Search arXiv⌕ Search

arXiv subjects

Minh Nguyen

Publications and source records attributed to Minh Nguyen.

At least 19 recordsLinked to original sources
arXiv2026

A visual large language foundational model for medical image recognition using clinician-oriented social media

Large language models (LLMs) have demonstrated strong capabilities across diverse domains, showing considerable potential in medicine. However, their application in medical settings remains limited by the scarcity of visual question answering (VQA) datasets that capture clinical reasoning and explicit image-text alignment. Here, we leverage de-identified medical images and expert commentaries shared on clinician-oriented social media. By combining an advanced LLM with clinician-in-the-loop verification, we established a rigorous pipeline to construct ThoughtMed-1M, a long-form medical VQA dataset containing over one million VQA pairs and designed to capture structured clinical logic and medical image-text alignment. To demonstrate its utility, we developed a FOundational LLM Trained on ThoughtMed-1M (FOLTMed). FOLTMed achieved state-of-the-art performance across 42 medical VQA benchmark datasets, with a macro accuracy of 85.4%, and generated more clinically coherent responses on the ThoughtMed-1M test set. It outperformed state-of-the-art models by 3--5% across factuality and similarity metrics, highlighting a scalable paradigm for advancing research on clinically grounded multimodal LLMs.

cs.AI↗
arXiv2026

Target-Weighted Neyman Allocation: Experimental Design for Heterogeneous Treatment Effects under Population Shift

Randomized experiments are often run in one population to guide decisions in another. Allocating by experimental proportions wastes budget on groups that rarely appear in deployment, whereas allocating by deployment proportions under-samples groups that are hard to measure precisely. We propose \textbf{TWNA} (Target-Weighted Neyman Allocation), a two-stage stratified design that uses pilot estimates of group--arm outcome variances to allocate final-stage sample sizes and treatment probabilities for target-weighted group average treatment effect (GATE) precision. The oracle rule has a closed form and balances deployment importance with statistical difficulty; the plug-in rule recovers it as pilot variance estimates stabilize. We also extend TWNA to handle uncertainty about deployment composition, remaining robust whether the target mix is roughly known or entirely unknown. Finally, we distinguish this weight robustness from a pilot-robust variant for skewed, rare-event, or contaminated outcomes. Simulations and real-covariate benchmarks show the largest gains when groups are both deployment-important and difficult to measure.

cs.LG↗
arXiv2026

ShapKO: Shapley-Adaptive Modality Knockout for Robust Multimodal Learning

Multimodal medical models often degrade when inputs are missing, a common scenario in real-world clinical workflows. Separately, even when all modalities are present, modality dominance is observed during training, where optimization over-relies on a highly predictive modality and undertrains complementary sources, resulting in poor robustness under partial availability. While training-time modality knockout improves missing-modality robustness, existing approaches use static masking rates that cannot adapt to evolving modality utility during training. We introduce ShapKO (Shapley-Adaptive Modality Knockout), a dynamic training strategy that learns modality-specific knockout probabilities based on validation utility. ShapKO periodically evaluates performance across modality subsets, estimates modality importance via Shapley values, and updates masking probabilities to suppress dominant modalities more frequently. This adaptive process promotes complementary representations, while requiring no architectural modifications. We evaluate ShapKO on three datasets covering multitask clinical classification, survival prediction, and cancer detection. ShapKO consistently improves performance under modality absence and yields interpretable trajectories of learned masking behavior. Code is available at: https://github.com/sumona00/ShapKO

