Showing 1–50 of 195 results for author: Nguyen, S

AuthentiCity: A Multi-Source Provenance-Aware Knowledge Graph and Benchmark for 3D City Models

Authors: Huynh Duc An Son Nguyen, Lukas Arzoumanidis, Youness Dehbi

Abstract: Urban digital twins increasingly combine authoritative, crowd-sourced, machine-learned, and reconstructed data with differing reliability, coverage, and semantics. Yet few urban datasets provide a unified representation supporting multi-source integration, provenance tracking, spatial reasoning, and machine learning. We present AuthentiCity, a multi-source, provenance-aware 3D city knowledge graph… ▽ More Urban digital twins increasingly combine authoritative, crowd-sourced, machine-learned, and reconstructed data with differing reliability, coverage, and semantics. Yet few urban datasets provide a unified representation supporting multi-source integration, provenance tracking, spatial reasoning, and machine learning. We present AuthentiCity, a multi-source, provenance-aware 3D city knowledge graph spanning five cities across three continents (Hamburg, Helsinki, Zurich, New York, and Tokyo) and comprising 180 GiB, 180M nodes, 220M edges, 1.2B properties, and 3.6M buildings. The labeled property graphs integrate authoritative CityGML and OpenStreetMap data for all cities, adding roof-material predictions and reconstructed LoD3 geometry for Hamburg, under a provenance model in which derived information never replaces authoritative data. Confidence-weighted edges resolve cross-source correspondences, constructing canonical urban entities while preserving traceable links to contributing evidence. AuthentiCity is primarily a data contribution. We introduce two benchmark families that demonstrate the tasks enabled by the representation. The first evaluates natural-language-to-query translation beyond conventional text-to-SQL and text-to-Cypher benchmarks, including 3D spatial reasoning, provenance-aware filtering, cross-source agreement and disagreement, coverage-aware aggregation, and infeasible-query detection. The second evaluates graph representation learning through multi-source attribute prediction, node classification, and cross-source matching prediction, enabling comparison of provenance-agnostic and provenance-aware embeddings. Even a strong commercial LLM reaches only 54-69 % execution accuracy and a 7B open-weight model 6-19 %, while the open-weight model never abstains on unanswerable questions. △ Less

Submitted 27 July, 2026; originally announced July 2026.

CrossSpine: Multi-scale Cross-sequence Attention with Anatomical Priors for Automated Pfirrmann Grading

Authors: Hai Son Nguyen, Duong Ngoc Vu, Trong-Nghia Nguyen, Bien Tran Van, Van-Dem Pham, Trang Mai Xuan, Huan Vu, Thien Van Luong

Abstract: Automated grading of Lumbar Disc Degeneration is essential for the objective quantification of structural changes associated with low back pain. Observing that baseline models underperformed on our data, we propose a framework designed to overcome these limitations. First, we present the Cross-sequence Attention Spine (CrossSpine) framework, a novel architecture that employs a cross-sequence atten… ▽ More Automated grading of Lumbar Disc Degeneration is essential for the objective quantification of structural changes associated with low back pain. Observing that baseline models underperformed on our data, we propose a framework designed to overcome these limitations. First, we present the Cross-sequence Attention Spine (CrossSpine) framework, a novel architecture that employs a cross-sequence attention mechanism to adaptively fuse features from different MRI sequences at multiple spa- tial scales. Second, we contribute a meticulously curated dataset aimed at automated Pfirrmann grading. Finally, we introduce an IVD-aware classification technique that integrates anatomical disc-level information, enabling the model to learn level-specific degeneration priors. Our experi- ments demonstrate the superiority of this approach: CrossSpine achieved a relative improvement exceeding 125% in the Macro F1 score, while boosting the Mean AUPRC by 99% and the Mean AUROC by 36% com- pared to the baseline. △ Less

Submitted 22 July, 2026; originally announced July 2026.

PhenSPINE: A Standardized Benchmark for Spine Pathology Diagnosis

Authors: Duong Ngoc Vu, Hai Son Nguyen, Trong-Nghia Nguyen, Bien Tran Van, Trang Mai Xuan, Huan Vu, Thien Van Luong

Abstract: The accurate diagnosis of spinal pathologies depends heavily on radiological interpretation, yet automated systems are hindered by the lack of diverse, high-quality benchmarks. In this study, we present PhenSPINE, a Magnetic Resonance Imaging dataset comprising 16,813 images from 250 patients, curated to facilitate advanced deep learning research. We propose a robust diagnostic benchmark that inte… ▽ More The accurate diagnosis of spinal pathologies depends heavily on radiological interpretation, yet automated systems are hindered by the lack of diverse, high-quality benchmarks. In this study, we present PhenSPINE, a Magnetic Resonance Imaging dataset comprising 16,813 images from 250 patients, curated to facilitate advanced deep learning research. We propose a robust diagnostic benchmark that integrates state-of-theart convolutional backbones with a Positional Encoding mechanism to explicitly model the anatomical context of intervertebral discs. Evaluating across four standard MRI sequences, our experiments demonstrate that the Sagittal T2-weighted sequence offers the most robust diagnostic value, achieving a superior Macro F1-score of 50.31%. We find that multisequence fusion strategies yield inferior performance compared to this single-sequence baseline, as the images across sequences in our dataset are significantly compromised by noise interference from surrounding anatomical regions. This work establishes a robust baseline and offers critical insights into sequence selection for spine analysis. △ Less

Submitted 21 July, 2026; originally announced July 2026.

Comments: 12 pages, figures, Accepted at CITA 2026 (The 15th Conference on Information Technology and its Applications, Scopus)

ACM Class: I.4.6; I.2.10

Trustworthy synthetic data for campaign decision support: strategy simulation fidelity and the PolicySynth framework

Authors: Tung Dang, The Hung Phung, Son Lam Nguyen, Tu Nguyen

Abstract: Decision support systems (DSS) increasingly run retention what-if analysis on synthetic customer populations, because privacy constraints preclude unrestricted use of real data. Such a system is trustworthy only if the synthetic data lead managers to the same decisions as the real data would; yet prevailing criteria certify distributional similarity, not decision alignment, so a synthetic populati… ▽ More Decision support systems (DSS) increasingly run retention what-if analysis on synthetic customer populations, because privacy constraints preclude unrestricted use of real data. Such a system is trustworthy only if the synthetic data lead managers to the same decisions as the real data would; yet prevailing criteria certify distributional similarity, not decision alignment, so a synthetic population can match every marginal distribution while still steering a marketing team toward the wrong campaigns. We close this decision-alignment gap with three contributions: strategy simulation fidelity (SSF), a criterion measuring how often the synthetic population yields the same go/no-go campaign decision as the real population; PolicySynth, a DSS framework whose generator is conditioned on the production churn scorer to align decision-relevant structure; and a three-axis reporting standard of decision alignment, membership-inference resistance, and novel-record rate as the minimum deployment quality gate. On a telecommunications churn corpus and a banking acquisition corpus, PolicySynth attains a mean SSF of 0.923 and 0.960, with seed-to-seed variance roughly ten times tighter than CTGAN on telecommunications and 2.5 times on banking. This stability is the deployable property: go/no-go recommendations shift by at most 1.2 percentage points between monthly retraining cycles, against 11.5 for CTGAN, a reversed recommendation on one campaign in nine. A bootstrap baseline matches PolicySynth on SSF yet copies real records verbatim and fails membership inference, evidence that no single axis suffices. PolicySynth reliably supports directional go/no-go screening; its ROI estimates diverge from real outcomes by 70 to 78% and require the volume correction we document. △ Less

Submitted 13 July, 2026; originally announced July 2026.

