyond batteries, the DLNet framework can extend to other industrial analytics tasks with strict hardware constraints. △ Less

Submitted 10 June, 2026; v1 submitted 9 January, 2026; originally announced January 2026.

Comments: Accepted at International Conference on Pattern Recognition, ICPR 2026. Code available at: https://github.com/Dhivya-DD17/DLNet

Online Inference of Constrained Optimization: Primal-Dual Optimality and Sequential Quadratic Programming

Authors: Yihang Gao, Michael K. Ng, Michael W. Mahoney, Sen Na

Abstract: We study online statistical inference for the solutions of stochastic optimization problems with equality and inequality constraints. Such problems are prevalent in statistics and machine learning, encompassing constrained $M$-estimation, physics-informed models, safe reinforcement learning, and algorithmic fairness. We develop a stochastic sequential quadratic programming (SSQP) method to solve t… ▽ More We study online statistical inference for the solutions of stochastic optimization problems with equality and inequality constraints. Such problems are prevalent in statistics and machine learning, encompassing constrained $M$-estimation, physics-informed models, safe reinforcement learning, and algorithmic fairness. We develop a stochastic sequential quadratic programming (SSQP) method to solve these problems, where the step direction is computed by sequentially performing a quadratic approximation of the objective and a linear approximation of the constraints. Despite having access to unbiased estimates of population gradients, a key challenge in constrained stochastic problems lies in dealing with the bias in the step direction. As such, we apply a momentum-style gradient moving-average technique within SSQP to debias the step. We show that our method achieves global almost-sure convergence and exhibits local asymptotic normality with an optimal primal-dual limiting covariance matrix in the sense of Hájek and Le Cam. In addition, we provide a plug-in covariance matrix estimator for practical inference. To our knowledge, the proposed SSQP method is the first fully online method that attains primal-dual asymptotic minimax optimality without relying on projection operators onto the constraint set, which are generally intractable for nonlinear problems. Through extensive experiments on benchmark nonlinear problems, as well as on constrained generalized linear models and portfolio allocation problems using both synthetic and real data, we demonstrate superior performance of our method, showing that the method and its asymptotic behavior not only solve constrained stochastic problems efficiently but also provide valid and practical online inference in real-world applications. △ Less

Submitted 27 November, 2025; originally announced December 2025.

Comments: 80 pages, 5 figures, 5 tables

MultiGA: Leveraging Multi-Source Seeding in Genetic Algorithms

Authors: Isabelle Diana May-Xin Ng, Tharindu Cyril Weerasooriya, Haitao Zhu, Wei Wei

Abstract: In this paper, we introduce, MultiGA, an optimization framework which applies genetic algorithm principles to address complex natural language tasks and reasoning problems by sampling from a diverse population of LLMs to initialize the population of candidate solutions. MultiGA generates a range of outputs from various parent LLMs and uses a neutral fitness function to evaluate them. Through an it… ▽ More In this paper, we introduce, MultiGA, an optimization framework which applies genetic algorithm principles to address complex natural language tasks and reasoning problems by sampling from a diverse population of LLMs to initialize the population of candidate solutions. MultiGA generates a range of outputs from various parent LLMs and uses a neutral fitness function to evaluate them. Through an iterative recombination process, we mix and refine these generations until an optimal solution is achieved. Our results show that MultiGA produces high accuracy across multiple benchmarks, and these insights lay the foundation for future research looking closer at integrating multiple LLMs for unexplored tasks in which selecting only one pre-trained model is unclear or suboptimal. △ Less

Submitted 2 April, 2026; v1 submitted 21 November, 2025; originally announced December 2025.

NeuMatC: A General Neural Framework for Fast Parametric Matrix Operation

Authors: Chuan Wang, Xi-le Zhao, Zhilong Han, Liang Li, Deyu Meng, Michael K. Ng

Abstract: Matrix operations (e.g., inversion and singular value decomposition (SVD)) are fundamental in science and engineering. In many emerging real-world applications (such as wireless communication and signal processing), these operations must be performed repeatedly over matrices with parameters varying continuously. However, conventional methods tackle each matrix operation independently, underexplori… ▽ More Matrix operations (e.g., inversion and singular value decomposition (SVD)) are fundamental in science and engineering. In many emerging real-world applications (such as wireless communication and signal processing), these operations must be performed repeatedly over matrices with parameters varying continuously. However, conventional methods tackle each matrix operation independently, underexploring the inherent low-rankness and continuity along the parameter dimension, resulting in significantly redundant computation. To address this challenge, we propose \textbf{\textit{Neural Matrix Computation Framework} (NeuMatC)}, which elegantly tackles general parametric matrix operation tasks by leveraging the underlying low-rankness and continuity along the parameter dimension. Specifically, NeuMatC unsupervisedly learns a low-rank and continuous mapping from parameters to their corresponding matrix operation results. Once trained, NeuMatC enables efficient computations at arbitrary parameters using only a few basic operations (e.g., matrix multiplications and nonlinear activations), significantly reducing redundant computations. Experimental results on both synthetic and real-world datasets demonstrate the promising performance of NeuMatC, exemplified by over $3\times$ speedup in parametric inversion and $10\times$ speedup in parametric SVD compared to the widely used NumPy baseline in wireless communication, while maintaining acceptable accuracy. △ Less

Submitted 28 November, 2025; originally announced November 2025.

Blind Deconvolution for Color Images Using Normalized Quaternion Kernels

Authors: Yuming Yang, Michael K. Ng, Zhigang Jia, Wei Wang

Abstract: In this work, we address the challenging problem of blind deconvolution for color images. Existing methods often convert color images to grayscale or process each color channel separately, which overlooking the relationships between color channels. To handle this issue, we formulate a novel quaternion fidelity term designed specifically for color image blind deconvolution. This fidelity term lever… ▽ More In this work, we address the challenging problem of blind deconvolution for color images. Existing methods often convert color images to grayscale or process each color channel separately, which overlooking the relationships between color channels. To handle this issue, we formulate a novel quaternion fidelity term designed specifically for color image blind deconvolution. This fidelity term leverages the properties of quaternion convolution kernel, which consists of four kernels: one that functions similarly to a non-negative convolution kernel to capture the overall blur, and three additional convolution kernels without constraints corresponding to red, green and blue channels respectively model their unknown interdependencies. In order to preserve image intensity, we propose to use the normalized quaternion kernel in the blind deconvolution process. Extensive experiments on real datasets of blurred color images show that the proposed method effectively removes artifacts and significantly improves deblurring effect, demonstrating its potential as a powerful tool for color image deconvolution. △ Less

Submitted 21 November, 2025; originally announced November 2025.