cs.CV↗
arXiv2026

Hierarchical forecasting: The role of information

In hierarchical forecasting, the process of forecast reconciliation transforms a set of "base" or "raw" forecasts, which do not satisfy the hierarchical aggregation constraints in the real data, into a set of "coherent" forecasts, which do satisfy those constraints. The academic literature provides ample simulation evidence and real-world examples demonstrating the value of forecast reconciliation in improving forecasts of hierarchical time series. This improvement is attributed to the imposition of aggregation constraints. However, this evidence is derived from base forecasts, each generated using a distinct information set, usually the univariate information set corresponding to each time series. Since reconciliation algorithms combine forecasts, it is difficult to determine the extent to which the improvement is due to the imposition of constraints versus the combination of information carried by different forecasts. In this paper, we demonstrate that when base forecasts are based on different information sets and historical data are available, there is scope for improving these forecasts by combining the information that each one carries, even when they are already coherent. We propose a new method, called the information combination (IComb) method, which combines the information content of forecasts during the reconciliation process. The method is regression-based and can be implemented using existing penalised regression packages. We provide simulation evidence to illustrate the role of information sets, as distinct from the role of aggregation constraints, in forecasting hierarchical time series. Finally, we apply our method to datasets previously used in the literature and demonstrate that it achieves superior results compared to traditional approaches.

stat.ME↗
arXiv2026

Minimum Specification Perturbation: Robustness as Distance-to-Falsification in Causal Inference

Empirical causal claims depend on many analyst decisions, from selecting covariates to choosing estimators. Existing robustness tools summarize how results vary across these choices, but, to the best of our knowledge, do not answer: \textbf{How many analyst decisions must change to reach a specification, which is a set of choices, whose confidence interval (CI) contains zero?} We introduce \emph{Minimum Specification Perturbation (MSP)}, the smallest number of changes. MSP is small under the null, grows with effect strength and captures distance-to-falsification information that dispersion-based summaries cannot report; when making decisions under weak effects, an MSP-based rule yields lower false-positive rates than dispersion-based rules. We show that Fragility Index and MSP measure orthogonal vulnerabilities: fragility to influential observations need not imply fragility to specification choices. On the LaLonde benchmark, MSP = 1 implies that one decision change makes the CI contain zero. We further provide exact permutation calibration under randomization and characterize computation, showing tractable cases under additive structure and NP-hardness in general.

stat.ME↗
arXiv2026

Inverse Safety Filtering: Inferring Constraints from Safety Filters for Decentralized Coordination

Safe multi-agent coordination in uncertain environments can benefit from learning constraints from other agents. Implicitly communicating safety constraints through actions is a promising approach, allowing agents to coordinate and maintain safety without expensive communication channels. This paper introduces an online method to infer constraints from observing the safety-filtered actions of other agents. We approach the problem by using safety filters to ensure forward safety and exploit their structure to work backwards and infer constraints. We provide sufficient conditions under which we can infer these constraints and prove that our inference method converges. This constraint inference procedure is coupled with a decentralized planning method that ensures safety when the constraint activation distance is sufficiently large. We then empirically validate our method with Monte Carlo simulations and hardware experiments with quadruped robots.

eess.SY↗
arXiv2026

Stochastic GW with the Orthogonalized Projector Augmented Wave Method

We introduce stochastic GW with the orthogonalized projector augmented-wave method (OPAW-sGW). This implementation enables accurate quasiparticle band gaps on significantly coarser real-space grids than norm-conserving pseudopotential sGW (NCPP-sGW). The orthogonalized PAW representation preserves the formal all-electron character and enables stochastic sampling of the Green's function and screened Coulomb interaction.

physics.chem-ph↗
arXiv2026

Convex function through Doob-Meyer decomposition

In this work, we aim to study a strong version of Ito's lemma for convex function. By considering the corresponding sub-martingale on a Brownian motion, we gain more insights about the convex function through a probabilistic viewpoint. The Doob-Meyer decomposition of this sub-martingale subsequently helps us deduce the Ito's lemma for convex function, and enables us to study a convex function via stochastic calculus. In particular, we use this version of Ito's lemma together probabilistic inequalities to recover an important analytic property of the convex function, which is its second-order differentiability.