Comments: 15 pages, 4 figures

pykci: A Compact Urban Knowledge Graph for Semantic and Spatial Queries using LLMs

Authors: Huynh Duc An Son Nguyen, Lukas Arzoumanidis, Youness Dehbi

Abstract: CityGML, the OGC standard for modeling, storage, and exchange of semantic 3D city models, describes urban objects with detailed semantics, geometry, and topology. Yet this richness is difficult to query directly: CityGML's XML encoding is designed for exchange rather than analysis, and relational mappings expose it through schemas requiring expert knowledge. We present pykci (Python Knowledge Grap… ▽ More CityGML, the OGC standard for modeling, storage, and exchange of semantic 3D city models, describes urban objects with detailed semantics, geometry, and topology. Yet this richness is difficult to query directly: CityGML's XML encoding is designed for exchange rather than analysis, and relational mappings expose it through schemas requiring expert knowledge. We present pykci (Python Knowledge Graph for Cities), an open-source system that transforms CityGML 2.0 datasets into a compact urban knowledge graph in Neo4j and makes it queryable in natural language. The graph schema covers all thematic feature modules of CityGML 2.0 across all levels of detail and is spatially indexed with an R-tree for efficient geometric retrieval. A complete end-to-end Python pipeline ingests CityGML datasets into the knowledge graph, exports them to OGC 3D Tiles for interactive visualization, and supports lossless round-trip export of all content back to CityGML. For querying, the graph is paired with a large language model through a model-agnostic text-to-Cypher mechanism: the graph schema is supplied as context, and the model translates natural-language questions into Cypher queries executed against the graph. We evaluate both a locally running open-weight model, which keeps sensitive city data on-premise, and a state-of-the-art commercial model for the most demanding spatial and semantic queries. Answers are grounded in exact city data rather than the model's parametric memory, reducing hallucination and providing auditable provenance for every response. We demonstrate the system on open-government CityGML LoD2 datasets from Hamburg, Germany, including complex semantic and spatial queries such as identifying roof surfaces suitable for greening. pykci enables urban planners, GIS practitioners, and citizens to interact with semantic 3D city models without expertise in query languages and database schemas. △ Less

Submitted 1 July, 2026; originally announced July 2026.

Cross-Session 3D LiDAR and Camera Fusion for Robust Localization of Unmanned Aerial Vehicles in GPS-Denied Environments

Authors: Cong Hoang Quach, Chi Thanh Vo, Dong LT. Tran, Truong Son Nguyen, Manh Duong Phung, Thuan Hoang Tran

Abstract: Accurate localization of unmanned aerial vehicles (UAVs) is essential for applications such as structural health monitoring, especially in environments where Global Positioning System (GPS) signals are denied or unreliable, like indoor spaces, tunnels, urban canyons, or areas beneath large structures. To address this challenge, we propose Cross-Fusion, a novel method for real-time UAV localization… ▽ More Accurate localization of unmanned aerial vehicles (UAVs) is essential for applications such as structural health monitoring, especially in environments where Global Positioning System (GPS) signals are denied or unreliable, like indoor spaces, tunnels, urban canyons, or areas beneath large structures. To address this challenge, we propose Cross-Fusion, a novel method for real-time UAV localization that integrates data from a 3D Light Detection and Ranging (LiDAR) and a monocular camera. A key contribution is its cross-session fusion strategy, which integrates visual and geometric information collected from multiple agents during routine baseline surveys to improve localization consistency and map completeness. The system employs LiDAR-based odometry for motion tracking and image-based feature matching via a single red-green-blue (RGB) camera to correct drift and improve accuracy. Unlike visual-inertial systems, Cross-Fusion maintains a simple sensor setup and avoids the complexity of stereo or global shutter configurations. Experimental results demonstrate that Cross-Fusion achieves localization accuracy comparable to GPS-based methods and performs reliably in challenging feature-sparse environments. △ Less

Submitted 27 June, 2026; originally announced June 2026.

Comments: Journal of Robotics, 2026

Automated Summarization of Software Documents: An LLM-based Multi-Agent Approach

Authors: Duc S. H. Nguyen, Minh T. Nguyen, Phuong T. Nguyen, Juri Di Rocco, Davide Di Ruscio

Abstract: Large Language Models (LLMs) and LLM-based Multi-Agent Systems (MAS) are revolutionizing software engineering (SE) by advancing automation, decision-making, and knowledge processing. Their recent application to SE tasks has already shown promising results. In this paper, we focus on summarization as a key application area. We present Metagente, an LLM-based MAS designed to generate concise and acc… ▽ More Large Language Models (LLMs) and LLM-based Multi-Agent Systems (MAS) are revolutionizing software engineering (SE) by advancing automation, decision-making, and knowledge processing. Their recent application to SE tasks has already shown promising results. In this paper, we focus on summarization as a key application area. We present Metagente, an LLM-based MAS designed to generate concise and accurate summaries of software documentation. Metagente employs a Teacher-Student architecture where multiple LLM agents collaborate to enhance relevance and precision of produced summaries. An empirical evaluation on real-world datasets demonstrates Metagente's effectiveness in streamlining workflows, outperforming the considered baselines. The evaluation provides evidence that Metagente improves summarization for requirements analysis and technical documentation. Our findings underscore the transformative potential of these technologies in SE, while identifying challenges and future research directions for their seamless integration. △ Less

Submitted 23 June, 2026; originally announced June 2026.

Comments: Paper has been accepted for publication with the Automated Software Engineering journal

TALAS: Teacher-Anchored Layer Alignment with Adaptive Sharpness-Aware Minimization for Embedding Distillation

Authors: Quoc Phong Dao, Hoang Son Nguyen, Pham Khanh Chi, Linh Ngo Van, Nguyen Thi Ngoc Diep, Thien Huu Nguyen, Trung Le

Abstract: Knowledge Distillation (KD) has established itself as a pivotal technique for compressing large pre-trained language models. However, existing methods that force a student to strictly mimic the teacher's sentence embeddings or internal features often incur prohibitive computational costs and yield suboptimal performance due to the inherent capacity gap. To address these challenges, we propose TALA… ▽ More Knowledge Distillation (KD) has established itself as a pivotal technique for compressing large pre-trained language models. However, existing methods that force a student to strictly mimic the teacher's sentence embeddings or internal features often incur prohibitive computational costs and yield suboptimal performance due to the inherent capacity gap. To address these challenges, we propose TALAS (Teacher-Anchored Layer Alignment with Sharpness-aware minimization), a unified framework that synergizes hierarchical (multi-layer) alignment with robust optimization. First, we introduce a Teacher-Anchored mechanism that selectively distills final sentence embeddings only into the student's upper layers, thereby reducing overhead while respecting capacity constraints. Second, we bridge the semantic gap in lower layers via Layer-Aligned Self-Distillation, which propagates knowledge top-down using internal geometric relational constraints in the embedding space. Finally, to prevent the student from memorizing point-wise teacher noise, we integrate Adaptive Sharpness-Aware Minimization (ASAM) into the training objective, guiding the model towards flat minima for enhanced generalization. Empirical results on standard sentence embedding benchmarks demonstrate that TALAS consistently outperforms strong distillation baselines while achieving superior training efficiency in terms of computational cost and memory footprint. △ Less

Submitted 19 June, 2026; originally announced June 2026.

Comments: ACL 2026

PiDA: Phonetically-Informed Data Augmentation for Robust Vietnamese Speech Translation

Authors: Giang Son Nguyen, Tung X. Nguyen, Hieu Minh Truong, Nhu Vo, Wray Buntine, Dung D. Le

Abstract: Cascaded speech translation (ST) systems suffer from error propagation when Automatic Speech Recognition (ASR) outputs incorrect transcripts. We present the first systematic categorization of ASR errors for Vietnamese ST, classifying substitution errors by phonetic cause and quantifying their impact on downstream Neural Machine Translation (NMT) performance using Linear Mixed-Effects Modelling. We… ▽ More Cascaded speech translation (ST) systems suffer from error propagation when Automatic Speech Recognition (ASR) outputs incorrect transcripts. We present the first systematic categorization of ASR errors for Vietnamese ST, classifying substitution errors by phonetic cause and quantifying their impact on downstream Neural Machine Translation (NMT) performance using Linear Mixed-Effects Modelling. We confirm that most ASR substitution errors arise from phonetic confusions rather than random noise, and that these phonetic errors significantly degrade ST quality. Motivated by this finding, we propose Phonetically-Informed Data Augmentation (PiDA), which generates ASR-like corruptions by substituting words with phonetically similar alternatives using phonetic word embeddings. Fine-tuning on a PiDA-augmented version of FLEURS Vietnamese-English improves translation of erroneous ASR outputs (up to +2.04 BLEU over standard fine-tuning) while also slightly improving clean-text performance. △ Less

Submitted 11 June, 2026; originally announced June 2026.