A Provably-Correct and Robust Convex Model for Smooth Separable NMF

Authors: Junjun Pan, Valentin Leplat, Michael Ng, Nicolas Gillis

Abstract: Nonnegative matrix factorization (NMF) is a linear dimensionality reduction technique for nonnegative data, with applications such as hyperspectral unmixing and topic modeling. NMF is a difficult problem in general (NP-hard), and its solutions are typically not unique. To address these two issues, additional constraints or assumptions are often used. In particular, separability assumes that the ba… ▽ More Nonnegative matrix factorization (NMF) is a linear dimensionality reduction technique for nonnegative data, with applications such as hyperspectral unmixing and topic modeling. NMF is a difficult problem in general (NP-hard), and its solutions are typically not unique. To address these two issues, additional constraints or assumptions are often used. In particular, separability assumes that the basis vectors in the NMF are equal to some columns of the input matrix. In that case, the problem is referred to as separable NMF (SNMF) and can be solved in polynomial-time with robustness guarantees, while identifying a unique solution. However, in real-world scenarios, due to noise or variability, multiple data points may lie near the basis vectors, which SNMF does not leverage. In this work, we rely on the smooth separability assumption, which assumes that each basis vector is close to multiple data points. We explore the properties of the corresponding problem, referred to as smooth SNMF (SSNMF), and examine how it relates to SNMF and orthogonal NMF. We then propose a convex model for SSNMF and show that it provably recovers the sought-after factors, even in the presence of noise. We finally adapt an existing fast gradient method to solve this convex model for SSNMF, and show that it compares favorably with state-of-the-art methods on both synthetic and hyperspectral datasets. △ Less

Submitted 3 July, 2026; v1 submitted 10 November, 2025; originally announced November 2025.

Comments: 33 pages, 10 figures, Accepted in SIAM J. Matrix Anal. Appl. Code available from https://github.com/vleplat/ConvexSmoothSeparableNMF.git

Global YouTube Trending Dataset (2022-2025): Three Years of Platform-Curated, Cross-National Trends in Digital Culture

Authors: Alexandre Goncalves, Yee Man Margaret Ng

Abstract: On July 1, 2025, YouTube retired its decade-long public "Trending" pages, ending platform-curated, non-personalized video discovery. The Trending list had long served as a vital lens into algorithmic influence, cultural diffusion, and crisis communication globally, offering a rare "ground-truth" reference to study global attention and cultural salience. We present a three-year archival dataset of… ▽ More On July 1, 2025, YouTube retired its decade-long public "Trending" pages, ending platform-curated, non-personalized video discovery. The Trending list had long served as a vital lens into algorithmic influence, cultural diffusion, and crisis communication globally, offering a rare "ground-truth" reference to study global attention and cultural salience. We present a three-year archival dataset of YouTube Trending videos, collected from July 1, 2022, to June 30, 2025, with four daily snapshots for each of the 104 countries. The dataset includes 446,971 snapshots, each capturing up to 200 trending videos, encompassing 78.4 million video entries (726,627 unique videos) and associated metadata. Each record includes core identifiers (snapshot time, country, rank) and content metadata (video ID, channel ID, title, description, tags, publication date, category, channel name, language, live status, views, and comments). Unlike previous datasets with limited geographic scope or short timeframes, our non-personalized data provides exceptional cross-national and longitudinal coverage for studying digital culture, platform governance, and temporal dynamics in content popularity. We document the data collection methodology, schema design, coverage, descriptive statistics for both global and U.S. trending videos, and the ethical safeguards implemented throughout. △ Less

Submitted 24 October, 2025; originally announced October 2025.

MaLei at MultiClinSUM: Summarisation of Clinical Documents using Perspective-Aware Iterative Self-Prompting with LLMs

Authors: Libo Ren, Yee Man Ng, Lifeng Han

Abstract: Efficient communication between patients and clinicians plays an important role in shared decision-making. However, clinical reports are often lengthy and filled with clinical jargon, making it difficult for domain experts to identify important aspects in the document efficiently. This paper presents the methodology we applied in the MultiClinSUM shared task for summarising clinical case documents… ▽ More Efficient communication between patients and clinicians plays an important role in shared decision-making. However, clinical reports are often lengthy and filled with clinical jargon, making it difficult for domain experts to identify important aspects in the document efficiently. This paper presents the methodology we applied in the MultiClinSUM shared task for summarising clinical case documents. We used an Iterative Self-Prompting technique on large language models (LLMs) by asking LLMs to generate task-specific prompts and refine them via example-based few-shot learning. Furthermore, we used lexical and embedding space metrics, ROUGE and BERT-score, to guide the model fine-tuning with epochs. Our submission using perspective-aware ISP on GPT-4 and GPT-4o achieved ROUGE scores (46.53, 24.68, 30.77) and BERTscores (87.84, 83.25, 85.46) for (P, R, F1) from the official evaluation on 3,396 clinical case reports from various specialties extracted from open journals. The high BERTscore indicates that the model produced semantically equivalent output summaries compared to the references, even though the overlap at the exact lexicon level is lower, as reflected in the lower ROUGE scores. This work sheds some light on how perspective-aware ISP (PA-ISP) can be deployed for clinical report summarisation and support better communication between patients and clinicians. △ Less

Submitted 9 September, 2025; originally announced September 2025.

Comments: system paper at CLEF 2025

Semi-on-Demand Transit Feeders with Shared Autonomous Vehicles and Reinforcement-Learning-Based Zonal Dispatching Control

Authors: Max T. M. Ng, Roman Engelhardt, Florian Dandl, Hani S. Mahmassani, Klaus Bogenberger

Abstract: This paper develops a semi-on-demand transit feeder service using shared autonomous vehicles (SAVs) and zonal dispatching control based on reinforcement learning (RL). This service combines the cost-effectiveness of fixed-route transit with the adaptability of demand-responsive transport to improve accessibility in lower-density areas. Departing from the terminus, SAVs first make scheduled fixed s… ▽ More This paper develops a semi-on-demand transit feeder service using shared autonomous vehicles (SAVs) and zonal dispatching control based on reinforcement learning (RL). This service combines the cost-effectiveness of fixed-route transit with the adaptability of demand-responsive transport to improve accessibility in lower-density areas. Departing from the terminus, SAVs first make scheduled fixed stops, then offer on-demand pick-ups and drop-offs in a pre-determined flexible-route area. Our deep RL model dynamically assigns vehicles to subdivided flexible-route zones in response to real-time demand fluctuations and operations, using a policy gradient algorithm - Proximal Policy Optimization. The methodology is demonstrated through agent-based simulations on a real-world bus route in Munich, Germany. Results show that after efficient training of the RL model, the semi-on-demand service with dynamic zonal control serves 16% more passengers at 13% higher generalized costs on average compared to traditional fixed-route service. The efficiency gain brought by RL control brings 2.4% more passengers at 1.4% higher costs. This study not only showcases the potential of integrating SAV feeders and machine learning techniques into public transit, but also sets the groundwork for further innovations in addressing first-mile-last-mile problems in multimodal transit systems. △ Less

Submitted 1 September, 2025; originally announced September 2025.