math.PR↗
arXiv2026

Ionic-instability induced color tuning in lead-based, mixed-halide perovskites

Contrary to conventional wisdom, intermediate photoluminescence energies can be stabilized in mixed-halide lead perovskites during photosegregation. These intermediate energies reside between those of the parent, mixed-halide alloy and fully photosegregated specimens. This demonstrates rudimentary color tuning and has practical implications for potential uses of mixed-halide perovskites in lighting applications. More fundamentally, such color tuning begs the question of how intermediate photosegregation energies arise and how they are kinetically stabilized. What follows is a study of the kinetics of terminal photosegregation energies under pulsed laser excitation. Through concerted continuous wave and pulsed laser photosegregation measurements, we develop a kinetic rationalization for how photosegregations repetition rate or duty cycle and peak fluence dependencies lead to intermediate, terminal photoluminescence energies. The developed model, in turn, explains prior observations of pulsed illumination photosegregation and offers potential insights into other, yet to be explained, phenomena such as spectral blueshifting under high intensity, pulsed illumination.

cond-mat.mtrl-sci↗
arXiv2026

PPEDCRF: Privacy-Preserving Enhanced Dynamic CRF for Location-Privacy Protection for Sequence Videos with Minimal Detection Degradation

Dashcam videos collected by autonomous or assisted-driving systems are increasingly shared for safety auditing and model improvement. Even when explicit GPS metadata are removed, an attacker can still infer the recording location by matching background visual cues (e.g., buildings and road layouts) against large-scale street-view imagery. This paper studies location-privacy leakage under a background-based retrieval attacker, and proposes PPEDCRF, a privacy-preserving enhanced dynamic conditional random field framework that injects calibrated perturbations only into inferred location-sensitive background regions while preserving foreground detection utility. PPEDCRF consists of three components: (i) a dynamic CRF that enforces temporal consistency to discover and track location sensitive regions across frames, (ii) a normalized control penalty (NCP) that allocates perturbation strength according to a hierarchical sensitivity model, and (iii) a utility-preserving noise injection module that minimizes interference to object detection and segmentation. Experiments on public driving datasets demonstrate that PPEDCRF significantly reduces location-retrieval attack success (e.g., Top-k retrieval accuracy) while maintaining competitive detection performance (e.g., mAP and segmentation metrics) compared with common baselines such as global noise, white-noise masking, and feature-based anonymization. The source code is in https://github.com/mabo1215/PPEDCRF.git

cs.CV↗
arXiv2026

Tracing the Evolution of Word Embedding Techniques in Natural Language Processing

This work traces the evolution of word-embedding techniques within the natural language processing (NLP) literature. We collect and analyze 149 research articles spanning the period from 1954 to 2025, providing both a comprehensive methodological review and a data-driven bibliometric analysis of how representation learning has developed over seven decades. Our study covers four major embedding paradigms, statistical representation-based methods (one-hot encoding, bag-of-words, TF-IDF), static word embeddings (Word2Vec, GloVe, FastText), contextual word embeddings (ELMo, BERT, GPT), and sentence/document embeddings, critically discussing the strengths, limitations, and intellectual lineage connecting each category. Beyond the methodological survey, we conduct a formal era comparison using GPT-3's release as a dividing line, applying seven hypothesis tests to quantify shifts in research focus, collaboration patterns, and institutional involvement. Our analysis reveals a dramatic post-GPT-3 paradigm shift: contextual and sentence-level methods now dominate at 6.4X the odds of the pre-GPT-3 era, mean team sizes have grown significantly (p = 0.018), and 30 entirely new techniques have emerged while 54 pre-GPT-3 methods received no further attention. These findings, combined with evidence of rising industry involvement, provide a quantitative account of how the field's epistemic priorities have been reshaped by the advent of large language models.