Comments: Accepted to INTERSPEECH 2026

A Data-Centric Framework for Detecting and Correcting Corrupted Labels

Authors: Ha-Linh Nguyen, Hong-Anh Nguyen, Minh-Duc La, Thu-Trang Nguyen, Son Nguyen, Hieu Dinh Vo

Abstract: The performance of machine learning and deep learning models largely depends on the quality of the training data. However, the quality of the real-world datasets is often compromised by noisy labels, which can substantially degrade model accuracy and reliability. To address this challenge, we propose Relabeler, an end-to-end data-centric framework for detecting and correcting corrupted labels. For… ▽ More The performance of machine learning and deep learning models largely depends on the quality of the training data. However, the quality of the real-world datasets is often compromised by noisy labels, which can substantially degrade model accuracy and reliability. To address this challenge, we propose Relabeler, an end-to-end data-centric framework for detecting and correcting corrupted labels. For corrupted label detection, Relabeler jointly leverages both local and global relationships among data instances to identify potentially noisy samples. After detecting suspicious instances, Relabeler further performs label correction by estimating the most probable clean label for each instance based on both its input features and observed noisy label. Extensive experiments across multiple datasets, noise types, and noise rates demonstrate that Relabeler consistently outperforms state-of-the-art baselines, achieving up to 58% improvement in label correction precision and 6% improvement in downstream task performance. △ Less

Submitted 10 June, 2026; originally announced June 2026.

Noise-Aware Framework for Correcting Corrupted Labels

Authors: Ha-Linh Nguyen, Hong-Anh Nguyen, Minh-Duc La, Phong Lam, Thu-Trang Nguyen, Son Nguyen, Hieu Dinh Vo

Abstract: High-quality labeled data is essential for training reliable ML/DL models. However, real-world datasets often contain a considerable proportion of corrupted labels, which can severely degrade model performance. To address this problem, we propose CANOLA, a novel framework for correcting corrupted labels through noise-aware learning and iterative label refinement. CANOLA explicitly estimates the un… ▽ More High-quality labeled data is essential for training reliable ML/DL models. However, real-world datasets often contain a considerable proportion of corrupted labels, which can severely degrade model performance. To address this problem, we propose CANOLA, a novel framework for correcting corrupted labels through noise-aware learning and iterative label refinement. CANOLA explicitly estimates the underlying noise distribution of the dataset and incorporates this information into the training of a noise-aware Deep Neural Network. By incorporating noise characteristics during learning, CANOLA enables the model to down-weight unreliable supervision signals and focus on trustworthy patterns, thereby improving robustness and generalization. Label correction is performed via cautious, iterative soft label refinement, in which model predictions are blended with observed labels to prevent premature or erroneous updates. This progressive refinement allows the dataset to be repaired in a stable and controlled manner. We evaluate CANOLA on six widely used datasets under realistic noisy labeling scenarios. Experimental results show that CANOLA consistently outperforms SOTA label correction methods, achieving relative improvements ranging from 19% to 52% in error reduction. Moreover, models trained on datasets corrected by CANOLA obtain substantial downstream performance gains. Even simple classifiers trained on CANOLA's corrected data can outperform complex model-centric approaches by margins of up to 67%. △ Less

Submitted 10 June, 2026; originally announced June 2026.

Contrastive Training with LLM-generated Near-Misses for Robust Code-Switching Speech Recognition

Authors: Tung X. Nguyen, Hieu Minh Truong, Giang Son Nguyen, Nhu Vo, Wray Buntine, Dung D. Le

Abstract: Code-switching (CS), the alternation between multiple languages within a single utterance, remains challenging for Automatic Speech Recognition (ASR). To address this issue, we propose a Point-of-Interest (POI)-aware contrastive training framework that improves recognition at CS-critical regions. We first identify CS spans by adopting POI detection method from literature, then construct acoustical… ▽ More Code-switching (CS), the alternation between multiple languages within a single utterance, remains challenging for Automatic Speech Recognition (ASR). To address this issue, we propose a Point-of-Interest (POI)-aware contrastive training framework that improves recognition at CS-critical regions. We first identify CS spans by adopting POI detection method from literature, then construct acoustically plausible near-miss hypotheses by perturbing POIs in ASR N-best outputs and expanding candidates with a large language model. Hard but plausible negatives are retained through filtering with acoustic, phonemic, and textual constraints. Finally, we fine-tune Whisper-small with LoRA using a POI-weighted cross-entropy anchor objective together with a multi-negative contrastive ranking loss. Experiments on CS-FLEURS (cmn-eng) and ViMedCSS (vie-eng) show consistent reductions of over 2% in both general and CS-aware error rates compared to standard LoRA fine-tuning. △ Less

Submitted 22 June, 2026; v1 submitted 5 June, 2026; originally announced June 2026.

Comments: Accepted at INTERSPEECH 2026

CUPID in the Model Zoo: Online Matchmaking for Selecting Your Dream LLM

Authors: Son Nguyen, Xinyuan Liu, Ransalu Senanayake

Abstract: Users increasingly face the challenge of selecting an appropriate LLM for a given task from a rapidly growing pool of LLMs, each with distinct but often opaque latent properties. Compounding this challenge, users may lack the vocabulary or awareness to explicitly articulate the characteristics they value in an LLM's responses or deployment. We propose an interaction-efficient active learning frame… ▽ More Users increasingly face the challenge of selecting an appropriate LLM for a given task from a rapidly growing pool of LLMs, each with distinct but often opaque latent properties. Compounding this challenge, users may lack the vocabulary or awareness to explicitly articulate the characteristics they value in an LLM's responses or deployment. We propose an interaction-efficient active learning framework in which a dueling bandit algorithm iteratively selects pairs of LLMs, collects user feedback about their responses, and updates its belief about the user's latent preferences. We introduce a novel belief-aware upper confidence bound strategy that balances exploration of the model pool with exploitation of inferred preferences, enabling efficient alignment between user needs and LLM capabilities under user-specified cost and time budgets. Through diverse experiments on LLMs and human studies, we experimentally verify that our model can efficiently match well-aligned LLMs to users at a lower cost. △ Less

Submitted 30 May, 2026; originally announced June 2026.

Comments: 38 pages, 11 figures

VisAnalog: A Diagnostic Suite for Visual Concept Transfer on Natural Images

Authors: Zhaonan Li, Kyle R. Chickering, Bangzheng Li, Jacob Dineen, Xiao Ye, Zhikun Xu, Shijie Lu, Yuxi Huang, Ming Shen, Bach Nguyen, Jaya Adithya Pavuluri, Mau Son Nguyen, Sanika Chavan, Ngoc Minh Thu Le, Muhao Chen, Ben Zhou

Abstract: A useful test of visual concept learning is not just whether a model can recognize a concept in a single image, but whether it can preserve and manipulate concept-level properties under transformation and transfer them to new scenes. We introduce VisAnalog, a controlled suite for this setting on natural images. Each example instantiates $A\!:\!B::C\!:\,?$: images $B$ and a hidden target image $D$… ▽ More A useful test of visual concept learning is not just whether a model can recognize a concept in a single image, but whether it can preserve and manipulate concept-level properties under transformation and transfer them to new scenes. We introduce VisAnalog, a controlled suite for this setting on natural images. Each example instantiates $A\!:\!B::C\!:\,?$: images $B$ and a hidden target image $D$ are produced by applying the same deterministic transformation sequence to source images $A$ and $C$. Given $A$, $B$, and $C$, a model must answer a multiple-choice question about $D$. The benchmark contains 617 human-validated questions spanning one- to four-step transformations such as zoom, quadrant swap, rotation, flip, and hue rotation. Across strong proprietary and open-source VLMs, end-to-end accuracy is substantially lower than oracle accuracy when $D$ is directly shown, and degrades sharply as transformation depth increases, while human performance remains near the ceiling. A program-conditioned evaluation further separates failures of relation inference from failures of transformation application, showing that inferring the visual relation from $A \rightarrow B$ is the dominant bottleneck, with additional application errors emerging on harder multi-step cases. The dataset is publicly available at https://huggingface.co/datasets/zli99/VisAnalog. △ Less

Submitted 21 May, 2026; originally announced May 2026.