Comments: 6 pages, 9 figures, published in 2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), Edmonton, Canada, 24-27 September 2024

Journal ref: 2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC)

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control

Authors: Quanfeng Lu, Zhantao Ma, Shuai Zhong, Jin Wang, Dahai Yu, Michael K. Ng, Ping Luo

Abstract: The rapid advancement of large vision language models (LVLMs) and agent systems has heightened interest in mobile GUI agents that can reliably translate natural language into interface operations. Existing single-agent approaches, however, remain limited by structural constraints. Although multi-agent systems naturally decouple different competencies, recent progress in multi-agent reinforcement l… ▽ More The rapid advancement of large vision language models (LVLMs) and agent systems has heightened interest in mobile GUI agents that can reliably translate natural language into interface operations. Existing single-agent approaches, however, remain limited by structural constraints. Although multi-agent systems naturally decouple different competencies, recent progress in multi-agent reinforcement learning (MARL) has often been hindered by inefficiency and remains incompatible with current LVLM architectures. To address these challenges, we introduce SWIRL, a staged workflow for interleaved reinforcement learning designed for multi-agent systems. SWIRL reformulates MARL into a sequence of single-agent reinforcement learning tasks, updating one agent at a time while keeping the others fixed. This formulation enables stable training and promotes efficient coordination across agents. Theoretically, we provide a stepwise safety bound, a cross-round monotonic improvement theorem, and convergence guarantees on return, ensuring robust and principled optimization. In application to mobile GUI control, SWIRL instantiates a Navigator that converts language and screen context into structured plans, and an Interactor that grounds these plans into executable atomic actions. Extensive experiments demonstrate superior performance on both high-level and low-level GUI benchmarks. Beyond GUI tasks, SWIRL also demonstrates strong capability in multi-agent mathematical reasoning, underscoring its potential as a general framework for developing efficient and robust multi-agent systems. △ Less

Submitted 27 August, 2025; originally announced August 2025.

Comments: 28 pages, 12 figures

MArgE: Meshing Argumentative Evidence from Multiple Large Language Models for Justifiable Claim Verification

Authors: Ming Pok Ng, Junqi Jiang, Gabriel Freedman, Antonio Rago, Francesca Toni

Abstract: Leveraging outputs from multiple large language models (LLMs) is emerging as a method for harnessing their power across a wide range of tasks while mitigating their capacity for making errors, e.g., hallucinations. However, current approaches to combining insights from multiple LLMs often involve unstructured interactions (e.g., free debate), resulting in model generations that are not faithfully… ▽ More Leveraging outputs from multiple large language models (LLMs) is emerging as a method for harnessing their power across a wide range of tasks while mitigating their capacity for making errors, e.g., hallucinations. However, current approaches to combining insights from multiple LLMs often involve unstructured interactions (e.g., free debate), resulting in model generations that are not faithfully justifiable. In this work, we introduce MArgE, a novel framework to provide formal structure to the evidence from each LLM, in the form of a tree of extracted arguments, for the task of claim verification. We use a variant of Argumentative LLMs (ArgLLMs), i.e. LLMs driven by frameworks and semantics from the field of computational argumentation, to construct structured argument trees for given claims. This process creates an inspectable pathway from the initial arguments to the final claim verification decisions, providing a faithful justification thereof. We show experimentally that MArgE can significantly outperform single LLMs, including three open-source models (4B to 8B parameters), GPT-4o-mini and existing ArgLLMs, as well as prior methods for unstructured multi-LLM debates. We thus demonstrate the advantages of incorporating formal, argumentative reasoning mechanisms when combining multiple LLM outputs. △ Less

Submitted 4 August, 2025; originally announced August 2025.

GenFT: A Generative Parameter-Efficient Fine-Tuning Method for Pretrained Foundation Models

Authors: Guangning Xu, Baoquan Zhang, Michael. K. Ng

Abstract: Parameter-efficient fine-tuning (PEFT) has emerged as a resource-efficient strategy for adapting Pretrained Foundation Models (PFMs) by learning a small number of task-specific updates $ΔW$. Existing methods often learn $ΔW$ largely independently of pretrained weights $W_0$, or exploit $W_0$ mainly through initialization or simple reparameterization. To further leverage the structural information… ▽ More Parameter-efficient fine-tuning (PEFT) has emerged as a resource-efficient strategy for adapting Pretrained Foundation Models (PFMs) by learning a small number of task-specific updates $ΔW$. Existing methods often learn $ΔW$ largely independently of pretrained weights $W_0$, or exploit $W_0$ mainly through initialization or simple reparameterization. To further leverage the structural information encoded in $W_0$, we propose Generative Parameter-Efficient Fine-Tuning (GenFT), a $W_0$-conditioned PEFT method that uses a deterministic weight generator to produce task-specific updates. Specifically, GenFT performs row and column transformations with nonlinear activations to extract structured patterns from $W_0$, and introduces a shared-specific decomposition to balance cross-layer information reuse and layer-specific flexibility. GenFT is simple and parameter-efficient, achieving competitive or better average performance across NLP and CV benchmarks. We further provide a pilot study on LLaMA-7B to examine its feasibility for generative models. The code is available at GitHub https://github.com/xuguangning1218/GenFT. △ Less

Submitted 4 June, 2026; v1 submitted 21 May, 2025; originally announced June 2025.