cs.CY↗
arXiv2026

Decoupled Continuous-Time Reinforcement Learning via Hamiltonian Flow

Many real-world control problems, ranging from finance to robotics, evolve in continuous time with non-uniform, event-driven decisions. Standard discrete-time reinforcement learning (RL), based on fixed-step Bellman updates, struggles in this setting: as time gaps shrink, the $Q$-function collapses to the value function $V$, eliminating action ranking. Existing continuous-time methods reintroduce action information via an advantage-rate function $q$. However, they enforce optimality through complicated martingale losses or orthogonality constraints, which are sensitive to the choice of test processes. These approaches entangle $V$ and $q$ into a large, complex optimization problem that is difficult to train reliably. To address these limitations, we propose a novel decoupled continuous-time actor-critic algorithm with alternating updates: $q$ is learned from diffusion generators on $V$, and $V$ is updated via a Hamiltonian-based value flow that remains informative under infinitesimal time steps, where standard max/softmax backups fail. Theoretically, we prove rigorous convergence via new probabilistic arguments, sidestepping the challenge that generator-based Hamiltonians lack Bellman-style contraction under the sup-norm. Empirically, our method outperforms prior continuous-time and leading discrete-time baselines across challenging continuous-control benchmarks and a real-world trading task, achieving 21% profit over a single quarter$-$nearly doubling the second-best method.

cs.LG↗
arXiv2026

Effect-Level Validation for Causal Discovery

Causal discovery is increasingly applied to large-scale telemetry data to estimate the effects of user-facing interventions, yet its reliability for decision-making in feedback-driven systems with strong self-selection remains unclear. In this paper, we propose an effect-centric, admissibility-first framework that treats discovered graphs as structural hypotheses and evaluates them by identifiability, stability, and falsification rather than by graph recovery accuracy alone. Empirically, we study the effect of early exposure to competitive gameplay on short-term retention using real-world game telemetry. We find that many statistically plausible discovery outputs do not admit point-identified causal queries once minimal temporal and semantic constraints are enforced, highlighting identifiability as a critical bottleneck for decision support. When identification is possible, several algorithm families converge to similar, decision-consistent effect estimates despite producing substantially different graph structures, including cases where the direct treatment-outcome edge is absent and the effect is preserved through indirect causal pathways. These converging estimates survive placebo, subsampling, and sensitivity refutation. In contrast, other methods exhibit sporadic admissibility and threshold-sensitive or attenuated effects due to endpoint ambiguity. These results suggest that graph-level metrics alone are inadequate proxies for causal reliability for a given target query. Therefore, trustworthy causal conclusions in telemetry-driven systems require prioritizing admissibility and effect-level validation over causal structural recovery alone.

cs.AI↗
arXiv2026

StochasticGW-GPU: rapid quasi-particle energies for molecules beyond 10000 atoms

$\mathtt{StochasticGW}$ is a code for computing accurate Quasi-Particle (QP) energies of molecules and material systems in the GW approximation. $\mathtt{StochasticGW}$ utilizes the stochastic Resolution of the Identity (sROI) technique to enable a massively-parallel implementation with computational costs that scale semi-linearly with system size, allowing the method to access systems with tens of thousands of electrons. We introduce a new implementation, $\mathtt{StochasticGW-GPU}$, for which the main bottleneck steps have been ported to GPUs and which gives substantial performance improvements over previous versions of the code. We showcase the new code by computing band gaps of hydrogenated silicon clusters ($\textrm{S}\textrm{i}_{\textrm{x}}\textrm{H}_{\textrm{y}}$) containing up to 10001 atoms and 35144 electrons, and we obtain individual QP energies with a statistical precision of better than $\pm0.03$ eV with times-to-solution on the order of minutes.

physics.chem-ph↗
arXiv2026

Lenses for Partially-Specified States (Extended Version)

A bidirectional transformation is a pair of transformations satisfying certain well-behavedness properties: one maps source data into view data, and the other translates changes on the view back to the source. However, when multiple views share a source, an update on one view may affect the others, making it hard to maintain correspondence while preserving the user's update, especially when multiple views are changed at once. Ensuring these properties within a compositional framework is even more challenging. In this paper, we propose partial-state lenses, which allow source and view states to be partially specified to precisely represent the user's update intentions. These intentions are partially ordered, providing clear semantics for merging intentions of updates coming from multiple views and a refined notion of update preservation compatible with this merging. We formalize partial-state lenses, together with partial-specifiedness-aware well-behavedness that supports compositional reasoning and ensures update preservation. In addition, we demonstrate the utility of the proposed system through examples.