Comments: Accepted to the Workshop on Visual Concepts at CVPR 2026 as a non-archival report

Cross-Lingual Consensus: Aligning Multilingual Cultural Knowledge via Multilingual Self-Consistency

Authors: Andrew Ivan Soegeng, Patrick Sutanto, Tan Sang Nguyen

Abstract: Although Large Language Models (LLMs) demonstrate strong capabilities across various tasks, they exhibit significant performance discrepancies across languages. While prompting LLMs in English typically yields the highest general performance, it often induces a Western-centric bias, hindering the model's ability to accurately reflect diverse cultural knowledge. We hypothesize that LLMs already pos… ▽ More Although Large Language Models (LLMs) demonstrate strong capabilities across various tasks, they exhibit significant performance discrepancies across languages. While prompting LLMs in English typically yields the highest general performance, it often induces a Western-centric bias, hindering the model's ability to accurately reflect diverse cultural knowledge. We hypothesize that LLMs already possess rich cultural knowledge embedded within local-language representations, but fail to retrieve it when prompted in English. To bridge this cross-lingual knowledge gap, we propose a novel self-supervised framework. Our method leverages multilingual self-consistency to identify the most reliable cultural responses across languages, combined with a self-critique mechanism to transfer this knowledge to the weaker language. Evaluations on the BLEnD benchmark demonstrate that our approach significantly improves cultural alignment-boosting performance on English queries by an average of 5.03%-relying entirely on self-generated data. Ultimately, our work demonstrates that latent cultural knowledge can be successfully surfaced and propagated across languages, enabling more culturally equitable and consistent LLMs. △ Less

Submitted 25 May, 2026; v1 submitted 21 May, 2026; originally announced May 2026.

Comments: Accepted to The 1st Workshop on Multilinguality in the Era of Large Language Models

SRA: Span Representation Alignment for Large Language Model Distillation

Authors: Quoc Phong Dao, Hoang Son Nguyen, Pham Khanh Chi, Tung Nguyen, Linh Ngo Van, Nguyen Thi Ngoc Diep, Trung Le

Abstract: Cross-Tokenizer Knowledge Distillation (CTKD) enables knowledge transfer between a large language model and a smaller student, even when they employ different tokenizers. While existing approaches mainly focus on token-level alignment strategies, which are often brittle and sensitive to discrepancies between tokenizers, we argue that the method of aggregating tokens into more robust representation… ▽ More Cross-Tokenizer Knowledge Distillation (CTKD) enables knowledge transfer between a large language model and a smaller student, even when they employ different tokenizers. While existing approaches mainly focus on token-level alignment strategies, which are often brittle and sensitive to discrepancies between tokenizers, we argue that the method of aggregating tokens into more robust representations before distillation is of equal importance. In this paper, we introduce \textbf{SRA} (\textbf{S}pan \textbf{R}epresentation \textbf{A}lignment for Large Language Model Distillation), a novel framework that reframes CTKD through the physical lens of Multi-Particle Dynamical Systems. SRA shifts the fundamental unit of alignment from tokens to robust, tokenizer-agnostic spans. We model each span as a cluster of particles and represent its state by its Center of Mass (CoM) - an attention-weighted average that captures rich semantic information. We leverage the concept of span centers of mass with attention-derived weighting to prioritize the most salient spans. In addition, we employ a geometric regularizer to preserve the structural integrity of the representation space and introduce aligned span logit distillation to enhance knowledge transfer across models. In challenging cross-architecture distillation experiments, SRA consistently and significantly outperforms state-of-the-art CTKD baselines, validating our physically-grounded approach. △ Less

Submitted 2 June, 2026; v1 submitted 1 May, 2026; originally announced May 2026.

Comments: ACL 2026

Batch Normalization for Neural Networks on Complex Domains

Authors: Xuan Son Nguyen, Nistor Grozavu

Abstract: Riemannian neural networks have proven effective in solving a variety of machine learning tasks. The key to their success lies in the development of principled Riemannian analogs of fundamental building blocks in deep neural networks (DNNs). Among those, Riemannian batch normalization (BN) layers have shown to enhance training stability and improve accuracy. In this paper, we propose BN layers for… ▽ More Riemannian neural networks have proven effective in solving a variety of machine learning tasks. The key to their success lies in the development of principled Riemannian analogs of fundamental building blocks in deep neural networks (DNNs). Among those, Riemannian batch normalization (BN) layers have shown to enhance training stability and improve accuracy. In this paper, we propose BN layers for neural networks on complex domains. The proposed layers have close connections with existing Riemannian BN layers. We derive essential components for practical implementations of BN layers on some complex domains which are less studied in previous works, e.g., the Siegel disk domain. We conduct experiments on radar clutter classification, node classification, and action recognition demonstrating the efficacy of our method. △ Less

Submitted 1 May, 2026; originally announced May 2026.

Region-Grounded Report Generation for 3D Medical Imaging: A Fine-Grained Dataset and Graph-Enhanced Framework

Authors: Cong Huy Nguyen, Son Dinh Nguyen, Guanlin Li, Tuan Dung Nguyen, Aditya Narayan Sankaran, Mai Huy Thong, Thanh Trung Nguyen, Mai Hong Son, Reza Farahbakhsh, Phi Le Nguyen, Noel Crespi

Abstract: Automated medical report generation for 3D PET/CT imaging is fundamentally challenged by the high-dimensional nature of volumetric data and a critical scarcity of annotated datasets, particularly for low-resource languages. Current black-box methods map whole volumes to reports, ignoring the clinical workflow of analyzing localized Regions of Interest (RoIs) to derive diagnostic conclusions. In th… ▽ More Automated medical report generation for 3D PET/CT imaging is fundamentally challenged by the high-dimensional nature of volumetric data and a critical scarcity of annotated datasets, particularly for low-resource languages. Current black-box methods map whole volumes to reports, ignoring the clinical workflow of analyzing localized Regions of Interest (RoIs) to derive diagnostic conclusions. In this paper, we bridge this gap by introducing VietPET-RoI, the first large-scale 3D PET/CT dataset with fine-grained RoI annotation for a low-resource language, comprising 600 PET/CT samples and 1,960 manually annotated RoIs, paired with corresponding clinical reports. Furthermore, to demonstrate the utility of this dataset, we propose HiRRA, a novel framework that mimics the professional radiologist diagnostic workflow by employing graph-based relational modules to capture dependencies between RoI attributes. This approach shifts from global pattern matching toward localized clinical findings. Additionally, we introduce new clinical evaluation metrics, namely RoI Coverage and RoI Quality Index, that measure both RoI localization accuracy and attribute description fidelity using LLM-based extraction. Extensive evaluation demonstrates that our framework achieves SOTA performance, surpassing existing models by 19.7% in BLEU and 4.7% in ROUGE-L, while achieving a remarkable 45.8% improvement in clinical metrics, indicating enhanced clinical reliability and reduced hallucination. Our code and dataset are available on GitHub. △ Less

Submitted 15 May, 2026; v1 submitted 20 April, 2026; originally announced April 2026.

Comments: 16 pages; Accepted to appear in ACL 2026

Structured Exploration and Exploitation of Label Functions for Automated Data Annotation

Authors: Phong Lam, Ha-Linh Nguyen, Thu-Trang Nguyen, Son Nguyen, Hieu Dinh Vo

Abstract: High-quality labeled data is critical for training reliable machine learning and deep learning models, yet manual annotation remains costly and error-prone. Programmatic labeling addresses this challenge by using label functions (LFs), i.e., heuristic rules that automatically generate weak labels for training datasets. However, existing automated LF generation methods either rely on large language… ▽ More High-quality labeled data is critical for training reliable machine learning and deep learning models, yet manual annotation remains costly and error-prone. Programmatic labeling addresses this challenge by using label functions (LFs), i.e., heuristic rules that automatically generate weak labels for training datasets. However, existing automated LF generation methods either rely on large language models (LLMs) to synthesize surface-level heuristics or employ model-based synthesis over hand-crafted primitives. These approaches often result in limited coverage and unreliable label quality. In this paper, we introduce EXPONA, an automated framework for programmatic labeling that formulates LF generation as a principled process balancing diversity and reliability. EXPONA systematically explores multi-level LFs, spanning surface, structural, and semantic perspectives. EXPONA further applies reliability-aware mechanisms to suppress noisy or redundant heuristics while preserving complementary signals. To evaluate EXPONA, we conducted extensive experiments on eleven classification datasets across diverse domains. Experimental results show that EXPONA consistently outperformed state-of-the-art automated LF generation methods. Specifically, EXPONA achieved nearly complete label coverage (up to 98.9%), improved weak label quality by up to 87%, and yielded downstream performance gains of up to 46% in weighted F1. These results indicate that EXPONA's combination of multi-level LF exploration and reliability-aware filtering enabled more consistent label quality and downstream performance across diverse tasks by balancing coverage and precision in the generated LF set. △ Less

Submitted 28 March, 2026; originally announced April 2026.