Comments: paper is accepted at ICANN 2026

ProRefine: Inference-Time Prompt Refinement with Textual Feedback

Authors: Deepak Pandita, Tharindu Cyril Weerasooriya, Ankit Parag Shah, Isabelle Diana May-Xin Ng, Christopher M. Homan, Wei Wei

Abstract: Agentic workflows, where multiple AI agents collaborate to accomplish complex tasks like reasoning or planning, play a substantial role in many cutting-edge commercial applications, and continue to fascinate researchers across fields for their potential to accomplish expensive, complex tasks that, until recently, only humans have been trusted to do. These workflows depend critically on the prompts… ▽ More Agentic workflows, where multiple AI agents collaborate to accomplish complex tasks like reasoning or planning, play a substantial role in many cutting-edge commercial applications, and continue to fascinate researchers across fields for their potential to accomplish expensive, complex tasks that, until recently, only humans have been trusted to do. These workflows depend critically on the prompts used to provide the roles models play in such workflows. Poorly designed prompts that fail even slightly to guide individual agents can lead to sub-optimal performance that may snowball within a system of agents, limiting their reliability and scalability. To address this important problem of inference-time prompt optimization, we introduce ProRefine, an innovative inference-time optimization method that uses an agentic loop of LLMs to generate and apply textual feedback. ProRefine dynamically refines prompts for multi-step reasoning tasks without additional training or ground truth labels. Evaluated on five benchmark mathematical reasoning datasets, ProRefine significantly surpasses zero-shot Chain-of-Thought baselines by 3 to 37 percentage points. This approach not only boosts accuracy but also allows smaller models to approach the performance of their larger counterparts. This highlights its potential for building more cost-effective and powerful hybrid AI systems, thereby democratizing access to high-performing AI. △ Less

Submitted 6 November, 2025; v1 submitted 5 June, 2025; originally announced June 2025.

Comments: Workshop on Efficient Reasoning at NeurIPS 2025

A Pre-trained Framework for Multilingual Brain Decoding Using Non-invasive Recordings

Authors: Yi Guo, Yihang Dong, Michael Kwok-Po Ng, Shuqiang Wang

Abstract: Brain-computer interfaces (BCIs) with speech decoding from brain recordings have broad application potential in fields such as clinical rehabilitation and cognitive neuroscience. However, current decoding methods remain limited to single-language, single-subject, and single neuroimaging modality settings, restricting their clinical applicability and generalizability. Here we propose a joint multil… ▽ More Brain-computer interfaces (BCIs) with speech decoding from brain recordings have broad application potential in fields such as clinical rehabilitation and cognitive neuroscience. However, current decoding methods remain limited to single-language, single-subject, and single neuroimaging modality settings, restricting their clinical applicability and generalizability. Here we propose a joint multilingual, multi-subject and multimodal decoding framework. It maps diverse brain recordings into a unified semantic space defined by a pre-trained multilingual model (PMM), enabling decoding across multiple languages, multiple subjects and multiple neuroimaging modalities. The proposed framework is validated using non-invasive brain recordings from 159 participants across four languages. Experimental results show that it exhibits strong generalization across multilingual, multi-subject, and multimodal settings. More importantly, the proposed framework can promote linguistic fairness, which is vital for underrepresented languages in BCI applications. The unified semantic space enables cross-lingual mapping enhancement, allowing the framework to boost the decoding performance of underrepresented languages, thereby promoting linguistic fairness. Overall, the proposed framework establishes a new potential paradigm for brain decoding, opening new paths for broader applications of BCI. △ Less

Submitted 3 June, 2025; originally announced June 2025.

ConnectomeDiffuser: Generative AI Enables Brain Network Construction from Diffusion Tensor Imaging

Authors: Xuhang Chen, Michael Kwok-Po Ng, Kim-Fung Tsang, Chi-Man Pun, Shuqiang Wang

Abstract: Brain network analysis plays a crucial role in diagnosing and monitoring neurodegenerative disorders such as Alzheimer's disease (AD). Existing approaches for constructing structural brain networks from diffusion tensor imaging (DTI) often rely on specialized toolkits that suffer from inherent limitations: operator subjectivity, labor-intensive workflows, and restricted capacity to capture complex… ▽ More Brain network analysis plays a crucial role in diagnosing and monitoring neurodegenerative disorders such as Alzheimer's disease (AD). Existing approaches for constructing structural brain networks from diffusion tensor imaging (DTI) often rely on specialized toolkits that suffer from inherent limitations: operator subjectivity, labor-intensive workflows, and restricted capacity to capture complex topological features and disease-specific biomarkers. To overcome these challenges and advance computational neuroimaging instrumentation, ConnectomeDiffuser is proposed as a novel diffusion-based framework for automated end-to-end brain network construction from DTI. The proposed model combines three key components: (1) a Template Network that extracts topological features from 3D DTI scans using Riemannian geometric principles, (2) a diffusion model that generates comprehensive brain networks with enhanced topological fidelity, and (3) a Graph Convolutional Network classifier that incorporates disease-specific markers to improve diagnostic accuracy. ConnectomeDiffuser demonstrates superior performance by capturing a broader range of structural connectivity and pathology-related information, enabling more sensitive analysis of individual variations in brain networks. Experimental validation on datasets representing two distinct neurodegenerative conditions demonstrates significant performance improvements over other brain network methods. This work contributes to the advancement of instrumentation in the context of neurological disorders, providing clinicians and researchers with a robust, generalizable measurement framework that facilitates more accurate diagnosis, deeper mechanistic understanding, and improved therapeutic monitoring of neurodegenerative diseases such as AD. △ Less

Submitted 23 May, 2025; originally announced May 2025.

Deep Learning Optimization Using Self-Adaptive Weighted Auxiliary Variables

Authors: Yaru Liu, Yiqi Gu, Michael K. Ng

Abstract: In this paper, we develop a new optimization framework for the least squares learning problem via fully connected neural networks or physics-informed neural networks. The gradient descent sometimes behaves inefficiently in deep learning because of the high non-convexity of loss functions and the vanishing gradient issue. Our idea is to introduce auxiliary variables to separate the layers of the de… ▽ More In this paper, we develop a new optimization framework for the least squares learning problem via fully connected neural networks or physics-informed neural networks. The gradient descent sometimes behaves inefficiently in deep learning because of the high non-convexity of loss functions and the vanishing gradient issue. Our idea is to introduce auxiliary variables to separate the layers of the deep neural networks and reformulate the loss functions for ease of optimization. We design the self-adaptive weights to preserve the consistency between the reformulated loss and the original mean squared loss, which guarantees that optimizing the new loss helps optimize the original problem. Numerical experiments are presented to verify the consistency and show the effectiveness and robustness of our models over gradient descent. △ Less

Submitted 30 April, 2025; originally announced April 2025.