cs.PL↗
arXiv2026

Cyberscurity Threats and Defense Mechanisms in IoT network

The rapid proliferation of Internet of Things (IoT) technologies, projected to exceed 30 billion interconnected devices by 2030, has significantly escalated the complexity of cybersecurity challenges. This survey aims to provide a comprehensive analysis of vulnerabilities, threats, and defense mechanisms, specifically focusing on the integration of network and application layers within real-time monitoring and decision-making systems. Employing an integrative review methodology, 59 scholarly articles published between 2009 and 2024 were selected from databases such as IEEE Xplore, ScienceDirect, and PubMed, utilizing keywords related to IoT vulnerabilities and security attacks. Key findings identify critical threat categories, including sensor vulnerabilities, Denial-of-Service (DoS) attacks, and public cloud insecurity. Conversely, the study highlights advanced defense approaches leveraging Artificial Intelligence (AI) for anomaly detection, Blockchain for decentralized trust, and Zero Trust Architecture (ZTA) for continuous verification. This paper contributes a novel five-layer IoT model and outlines future research directions involving quantum computing and 6G networks to bolster IoT ecosystem resilience.

cs.CR↗
arXiv2025

GRL-SNAM: Geometric Reinforcement Learning with Path Differential Hamiltonians for Simultaneous Navigation and Mapping in Unknown Environments

We present GRL-SNAM, a geometric reinforcement learning framework for Simultaneous Navigation and Mapping(SNAM) in unknown environments. A SNAM problem is challenging as it needs to design hierarchical or joint policies of multiple agents that control the movement of a real-life robot towards the goal in mapless environment, i.e. an environment where the map of the environment is not available apriori, and needs to be acquired through sensors. The sensors are invoked from the path learner, i.e. navigator, through active query responses to sensory agents, and along the motion path. GRL-SNAM differs from preemptive navigation algorithms and other reinforcement learning methods by relying exclusively on local sensory observations without constructing a global map. Our approach formulates path navigation and mapping as a dynamic shortest path search and discovery process using controlled Hamiltonian optimization: sensory inputs are translated into local energy landscapes that encode reachability, obstacle barriers, and deformation constraints, while policies for sensing, planning, and reconfiguration evolve stagewise via updating Hamiltonians. A reduced Hamiltonian serves as an adaptive score function, updating kinetic/potential terms, embedding barrier constraints, and continuously refining trajectories as new local information arrives. We evaluate GRL-SNAM on two different 2D navigation tasks. Comparing against local reactive baselines and global policy learning references under identical stagewise sensing constraints, it preserves clearance, generalizes to unseen layouts, and demonstrates that Geometric RL learning via updating Hamiltonians enables high-quality navigation through minimal exploration via local energy refinement rather than extensive global mapping. The code is publicly available on \href{https://github.com/CVC-Lab/GRL-SNAM}{Github}.

cs.LG↗
arXiv2025

Real-time time-dependent density functional theory for high-energy density physics

Electronic response properties of high-energy density (HED) systems influence planetary structure, drive evolution of fusion targets, and underpin diagnostics in laboratory astrophysics. Real-time time-dependent density functional theory (TDDFT) offers a versatile modeling framework capable of accurately predicting the dynamic response of HED materials -- including free-free, bound-free, and bound-bound contributions without requiring ad hoc state partitioning; capturing both collective and non-collective behavior; and applicable within the linear-response regime and beyond. We review the theoretical formalism of real-time TDDFT as applied to HED systems, provide a practical tutorial for computing relevant response properties (dynamic structure factors, conductivity, and stopping power), and comment on avenues for further development of this powerful computational method in service of HED science.

physics.plasm-ph↗