Comments: Accepted by KBS Journal

REALITrees: Rashomon Ensemble Active Learning for Interpretable Trees

Authors: Simon D. Nguyen, Hayden McTavish, Kentaro Hoffman, Cynthia Rudin, Tyler H. McCormick

Abstract: Active learning reduces labeling costs by selecting samples that maximize information gain. A dominant framework, Query-by-Committee (QBC), typically relies on perturbation-based diversity by inducing model disagreement through random feature subsetting or data blinding. While this approximates one notion of epistemic uncertainty, it sacrifices direct characterization of the plausible hypothesis s… ▽ More Active learning reduces labeling costs by selecting samples that maximize information gain. A dominant framework, Query-by-Committee (QBC), typically relies on perturbation-based diversity by inducing model disagreement through random feature subsetting or data blinding. While this approximates one notion of epistemic uncertainty, it sacrifices direct characterization of the plausible hypothesis space. We propose the complementary approach: Rashomon Ensembled Active Learning (REAL) which constructs a committee by exhaustively enumerating the Rashomon Set of all near-optimal models. To address functional redundancy within this set, we adopt a PAC-Bayesian framework using a Gibbs posterior to weight committee members by their empirical risk. Leveraging recent algorithmic advances, we exactly enumerate this set for the class of sparse decision trees. Across synthetic and established active learning baselines, REAL outperforms randomized ensembles, particularly in moderately noisy environments where it strategically leverages expanded model multiplicity to achieve faster convergence. △ Less

Submitted 23 March, 2026; originally announced March 2026.

LLM Routing as Reasoning: A MaxSAT View

Authors: Son Nguyen, Xinyuan Liu, Ransalu Senanayake

Abstract: Routing a query through an appropriate LLM is challenging, particularly when user preferences are expressed in natural language and model attributes are only partially observable. We propose a constraint-based interpretation of language-conditioned LLM routing, formulating it as a weighted MaxSAT/MaxSMT problem in which natural language feedback induces hard and soft constraints over model attribu… ▽ More Routing a query through an appropriate LLM is challenging, particularly when user preferences are expressed in natural language and model attributes are only partially observable. We propose a constraint-based interpretation of language-conditioned LLM routing, formulating it as a weighted MaxSAT/MaxSMT problem in which natural language feedback induces hard and soft constraints over model attributes. Under this view, routing corresponds to selecting models that approximately maximize satisfaction of feedback-conditioned clauses. Empirical analysis on a 25-model benchmark shows that language feedback produces near-feasible recommendation sets, while no-feedback scenarios reveal systematic priors. Our results suggest that LLM routing can be understood as structured constraint optimization under language-conditioned preferences. △ Less

Submitted 13 March, 2026; originally announced March 2026.

LLMGreenRec: LLM-Based Multi-Agent Recommender System for Sustainable E-Commerce

Authors: Hao N. Nguyen, Hieu M. Nguyen, Son Van Nguyen, Nguyen Thi Hanh

Abstract: Rising environmental awareness in e-commerce necessitates recommender systems that not only guide users to sustainable products but also minimize their own digital carbon footprints. Traditional session-based systems, optimized for short-term conversions, often fail to capture nuanced user intents for eco-friendly choices, perpetuating a gap between green intentions and actions. To tackle this, we… ▽ More Rising environmental awareness in e-commerce necessitates recommender systems that not only guide users to sustainable products but also minimize their own digital carbon footprints. Traditional session-based systems, optimized for short-term conversions, often fail to capture nuanced user intents for eco-friendly choices, perpetuating a gap between green intentions and actions. To tackle this, we introduce LLMGreenRec, a novel multi-agent framework that leverages Large Language Models (LLMs) to promote sustainable consumption. Through collaborative analysis of user interactions and iterative prompt refinement, LLMGreenRec's specialized agents deduce green-oriented user intents and prioritize eco-friendly product recommendations. Notably, this intent-driven approach also reduces unnecessary interactions and energy consumption. Extensive experiments on benchmark datasets validate LLMGreenRec's effectiveness in recommending sustainable products, demonstrating a robust solution that fosters a responsible digital economy. △ Less

Submitted 11 March, 2026; originally announced March 2026.

Comments: Accepted to the Proceedings of the Conference on Digital Economy and Fintech Innovation (DEFI 2025). To appear in IEEE Xplore

Adaptive Active Learning for Regression via Reinforcement Learning

Authors: Simon D. Nguyen, Troy Russo, Kentaro Hoffman, Tyler H. McCormick

Abstract: Active learning for regression reduces labeling costs by selecting the most informative samples. Improved Greedy Sampling is a prominent method that balances feature-space diversity and output-space uncertainty using a static, multiplicative rule. We propose Weighted improved Greedy Sampling (WiGS), which replaces this framework with a dynamic, additive criterion. We formulate weight selection as… ▽ More Active learning for regression reduces labeling costs by selecting the most informative samples. Improved Greedy Sampling is a prominent method that balances feature-space diversity and output-space uncertainty using a static, multiplicative rule. We propose Weighted improved Greedy Sampling (WiGS), which replaces this framework with a dynamic, additive criterion. We formulate weight selection as a reinforcement learning problem, enabling an agent to adapt the exploration-investigation balance throughout learning. Experiments on 18 benchmark datasets and a synthetic environment show WiGS outperforms iGS and other baseline methods in both accuracy and labeling efficiency, particularly in domains with irregular data density where the baseline's multiplicative rule ignores high-error samples in dense regions. △ Less

Submitted 11 March, 2026; originally announced March 2026.

Comments: 33 pages, 103 figures. Main paper (8 pages, 4 figures) plus appendix with proofs and supplemental experimental results. Submitted to UAI2026. Codebase available at https://github.com/thatswhatsimonsaid/WeightedGreedySampling

Retcon -- a Prompt-Based Technique for Precise Control of LLMs in Conversations

Authors: David Kogan, Sam Nguyen, Masanori Suzuki, Feiyang Chen

Abstract: Recent advances in Large Language Models (LLMs) allow agents to execute complex natural language tasks. Many LLM applications, such as support agents, teaching assistants, and interactive bots, involve multi-turn conversations. However, it remains challenging to control LLMs in the context of such interactions, particularly when the LLM behavior needs to be adjustable over the course of the conver… ▽ More Recent advances in Large Language Models (LLMs) allow agents to execute complex natural language tasks. Many LLM applications, such as support agents, teaching assistants, and interactive bots, involve multi-turn conversations. However, it remains challenging to control LLMs in the context of such interactions, particularly when the LLM behavior needs to be adjustable over the course of the conversation. In this paper, we present Retcon, a few-shot prompting technique designed to provide turn-level control over LLMs in conversations. We then demonstrate that it performs significantly better than zero-shot and traditional few-shot prompting. △ Less

Submitted 9 February, 2026; originally announced March 2026.

Comments: 5 pages, 2 figures, 3 appendixes with prompts and examples

Beyond the Flag: A Framework for Integrating Cybersecurity Competitions into K-12 Education for Cognitive Apprenticeship and Ethical Skill Development

Authors: Tran Duc Le, Truong Duy Dinh, Phuc Hao Do, Van Dai Pham, Nam Son Nguyen

Abstract: Capture the Flag (CTF) competitions are powerful pedagogical tools for addressing the global cybersecurity workforce gap, yet their effective K-12 implementation is often undermined by significant barriers, including educator preparedness gaps and equity concerns. This paper addresses these challenges by proposing the Ethical-Cognitive Apprenticeship in Cybersecurity (ECAC) framework, a new model… ▽ More Capture the Flag (CTF) competitions are powerful pedagogical tools for addressing the global cybersecurity workforce gap, yet their effective K-12 implementation is often undermined by significant barriers, including educator preparedness gaps and equity concerns. This paper addresses these challenges by proposing the Ethical-Cognitive Apprenticeship in Cybersecurity (ECAC) framework, a new model derived from a systematic Framework Synthesis of existing literature and empirical evidence. ECAC systematically integrates cognitive apprenticeship theory with embedded ethical development across five phases: (1) Foundational Modeling, (2) Scaffolding the Arena, (3) Coaching and Articulation, (4) Ethical Dilemma Injections, and (5) Reflective Exploration. The framework provides a "low floor, high ceiling" learning pathway designed to broaden participation among diverse student groups, including underrepresented minorities and women, while fostering deep, transferable skills. By reframing the educator role as a lead learner," ECAC also offers a sustainable solution to the teacher expertise gap. Ultimately, this framework provides a practical roadmap for transforming CTFs from standalone competitions into integral learning experiences that cultivate a more skilled, ethical, and diverse generation of cybersecurity professionals. △ Less

Submitted 18 February, 2026; originally announced February 2026.