Comments: 32 pages, 11 figures

Quaternion Nuclear Norms Over Frobenius Norms Minimization for Robust Matrix Completion

Authors: Yu Guo, Guoqing Chen, Tieyong Zeng, Qiyu Jin, Michael Kwok-Po Ng

Abstract: Recovering hidden structures from incomplete or noisy data remains a pervasive challenge across many fields, particularly where multi-dimensional data representation is essential. Quaternion matrices, with their ability to naturally model multi-dimensional data, offer a promising framework for this problem. This paper introduces the quaternion nuclear norm over the Frobenius norm (QNOF) as a novel… ▽ More Recovering hidden structures from incomplete or noisy data remains a pervasive challenge across many fields, particularly where multi-dimensional data representation is essential. Quaternion matrices, with their ability to naturally model multi-dimensional data, offer a promising framework for this problem. This paper introduces the quaternion nuclear norm over the Frobenius norm (QNOF) as a novel nonconvex approximation for the rank of quaternion matrices. QNOF is parameter-free and scale-invariant. Utilizing quaternion singular value decomposition, we prove that solving the QNOF can be simplified to solving the singular value $L_1/L_2$ problem. Additionally, we extend the QNOF to robust quaternion matrix completion, employing the alternating direction multiplier method to derive solutions that guarantee weak convergence under mild conditions. Extensive numerical experiments validate the proposed model's superiority, consistently outperforming state-of-the-art quaternion methods. △ Less

Submitted 30 April, 2025; originally announced April 2025.

MSC Class: 65F35; 90C30; 94A08; 68U10

A Graph-Partitioning Based Continuous Optimization Approach to Semi-supervised Clustering Problems

Authors: Wei Liu, Xin Liu, Michael K. Ng, Zaikun Zhang

Abstract: Semi-supervised clustering is a basic problem in various applications. Most existing methods require knowledge of the ideal cluster number, which is often difficult to obtain in practice. Besides, satisfying the must-link constraints is another major challenge for these methods. In this work, we view the semi-supervised clustering task as a partitioning problem on a graph associated with the given… ▽ More Semi-supervised clustering is a basic problem in various applications. Most existing methods require knowledge of the ideal cluster number, which is often difficult to obtain in practice. Besides, satisfying the must-link constraints is another major challenge for these methods. In this work, we view the semi-supervised clustering task as a partitioning problem on a graph associated with the given dataset, where the similarity matrix includes a scaling parameter to reflect the must-link constraints. Utilizing a relaxation technique, we formulate the graph partitioning problem into a continuous optimization model that does not require the exact cluster number, but only an overestimate of it. We then propose a block coordinate descent algorithm to efficiently solve this model, and establish its convergence result. Based on the obtained solution, we can construct the clusters that theoretically meet the must-link constraints under mild assumptions. Furthermore, we verify the effectiveness and efficiency of our proposed method through comprehensive numerical experiments. △ Less

Submitted 6 March, 2025; originally announced March 2025.

Low Tensor-Rank Adaptation of Kolmogorov--Arnold Networks

Authors: Yihang Gao, Michael K. Ng, Vincent Y. F. Tan

Abstract: Kolmogorov--Arnold networks (KANs) have demonstrated their potential as an alternative to multi-layer perceptions (MLPs) in various domains, especially for science-related tasks. However, transfer learning of KANs remains a relatively unexplored area. In this paper, inspired by Tucker decomposition of tensors and evidence on the low tensor-rank structure in KAN parameter updates, we develop low te… ▽ More Kolmogorov--Arnold networks (KANs) have demonstrated their potential as an alternative to multi-layer perceptions (MLPs) in various domains, especially for science-related tasks. However, transfer learning of KANs remains a relatively unexplored area. In this paper, inspired by Tucker decomposition of tensors and evidence on the low tensor-rank structure in KAN parameter updates, we develop low tensor-rank adaptation (LoTRA) for fine-tuning KANs. We study the expressiveness of LoTRA based on Tucker decomposition approximations. Furthermore, we provide a theoretical analysis to select the learning rates for each LoTRA component to enable efficient training. Our analysis also shows that using identical learning rates across all components leads to inefficient training, highlighting the need for an adaptive learning rate strategy. Beyond theoretical insights, we explore the application of LoTRA for efficiently solving various partial differential equations (PDEs) by fine-tuning KANs. Additionally, we propose Slim KANs that incorporate the inherent low-tensor-rank properties of KAN parameter tensors to reduce model size while maintaining superior performance. Experimental results validate the efficacy of the proposed learning rate selection strategy and demonstrate the effectiveness of LoTRA for transfer learning of KANs in solving PDEs. Further evaluations on Slim KANs for function representation and image classification tasks highlight the expressiveness of LoTRA and the potential for parameter reduction through low tensor-rank decomposition. △ Less

Submitted 13 February, 2025; v1 submitted 9 February, 2025; originally announced February 2025.

Analyzing Country-Level Vaccination Rates and Determinants of Practical Capacity to Administer COVID-19 Vaccines

Authors: Sharika J. Hegde, Max T. M. Ng, Marcos Rios, Hani S. Mahmassani, Ying Chen, Karen Smilowitz

Abstract: The COVID-19 vaccine development, manufacturing, transportation, and administration proved an extreme logistics operation of global magnitude. Global vaccination levels, however, remain a key concern in preventing the emergence of new strains and minimizing the impact of the pandemic's disruption of daily life. In this paper, country-level vaccination rates are analyzed through a queuing framework… ▽ More The COVID-19 vaccine development, manufacturing, transportation, and administration proved an extreme logistics operation of global magnitude. Global vaccination levels, however, remain a key concern in preventing the emergence of new strains and minimizing the impact of the pandemic's disruption of daily life. In this paper, country-level vaccination rates are analyzed through a queuing framework to extract service rates that represent the practical capacity of a country to administer vaccines. These rates are further characterized through regression and interpretable machine learning methods with country-level demographic, governmental, and socio-economic variates. Model results show that participation in multi-governmental collaborations such as COVAX may improve the ability to vaccinate. Similarly, improved transportation and accessibility variates such as roads per area for low-income countries and rail lines per area for high-income countries can improve rates. It was also found that for low-income countries specifically, improvements in basic and health infrastructure (as measured through spending on healthcare, number of doctors and hospital beds per 100k, population percent with access to electricity, life expectancy, and vehicles per 1000 people) resulted in higher vaccination rates. Of the high-income countries, those with larger 65-plus populations struggled to vaccinate at high rates, indicating potential accessibility issues for the elderly. This study finds that improving basic and health infrastructure, focusing on accessibility in the last mile, particularly for the elderly, and fostering global partnerships can improve logistical operations of such a scale. Such structural impediments and inequities in global health care must be addressed in preparation for future global public health crises. △ Less

Submitted 8 January, 2025; v1 submitted 29 December, 2024; originally announced January 2025.