Comments: 38 pages, 2 figures

ACM Class: K.3.1; K.3.2

iML: Executable, Problem-Grounded, and Broadly Exploratory Code-Driven AutoML

Authors: Dat Le, Duc-Cuong Le, Anh-Son Nguyen, Tuan-Dung Bui, Thu-Trang Nguyen, Son Nguyen, Hieu Dinh Vo

Abstract: Automated Machine Learning (AutoML) has improved access to machine learning, yet existing techniques often remain limited in flexibility, transparency, and execution reliability. Code-driven AutoML offers a promising direction by synthesizing executable code for preprocessing, model training, and evaluation. However, current LLM-based approaches frequently generate code that is plausible in text y… ▽ More Automated Machine Learning (AutoML) has improved access to machine learning, yet existing techniques often remain limited in flexibility, transparency, and execution reliability. Code-driven AutoML offers a promising direction by synthesizing executable code for preprocessing, model training, and evaluation. However, current LLM-based approaches frequently generate code that is plausible in text yet brittle in execution, insufficiently grounded in the actual dataset, or restricted to narrow solution paths. In this paper, we introduce iML, a multi-agent code-driven AutoML framework designed around three requirements: executability, problem grounding, and broad exploration of valid solutions. iML first analyzes the task and profiles the data, then synthesizes a structured blueprint that guides modular code generation across multiple implementation tracks, including traditional ML,pretrained adaptation, and custom neural architectures. To improve reliability, iML enforces interface checking, dynamic execution, and iterative debugging during integration. We evaluate iML on MLE-BENCH and the newly introduced iML-BENCH, covering diverse Kaggle-style tasks. On MLE-BENCH, iML attains a 90% valid submission rate and a 45% medal rate, and an APS of 0.82, improving the average standardized performance score (APS) over the LLM-based baselines by 52%-273%. On iML-BENCH, it achieves the highest APS and demonstrates robust performance even when task descriptions are substantially stripped. These results establish iML as a reliable and competitive framework for code-driven AutoML. △ Less

Submitted 29 May, 2026; v1 submitted 14 February, 2026; originally announced February 2026.

An Online Reference-Free Evaluation Framework for Flowchart Image-to-Code Generation

Authors: Giang Son Nguyen, Zi Pong Lim, Sarthak Ketanbhai Modi, Yon Shin Teo, Wenya Wang

Abstract: Vision-Language Models (VLMs) are increasingly used in document processing pipelines to convert flowchart images into structured code (e.g., Mermaid). In production, these systems process arbitrary inputs for which no ground-truth code exists, making output quality difficult to assess. We propose a reference-free evaluation framework that monitors flowchart image-to-code generation quality at infe… ▽ More Vision-Language Models (VLMs) are increasingly used in document processing pipelines to convert flowchart images into structured code (e.g., Mermaid). In production, these systems process arbitrary inputs for which no ground-truth code exists, making output quality difficult to assess. We propose a reference-free evaluation framework that monitors flowchart image-to-code generation quality at inference time, using only the input image and the generated output. The framework introduces two automated metrics: $\text{Recall}{\text{OCR}}$, which estimates content coverage by extracting text from the input image via OCR as a proxy reference, and $\text{Precision}{\text{VE}}$, which detects hallucinated elements through Visual Entailment against the original image. Their harmonic mean, $\text{F1}{\text{OCR-VE}}$, provides a unified quality score. Validation on the FlowVQA dataset shows strong agreement with ground-truth metrics (average Pearson's $r = 0.97$, $0.91$, and $0.94$ for Recall, Precision, and F1, respectively), confirming the framework's reliability as a practical, reference-free alternative for continuous quality monitoring in production settings. △ Less

Submitted 8 July, 2026; v1 submitted 13 February, 2026; originally announced February 2026.

Comments: This manuscript was inadvertently made publicly available before all necessary internal review processes had been completed. The authors are withdrawing the manuscript

ViHERMES: A Graph-Grounded Multihop Question Answering Benchmark and System for Vietnamese Healthcare Regulations

Authors: Long S. T. Nguyen, Quan M. Bui, Tin T. Ngo, Quynh T. N. Vo, Dung N. H. Le, Tho T. Quan

Abstract: Question Answering (QA) over regulatory documents is inherently challenging due to the need for multihop reasoning across legally interdependent texts, a requirement that is particularly pronounced in the healthcare domain where regulations are hierarchically structured and frequently revised through amendments and cross-references. Despite recent progress in retrieval-augmented and graph-based QA… ▽ More Question Answering (QA) over regulatory documents is inherently challenging due to the need for multihop reasoning across legally interdependent texts, a requirement that is particularly pronounced in the healthcare domain where regulations are hierarchically structured and frequently revised through amendments and cross-references. Despite recent progress in retrieval-augmented and graph-based QA methods, systematic evaluation in this setting remains limited, especially for low-resource languages such as Vietnamese, due to the lack of benchmark datasets that explicitly support multihop reasoning over healthcare regulations. In this work, we introduce the Vietnamese Healthcare Regulations-Multihop Reasoning Dataset (ViHERMES), a benchmark designed for multihop QA over Vietnamese healthcare regulatory documents. ViHERMES consists of high-quality question-answer pairs that require reasoning across multiple regulations and capture diverse dependency patterns, including amendment tracing, cross-document comparison, and procedural synthesis. To construct the dataset, we propose a controlled multihop QA generation pipeline based on semantic clustering and graph-inspired data mining, followed by large language model-based generation with structured evidence and reasoning annotations. We further present a graph-aware retrieval framework that models formal legal relations at the level of legal units and supports principled context expansion for legally valid and coherent answers. Experimental results demonstrate that ViHERMES provides a challenging benchmark for evaluating multihop regulatory QA systems and that the proposed graph-aware approach consistently outperforms strong retrieval-based baselines. The ViHERMES dataset and system implementation are publicly available at https://github.com/ura-hcmut/ViHERMES. △ Less

Submitted 6 February, 2026; originally announced February 2026.

Comments: Accepted at ACIIDS 2026

OpenSeal: Good, Fast, and Cheap Construction of an Open-Source Southeast Asian LLM via Parallel Data

Authors: Tan Sang Nguyen, Muhammad Reza Qorib, Hwee Tou Ng

Abstract: Large language models (LLMs) have proven to be effective tools for a wide range of natural language processing (NLP) applications. Although many LLMs are multilingual, most remain English-centric and perform poorly on low-resource languages. Recently, several Southeast Asia-focused LLMs have been developed, but none are truly open source, as they do not publicly disclose their training data. Truly… ▽ More Large language models (LLMs) have proven to be effective tools for a wide range of natural language processing (NLP) applications. Although many LLMs are multilingual, most remain English-centric and perform poorly on low-resource languages. Recently, several Southeast Asia-focused LLMs have been developed, but none are truly open source, as they do not publicly disclose their training data. Truly open-source models are important for transparency and for enabling a deeper and more precise understanding of LLM internals and development, including biases, generalization, and multilinguality. Motivated by recent advances demonstrating the effectiveness of parallel data in improving multilingual performance, we conduct controlled and comprehensive experiments to study the effectiveness of parallel data in continual pretraining of LLMs. Our findings show that using only parallel data is the most effective way to extend an LLM to new languages. Using just 34.7B tokens of parallel data and 180 hours on 8x NVIDIA H200 GPUs, we built OpenSeal, the first truly open Southeast Asian LLM that rivals the performance of existing models of similar size. △ Less

Submitted 2 February, 2026; originally announced February 2026.

EditYourself: Audio-Driven Generation and Manipulation of Talking Head Videos with Diffusion Transformers

Authors: John Flynn, Wolfgang Paier, Dimitar Dinev, Sam Nhut Nguyen, Hayk Poghosyan, Manuel Toribio, Sandipan Banerjee, Guy Gafni

Abstract: Current generative video models excel at producing novel content from text and image prompts, but leave a critical gap in editing existing pre-recorded videos, where minor alterations to the spoken script require preserving motion, temporal coherence, speaker identity, and accurate lip synchronization. We introduce EditYourself, a DiT-based framework for audio-driven video-to-video (V2V) editing t… ▽ More Current generative video models excel at producing novel content from text and image prompts, but leave a critical gap in editing existing pre-recorded videos, where minor alterations to the spoken script require preserving motion, temporal coherence, speaker identity, and accurate lip synchronization. We introduce EditYourself, a DiT-based framework for audio-driven video-to-video (V2V) editing that enables transcript-based modification of talking head videos, including the seamless addition, removal, and retiming of visually spoken content. Building on a general-purpose video diffusion model, EditYourself augments its V2V capabilities with audio conditioning and region-aware, edit-focused training extensions. This enables precise lip synchronization and temporally coherent restructuring of existing performances via spatiotemporal inpainting, including the synthesis of realistic human motion in newly added segments, while maintaining visual fidelity and identity consistency over long durations. This work represents a foundational step toward generative video models as practical tools for professional video post-production. △ Less

Submitted 29 January, 2026; originally announced January 2026.

Comments: Project page: https://edit-yourself.github.io/

Leveraging Sentence-oriented Augmentation and Transformer-Based Architecture for Vietnamese-Bahnaric Translation

Authors: Tan Sang Nguyen, Quoc Nguyen Pham, Tho Quan

Abstract: The Bahnar people, an ethnic minority in Vietnam with a rich ancestral heritage, possess a language of immense cultural and historical significance. The government places a strong emphasis on preserving and promoting the Bahnaric language by making it accessible online and encouraging communication across generations. Recent advancements in artificial intelligence, such as Neural Machine Translati… ▽ More The Bahnar people, an ethnic minority in Vietnam with a rich ancestral heritage, possess a language of immense cultural and historical significance. The government places a strong emphasis on preserving and promoting the Bahnaric language by making it accessible online and encouraging communication across generations. Recent advancements in artificial intelligence, such as Neural Machine Translation (NMT), have brought about a transformation in translation by improving accuracy and fluency. This, in turn, contributes to the revival of the language through educational efforts, communication, and documentation. Specifically, NMT is pivotal in enhancing accessibility for Bahnaric speakers, making information and content more readily available. Nevertheless, the translation of Vietnamese into Bahnaric faces practical challenges due to resource constraints, especially given the limited resources available for the Bahnaric language. To address this, we employ state-of-the-art techniques in NMT along with two augmentation strategies for domain-specific Vietnamese-Bahnaric translation task. Importantly, both approaches are flexible and can be used with various neural machine translation models. Additionally, they do not require complex data preprocessing steps, the training of additional systems, or the acquisition of extra data beyond the existing training parallel corpora. △ Less

Submitted 26 January, 2026; originally announced January 2026.

Low-Back Pain Physical Rehabilitation by Movement Analysis in Clinical Trial

Authors: Sao Mai Nguyen

Abstract: To allow the development and assessment of physical rehabilitation by an intelligent tutoring system, we propose a medical dataset of clinical patients carrying out low back-pain rehabilitation exercises and benchmark on state of the art human movement analysis algorithms. This dataset is valuable because it includes rehabilitation motions in a clinical setting with patients in their rehabilitatio… ▽ More To allow the development and assessment of physical rehabilitation by an intelligent tutoring system, we propose a medical dataset of clinical patients carrying out low back-pain rehabilitation exercises and benchmark on state of the art human movement analysis algorithms. This dataset is valuable because it includes rehabilitation motions in a clinical setting with patients in their rehabilitation program. This paper introduces the Keraal dataset, a clinically collected dataset to enable intelligent tutoring systems (ITS) for rehabilitation. It addresses four challenges in exercise monitoring: motion assessment, error recognition, spatial localization, temporal localization △ Less

Submitted 5 January, 2026; originally announced January 2026.

Comments: ICMST, Tokyo University of Science; Taiwanese Society of Movement Science and Technology; Research institute for Science and Technology, Nov 2025, Tokyo, Japan

Neural Networks on Symmetric Spaces of Noncompact Type

Authors: Xuan Son Nguyen, Shuo Yang, Aymeric Histace

Abstract: Recent works have demonstrated promising performances of neural networks on hyperbolic spaces and symmetric positive definite (SPD) manifolds. These spaces belong to a family of Riemannian manifolds referred to as symmetric spaces of noncompact type. In this paper, we propose a novel approach for developing neural networks on such spaces. Our approach relies on a unified formulation of the distanc… ▽ More Recent works have demonstrated promising performances of neural networks on hyperbolic spaces and symmetric positive definite (SPD) manifolds. These spaces belong to a family of Riemannian manifolds referred to as symmetric spaces of noncompact type. In this paper, we propose a novel approach for developing neural networks on such spaces. Our approach relies on a unified formulation of the distance from a point to a hyperplane on the considered spaces. We show that some existing formulations of the point-to-hyperplane distance can be recovered by our approach under specific settings. Furthermore, we derive a closed-form expression for the point-to-hyperplane distance in higher-rank symmetric spaces of noncompact type equipped with G-invariant Riemannian metrics. The derived distance then serves as a tool to design fully-connected (FC) layers and an attention mechanism for neural networks on the considered spaces. Our approach is validated on challenging benchmarks for image classification, electroencephalogram (EEG) signal classification, image generation, and natural language inference. △ Less

Submitted 3 January, 2026; originally announced January 2026.

MetaFormer-driven Encoding Network for Robust Medical Semantic Segmentation

Authors: Le-Anh Tran, Chung Nguyen Tran, Nhan Cach Dang, Anh Le Van Quoc, Jordi Carrabina, David Castells-Rufas, Minh Son Nguyen

Abstract: Semantic segmentation is crucial for medical image analysis, enabling precise disease diagnosis and treatment planning. However, many advanced models employ complex architectures, limiting their use in resource-constrained clinical settings. This paper proposes MFEnNet, an efficient medical image segmentation framework that incorporates MetaFormer in the encoding phase of the U-Net backbone. MetaF… ▽ More Semantic segmentation is crucial for medical image analysis, enabling precise disease diagnosis and treatment planning. However, many advanced models employ complex architectures, limiting their use in resource-constrained clinical settings. This paper proposes MFEnNet, an efficient medical image segmentation framework that incorporates MetaFormer in the encoding phase of the U-Net backbone. MetaFormer, an architectural abstraction of vision transformers, provides a versatile alternative to convolutional neural networks by transforming tokenized image patches into sequences for global context modeling. To mitigate the substantial computational cost associated with self-attention, the proposed framework replaces conventional transformer modules with pooling transformer blocks, thereby achieving effective global feature aggregation at reduced complexity. In addition, Swish activation is used to achieve smoother gradients and faster convergence, while spatial pyramid pooling is incorporated at the bottleneck to improve multi-scale feature extraction. Comprehensive experiments on different medical segmentation benchmarks demonstrate that the proposed MFEnNet approach attains competitive accuracy while significantly lowering computational cost compared to state-of-the-art models. The source code for this work is available at https://github.com/tranleanh/mfennet. △ Less

Submitted 1 January, 2026; originally announced January 2026.

Comments: 10 pages, 5 figures, MCT4SD 2025

Schrodinger AI: A Unified Spectral-Dynamical Framework for Classification, Reasoning, and Operator-Based Generalization

Authors: Truong Son Nguyen

Abstract: We introduce \textbf{Schrödinger AI}, a unified machine learning framework inspired by quantum mechanics. The system is defined by three tightly coupled components: (1) a {time-independent wave-energy solver} that treats perception and classification as spectral decomposition under a learned Hamiltonian; (2) a {time-dependent dynamical solver} governing the evolution of semantic wavefunctions over… ▽ More We introduce \textbf{Schrödinger AI}, a unified machine learning framework inspired by quantum mechanics. The system is defined by three tightly coupled components: (1) a {time-independent wave-energy solver} that treats perception and classification as spectral decomposition under a learned Hamiltonian; (2) a {time-dependent dynamical solver} governing the evolution of semantic wavefunctions over time, enabling context-aware decision revision, re-routing, and reasoning under environmental changes; and (3) a {low-rank operator calculus} that learns symbolic transformations such as modular arithmetic through learned quantum-like transition operators. Together, these components form a coherent physics-driven alternative to conventional cross-entropy training and transformer attention, providing robust generalization, interpretable semantics, and emergent topology. Empirically, Schrödinger AI demonstrates: (a) emergent semantic manifolds that reflect human-conceived class relations without explicit supervision; (b) dynamic reasoning that adapts to changing environments, including maze navigation with real-time potential-field perturbations; and (c) exact operator generalization on modular arithmetic tasks, where the system learns group actions and composes them across sequences far beyond training length. These results suggest a new foundational direction for machine learning, where learning is cast as discovering and navigating an underlying semantic energy landscape. △ Less

Submitted 27 December, 2025; originally announced December 2025.