Comments: Under consideration for more thorough analysis

Multisource Collaborative Domain Generalization for Cross-Scene Remote Sensing Image Classification

Authors: Zhu Han, Ce Zhang, Lianru Gao, Zhiqiang Zeng, Michael K. Ng, Bing Zhang, Jocelyn Chanussot

Abstract: Cross-scene image classification aims to transfer prior knowledge of ground materials to annotate regions with different distributions and reduce hand-crafted cost in the field of remote sensing. However, existing approaches focus on single-source domain generalization to unseen target domains, and are easily confused by large real-world domain shifts due to the limited training information and in… ▽ More Cross-scene image classification aims to transfer prior knowledge of ground materials to annotate regions with different distributions and reduce hand-crafted cost in the field of remote sensing. However, existing approaches focus on single-source domain generalization to unseen target domains, and are easily confused by large real-world domain shifts due to the limited training information and insufficient diversity modeling capacity. To address this gap, we propose a novel multi-source collaborative domain generalization framework (MS-CDG) based on homogeneity and heterogeneity characteristics of multi-source remote sensing data, which considers data-aware adversarial augmentation and model-aware multi-level diversification simultaneously to enhance cross-scene generalization performance. The data-aware adversarial augmentation adopts an adversary neural network with semantic guide to generate MS samples by adaptively learning realistic channel and distribution changes across domains. In views of cross-domain and intra-domain modeling, the model-aware diversification transforms the shared spatial-channel features of MS data into the class-wise prototype and kernel mixture module, to address domain discrepancies and cluster different classes effectively. Finally, the joint classification of original and augmented MS samples is employed by introducing a distribution consistency alignment to increase model diversity and ensure better domain-invariant representation learning. Extensive experiments on three public MS remote sensing datasets demonstrate the superior performance of the proposed method when benchmarked with the state-of-the-art methods. △ Less

Submitted 5 December, 2024; originally announced December 2024.

The subTuring degrees

Authors: Takayuki Kihara, Keng Meng Ng

Abstract: In this article, we introduce a notion of reducibility for partial functions on the natural numbers, which we call subTuring reducibility. One important aspect is that the subTuring degrees correspond to the structure of the realizability subtoposes of the effective topos. We show that the subTuring degrees (that is, the realizability subtoposes of the effective topos) form a dense non-modular (th… ▽ More In this article, we introduce a notion of reducibility for partial functions on the natural numbers, which we call subTuring reducibility. One important aspect is that the subTuring degrees correspond to the structure of the realizability subtoposes of the effective topos. We show that the subTuring degrees (that is, the realizability subtoposes of the effective topos) form a dense non-modular (thus, non-distributive) lattice. We also show that there is a nonzero join-irreducible subTuring degree (which implies that there is a realizability subtopos of the effective topos that cannot be decomposed into two smaller realizability subtoposes). △ Less

Submitted 20 November, 2024; v1 submitted 8 November, 2024; originally announced November 2024.

Low-Rank Tensor Learning by Generalized Nonconvex Regularization

Authors: Sijia Xia, Michael K. Ng, Xiongjun Zhang

Abstract: In this paper, we study the problem of low-rank tensor learning, where only a few of training samples are observed and the underlying tensor has a low-rank structure. The existing methods are based on the sum of nuclear norms of unfolding matrices of a tensor, which may be suboptimal. In order to explore the low-rankness of the underlying tensor effectively, we propose a nonconvex model based on t… ▽ More In this paper, we study the problem of low-rank tensor learning, where only a few of training samples are observed and the underlying tensor has a low-rank structure. The existing methods are based on the sum of nuclear norms of unfolding matrices of a tensor, which may be suboptimal. In order to explore the low-rankness of the underlying tensor effectively, we propose a nonconvex model based on transformed tensor nuclear norm for low-rank tensor learning. Specifically, a family of nonconvex functions are employed onto the singular values of all frontal slices of a tensor in the transformed domain to characterize the low-rankness of the underlying tensor. An error bound between the stationary point of the nonconvex model and the underlying tensor is established under restricted strong convexity on the loss function (such as least squares loss and logistic regression) and suitable regularity conditions on the nonconvex penalty function. By reformulating the nonconvex function into the difference of two convex functions, a proximal majorization-minimization (PMM) algorithm is designed to solve the resulting model. Then the global convergence and convergence rate of PMM are established under very mild conditions. Numerical experiments are conducted on tensor completion and binary classification to demonstrate the effectiveness of the proposed method over other state-of-the-art methods. △ Less

Submitted 23 October, 2024; originally announced October 2024.

DAPE V2: Process Attention Score as Feature Map for Length Extrapolation

Authors: Chuanyang Zheng, Yihang Gao, Han Shi, Jing Xiong, Jiankai Sun, Jingyao Li, Minbin Huang, Xiaozhe Ren, Michael Ng, Xin Jiang, Zhenguo Li, Yu Li

Abstract: The attention mechanism is a fundamental component of the Transformer model, contributing to interactions among distinct tokens, in contrast to earlier feed-forward neural networks. In general, the attention scores are determined simply by the key-query products. However, this work's occasional trial (combining DAPE and NoPE) of including additional MLPs on attention scores without position encodi… ▽ More The attention mechanism is a fundamental component of the Transformer model, contributing to interactions among distinct tokens, in contrast to earlier feed-forward neural networks. In general, the attention scores are determined simply by the key-query products. However, this work's occasional trial (combining DAPE and NoPE) of including additional MLPs on attention scores without position encoding indicates that the classical key-query multiplication may limit the performance of Transformers. In this work, we conceptualize attention as a feature map and apply the convolution operator (for neighboring attention scores across different heads) to mimic the processing methods in computer vision. Specifically, the main contribution of this paper is identifying and interpreting the Transformer length extrapolation problem as a result of the limited expressiveness of the naive query and key dot product, and we successfully translate the length extrapolation issue into a well-understood feature map processing problem. The novel insight, which can be adapted to various attention-related models, reveals that the current Transformer architecture has the potential for further evolution. Extensive experiments demonstrate that treating attention as a feature map and applying convolution as a processing method significantly enhances Transformer performance. △ Less

Submitted 10 October, 2024; v1 submitted 7 October, 2024; originally announced October 2024.

Comments: Tech Report. Compared to DAPE, this work (DAPE V2) further analyzes the length extrapolation problem and translate the length extrapolation issue into a well-understood feature map processing problem. arXiv admin note: text overlap with arXiv:2405.14722

Leveraging Open-Source Large Language Models for Native Language Identification

Authors: Yee Man Ng, Ilia Markov

Abstract: Native Language Identification (NLI) - the task of identifying the native language (L1) of a person based on their writing in the second language (L2) - has applications in forensics, marketing, and second language acquisition. Historically, conventional machine learning approaches that heavily rely on extensive feature engineering have outperformed transformer-based language models on this task.… ▽ More Native Language Identification (NLI) - the task of identifying the native language (L1) of a person based on their writing in the second language (L2) - has applications in forensics, marketing, and second language acquisition. Historically, conventional machine learning approaches that heavily rely on extensive feature engineering have outperformed transformer-based language models on this task. Recently, closed-source generative large language models (LLMs), e.g., GPT-4, have demonstrated remarkable performance on NLI in a zero-shot setting, including promising results in open-set classification. However, closed-source LLMs have many disadvantages, such as high costs and undisclosed nature of training data. This study explores the potential of using open-source LLMs for NLI. Our results indicate that open-source LLMs do not reach the accuracy levels of closed-source LLMs when used out-of-the-box. However, when fine-tuned on labeled training data, open-source LLMs can achieve performance comparable to that of commercial LLMs. △ Less

Submitted 19 January, 2025; v1 submitted 15 September, 2024; originally announced September 2024.

Quaternion Nuclear Norm minus Frobenius Norm Minimization for color image reconstruction

Authors: Yu Guo, Guoqing Chen, Tieyong Zeng, Qiyu Jin, Michael Kwok-Po Ng

Abstract: Color image restoration methods typically represent images as vectors in Euclidean space or combinations of three monochrome channels. However, they often overlook the correlation between these channels, leading to color distortion and artifacts in the reconstructed image. To address this, we present Quaternion Nuclear Norm Minus Frobenius Norm Minimization (QNMF), a novel approach for color image… ▽ More Color image restoration methods typically represent images as vectors in Euclidean space or combinations of three monochrome channels. However, they often overlook the correlation between these channels, leading to color distortion and artifacts in the reconstructed image. To address this, we present Quaternion Nuclear Norm Minus Frobenius Norm Minimization (QNMF), a novel approach for color image reconstruction. QNMF utilizes quaternion algebra to capture the relationships among RGB channels comprehensively. By employing a regularization technique that involves nuclear norm minus Frobenius norm, QNMF approximates the underlying low-rank structure of quaternion-encoded color images. Theoretical proofs are provided to ensure the method's mathematical integrity. Demonstrating versatility and efficacy, the QNMF regularizer excels in various color low-level vision tasks, including denoising, deblurring, inpainting, and random impulse noise removal, achieving state-of-the-art results. △ Less

Submitted 12 September, 2024; originally announced September 2024.

Comments: This paper was accepted by Pattern Recognition on September 5, 2024

Journal ref: Pattern Recognition, 2025, 158:110986

Robust Instance Optimal Phase-Only Compressed Sensing

Authors: Junren Chen, Michael K. Ng, Jonathan Scarlett

Abstract: Phase-only compressed sensing (PO-CS) concerns the recovery of sparse signals from the phases of complex measurements. Recent results show that sparse signals in the standard sphere $\mathbb{S}^{n-1}$ can be exactly recovered from complex Gaussian phases by a linearization procedure, which recasts PO-CS as linear compressed sensing and then applies (quadratically constrained) basis pursuit to obta… ▽ More Phase-only compressed sensing (PO-CS) concerns the recovery of sparse signals from the phases of complex measurements. Recent results show that sparse signals in the standard sphere $\mathbb{S}^{n-1}$ can be exactly recovered from complex Gaussian phases by a linearization procedure, which recasts PO-CS as linear compressed sensing and then applies (quadratically constrained) basis pursuit to obtain $\mathbf{x}^\sharp$. This paper focuses on the instance optimality and robustness of $\mathbf{x}^{\sharp}$. First, we strengthen the nonuniform instance optimality of Jacques and Feuillen (2021) to a uniform one over the entire signal space. We show the existence of some universal constant $C$ such that $\|\mathbf{x}^\sharp-\mathbf{x}\|_2\le Cs^{-1/2}σ_{\ell_1}(\mathbf{x},Σ^n_s)$ holds for all $\mathbf{x}$ in the unit Euclidean sphere, where $σ_{\ell_1}(\mathbf{x},Σ^n_s)$ is the $\ell_1$ distance of $\mathbf{x}$ to its closest $s$-sparse signal. This is achieved by showing the new sensing matrices corresponding to all approximately sparse signals simultaneously satisfy RIP. Second, we investigate the estimator's robustness to noise and corruption. We show that dense noise with entries bounded by some small $τ_0$, appearing either prior or posterior to retaining the phases, increments $\|\mathbf{x}^\sharp-\mathbf{x}\|_2$ by $O(τ_0)$. This is near-optimal (up to log factors) for any algorithm. On the other hand, adversarial corruption, which changes an arbitrary $ζ_0$-fraction of the measurements to any phase-only values, increments $\|\mathbf{x}^\sharp-\mathbf{x}\|_2$ by $O(\sqrt{ζ_0\log(1/ζ_0)})$. The developments are then combined to yield a robust instance optimal guarantee that resembles the standard one in linear compressed sensing. △ Less

Submitted 4 April, 2026; v1 submitted 12 August, 2024; originally announced August 2024.

Comments: To appear in Information and inference: A Journal of the IMA

Non-Negative Reduced Biquaternion Matrix Factorization with Applications in Color Face Recognition

Authors: Jifei Miao, Junjun Pan, Michael K. Ng

Abstract: Reduced biquaternion (RB), as a four-dimensional algebra highly suitable for representing color pixels, has recently garnered significant attention from numerous scholars. In this paper, for color image processing problems, we introduce a concept of the non-negative RB matrix and then use the multiplication properties of RB to propose a non-negative RB matrix factorization (NRBMF) model. The NRBMF… ▽ More Reduced biquaternion (RB), as a four-dimensional algebra highly suitable for representing color pixels, has recently garnered significant attention from numerous scholars. In this paper, for color image processing problems, we introduce a concept of the non-negative RB matrix and then use the multiplication properties of RB to propose a non-negative RB matrix factorization (NRBMF) model. The NRBMF model is introduced to address the challenge of reasonably establishing a non-negative quaternion matrix factorization model, which is primarily hindered by the multiplication properties of traditional quaternions. Furthermore, this paper transforms the problem of solving the NRBMF model into an RB alternating non-negative least squares (RB-ANNLS) problem. Then, by introducing a method to compute the gradient of the real function with RB matrix variables, we solve the RB-ANNLS optimization problem using the RB projected gradient algorithm and conduct a convergence analysis of the algorithm. Finally, we validate the effectiveness and superiority of the proposed NRBMF model in color face recognition. △ Less

Submitted 9 July, 2025; v1 submitted 10 August, 2024; originally announced August 2024.

Multi-modal Mood Reader: Pre-trained Model Empowers Cross-Subject Emotion Recognition

Authors: Yihang Dong, Xuhang Chen, Yanyan Shen, Michael Kwok-Po Ng, Tao Qian, Shuqiang Wang

Abstract: Emotion recognition based on Electroencephalography (EEG) has gained significant attention and diversified development in fields such as neural signal processing and affective computing. However, the unique brain anatomy of individuals leads to non-negligible natural differences in EEG signals across subjects, posing challenges for cross-subject emotion recognition. While recent studies have attem… ▽ More Emotion recognition based on Electroencephalography (EEG) has gained significant attention and diversified development in fields such as neural signal processing and affective computing. However, the unique brain anatomy of individuals leads to non-negligible natural differences in EEG signals across subjects, posing challenges for cross-subject emotion recognition. While recent studies have attempted to address these issues, they still face limitations in practical effectiveness and model framework unity. Current methods often struggle to capture the complex spatial-temporal dynamics of EEG signals and fail to effectively integrate multimodal information, resulting in suboptimal performance and limited generalizability across subjects. To overcome these limitations, we develop a Pre-trained model based Multimodal Mood Reader for cross-subject emotion recognition that utilizes masked brain signal modeling and interlinked spatial-temporal attention mechanism. The model learns universal latent representations of EEG signals through pre-training on large scale dataset, and employs Interlinked spatial-temporal attention mechanism to process Differential Entropy(DE) features extracted from EEG data. Subsequently, a multi-level fusion layer is proposed to integrate the discriminative features, maximizing the advantages of features across different dimensions and modalities. Extensive experiments on public datasets demonstrate Mood Reader's superior performance in cross-subject emotion recognition tasks, outperforming state-of-the-art methods. Additionally, the model is dissected from attention perspective, providing qualitative analysis of emotion-related brain areas, offering valuable insights for affective research in neural signal processing. △ Less

Submitted 28 May, 2024; originally announced May 2024.

Comments: Accepted by International Conference on Neural Computing for Advanced Applications, 2024

Hyperspectral and multispectral image fusion with arbitrary resolution through self-supervised representations

Authors: Ting Wang, Zipei Yan, Jizhou Li, Xile Zhao, Chao Wang, Michael Ng

Abstract: The fusion of a low-resolution hyperspectral image (LR-HSI) with a high-resolution multispectral image (HR-MSI) has emerged as an effective technique for achieving HSI super-resolution (SR). Previous studies have mainly concentrated on estimating the posterior distribution of the latent high-resolution hyperspectral image (HR-HSI), leveraging an appropriate image prior and likelihood computed from… ▽ More The fusion of a low-resolution hyperspectral image (LR-HSI) with a high-resolution multispectral image (HR-MSI) has emerged as an effective technique for achieving HSI super-resolution (SR). Previous studies have mainly concentrated on estimating the posterior distribution of the latent high-resolution hyperspectral image (HR-HSI), leveraging an appropriate image prior and likelihood computed from the discrepancy between the latent HSI and observed images. Low rankness stands out for preserving latent HSI characteristics through matrix factorization among the various priors. However, the primary limitation in previous studies lies in the generalization of a fusion model with fixed resolution scales, which necessitates retraining whenever output resolutions are changed. To overcome this limitation, we propose a novel continuous low-rank factorization (CLoRF) by integrating two neural representations into the matrix factorization, capturing spatial and spectral information, respectively. This approach enables us to harness both the low rankness from the matrix factorization and the continuity from neural representation in a self-supervised manner.Theoretically, we prove the low-rank property and Lipschitz continuity in the proposed continuous low-rank factorization. Experimentally, our method significantly surpasses existing techniques and achieves user-desired resolutions without the need for neural network retraining. Code is available at https://github.com/wangting1907/CLoRF-Fusion. △ Less

Submitted 25 November, 2024; v1 submitted 28 May, 2024; originally announced May 2024.

Data Valuation by Fusing Global and Local Statistical Information

Authors: Xiaoling Zhou, Ou Wu, Michael K. Ng, Hao Jiang

Abstract: Data valuation has garnered increasing attention in recent years, given the critical role of high-quality data in various applications. Among diverse data valuation approaches, Shapley value-based methods are predominant due to their strong theoretical grounding. However, the exact computation of Shapley values is often computationally prohibitive, prompting the development of numerous approximati… ▽ More Data valuation has garnered increasing attention in recent years, given the critical role of high-quality data in various applications. Among diverse data valuation approaches, Shapley value-based methods are predominant due to their strong theoretical grounding. However, the exact computation of Shapley values is often computationally prohibitive, prompting the development of numerous approximation techniques. Despite notable advancements, existing methods generally neglect the incorporation of value distribution information and fail to account for dynamic data conditions, thereby compromising their performance and application potential. In this paper, we highlight the crucial role of both global and local statistical properties of value distributions in the context of data valuation for machine learning. First, we conduct a comprehensive analysis of these distributions across various simulated and real-world datasets, uncovering valuable insights and key patterns. Second, we propose an enhanced data valuation method that fuses the explored distribution characteristics into two regularization terms to refine Shapley value estimation. The proposed regularizers can be seamlessly incorporated into various existing data valuation methods. Third, we introduce a novel approach for dynamic data valuation that infers updated data values without recomputing Shapley values, thereby significantly improving computational efficiency. Extensive experiments have been conducted across a range of tasks, including Shapley value estimation, value-based data addition and removal, mislabeled data detection, and dynamic data valuation. The results showcase the consistent effectiveness and efficiency of our proposed methodologies, affirming the significant potential of global and local value distributions in data valuation. △ Less

Submitted 26 November, 2025; v1 submitted 23 May, 2024; originally announced May 2024.

Comments: 35 pages, 9 figures

ACM Class: I.2