BRIDGE: Budget-aware Reasoning via Intermediate Distillation with Guided Examples

Authors: Xuan-An Le, Minh-Nam Tran, Son Nguyen

Abstract: Distilling knowledge from large proprietary models (e.g., GPT-4) to tiny deployable models (less than 1B parameters) faces a critical capacity-budget trap: the 1000x capacity gap between teachers and students prevents effective direct transfer, while API costs prohibit extensive data collection. We introduce BRIDGE (Budget-Aware Reasoning via Intermediate Distillation), a two-phase framework that… ▽ More Distilling knowledge from large proprietary models (e.g., GPT-4) to tiny deployable models (less than 1B parameters) faces a critical capacity-budget trap: the 1000x capacity gap between teachers and students prevents effective direct transfer, while API costs prohibit extensive data collection. We introduce BRIDGE (Budget-Aware Reasoning via Intermediate Distillation), a two-phase framework that resolves these constraints through strategic intermediation and budget asymmetry. In Phase 1, a mid-sized Teacher Assistant (TA; e.g., about 7B) learns from the black-box teacher on a strictly limited subset of data (e.g., 3-5%), selected via a zero-API-cost pipeline that balances entropic difficulty and semantic diversity using only local TA inference. In Phase 2, we exploit this asymmetry-teacher queries are expensive, whereas TA inference is free to amplify supervision: the refined TA generates synthetic rationales for the full dataset to train the tiny student. Crucially, we apply an instruction-tuning curriculum to establish behavioral alignment in the tiny student before transferring reasoning. Our theoretical analysis shows that BRIDGE yields tighter generalization bounds than direct distillation when data is abundant. Experiments across medical, legal, and financial benchmarks demonstrate consistent improvements: BRIDGE delivers student performance gains of 28-41%, closing the capability gap with proprietary teachers by 12-16% while using 10x fewer teacher queries. Notably, BRIDGE defies the conventional cost-performance frontier, surpassing direct distillation baselines that use 100% of the budget while consuming only 5% of the resources. △ Less

Submitted 23 December, 2025; originally announced December 2025.

Robust Scene Coordinate Regression via Geometrically-Consistent Global Descriptors

Authors: Son Tung Nguyen, Alejandro Fontan, Michael Milford, Tobias Fischer

Abstract: Recent learning-based visual localization methods use global descriptors to disambiguate visually similar places, but existing approaches often derive these descriptors from geometric cues alone (e.g., covisibility graphs), limiting their discriminative power and reducing robustness in the presence of noisy geometric constraints. We propose an aggregator module that learns global descriptors consi… ▽ More Recent learning-based visual localization methods use global descriptors to disambiguate visually similar places, but existing approaches often derive these descriptors from geometric cues alone (e.g., covisibility graphs), limiting their discriminative power and reducing robustness in the presence of noisy geometric constraints. We propose an aggregator module that learns global descriptors consistent with both geometrical structure and visual similarity, ensuring that images are close in descriptor space only when they are visually similar and spatially connected. This corrects erroneous associations caused by unreliable overlap scores. Using a batch-mining strategy based solely on the overlap scores and a modified contrastive loss, our method trains without manual place labels and generalizes across diverse environments. Experiments on challenging benchmarks show substantial localization gains in large-scale environments while preserving computational and memory efficiency. Code is available at https://github.com/sontung/robust_scr. △ Less

Submitted 8 January, 2026; v1 submitted 18 December, 2025; originally announced December 2025.

Comments: Accepted at IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2026

CAHC:A General Conflict-Aware Heuristic Caching Framework for Multi-Agent Path Finding

Authors: HT To, S Nguyen, NH Pham

Abstract: Multi-Agent Path Finding (MAPF) algorithms, including those for car-like robots and grid-based scenarios, face significant computational challenges due to expensive heuristic calculations. Traditional heuristic caching assumes that the heuristic function depends only on the state, which is incorrect in constraint-based search algorithms (e.g., CBS, MAPF-LNS, MAP2) where constraints from conflict r… ▽ More Multi-Agent Path Finding (MAPF) algorithms, including those for car-like robots and grid-based scenarios, face significant computational challenges due to expensive heuristic calculations. Traditional heuristic caching assumes that the heuristic function depends only on the state, which is incorrect in constraint-based search algorithms (e.g., CBS, MAPF-LNS, MAP2) where constraints from conflict resolution make the search space context-dependent. We propose \textbf{CAHC} (Conflict-Aware Heuristic Caching), a general framework that caches heuristic values based on both state and relevant constraint context, addressing this fundamental limitation. We demonstrate CAHC through a case study on CL-CBS for car-like robots, where we combine conflict-aware caching with an adaptive hybrid heuristic in \textbf{CAR-CHASE} (Car-Like Robot Conflict-Aware Heuristic Adaptive Search Enhancement). Our key innovations are (1) a compact \emph{conflict fingerprint} that efficiently encodes which constraints affect a state's heuristic, (2) a domain-adaptable relevance filter using spatial, temporal, and geometric criteria, and (3) a modular architecture that enables systematic application to diverse MAPF algorithms. Experimental evaluation on 480 CL-CBS benchmark instances demonstrates a geometric mean speedup of 2.46$\times$ while maintaining solution optimality. The optimizations improve success rate from 77.9\% to 84.8\% (+6.9 percentage points), reduce total runtime by 70.1\%, and enable solving 33 additional instances. The framework's general architecture makes it applicable as a reliable optimization technique for MAP2, MAPF-LNS, and other constraint-based MAPF algorithms. △ Less

Submitted 17 January, 2026; v1 submitted 13 December, 2025; originally announced December 2025.

Siegel Neural Networks

Authors: Xuan Son Nguyen, Aymeric Histace, Nistor Grozavu

Abstract: Riemannian symmetric spaces (RSS) such as hyperbolic spaces and symmetric positive definite (SPD) manifolds have become popular spaces for representation learning. In this paper, we propose a novel approach for building discriminative neural networks on Siegel spaces, a family of RSS that is largely unexplored in machine learning tasks. For classification applications, one focus of recent works is… ▽ More Riemannian symmetric spaces (RSS) such as hyperbolic spaces and symmetric positive definite (SPD) manifolds have become popular spaces for representation learning. In this paper, we propose a novel approach for building discriminative neural networks on Siegel spaces, a family of RSS that is largely unexplored in machine learning tasks. For classification applications, one focus of recent works is the construction of multiclass logistic regression (MLR) and fully-connected (FC) layers for hyperbolic and SPD neural networks. Here we show how to build such layers for Siegel neural networks. Our approach relies on the quotient structure of those spaces and the notation of vector-valued distance on RSS. We demonstrate the relevance of our approach on two applications, i.e., radar clutter classification and node classification. Our results successfully demonstrate state-of-the-art performance across all datasets. △ Less

Submitted 12 November, 2025; originally announced November 2025.

Can LLMs Translate Human Instructions into a Reinforcement Learning Agent's Internal Emergent Symbolic Representation?

Authors: Ziqi Ma, Sao Mai Nguyen, Philippe Xu

Abstract: Emergent symbolic representations are critical for enabling developmental learning agents to plan and generalize across tasks. In this work, we investigate whether large language models (LLMs) can translate human natural language instructions into the internal symbolic representations that emerge during hierarchical reinforcement learning. We apply a structured evaluation framework to measure the… ▽ More Emergent symbolic representations are critical for enabling developmental learning agents to plan and generalize across tasks. In this work, we investigate whether large language models (LLMs) can translate human natural language instructions into the internal symbolic representations that emerge during hierarchical reinforcement learning. We apply a structured evaluation framework to measure the translation performance of commonly seen LLMs -- GPT, Claude, Deepseek and Grok -- across different internal symbolic partitions generated by a hierarchical reinforcement learning algorithm in the Ant Maze and Ant Fall environments. Our findings reveal that although LLMs demonstrate some ability to translate natural language into a symbolic representation of the environment dynamics, their performance is highly sensitive to partition granularity and task complexity. The results expose limitations in current LLMs capacity for representation alignment, highlighting the need for further research on robust alignment between language and internal agent representations. △ Less

Submitted 28 October, 2025; originally announced October 2025.

Interpret Policies in Deep Reinforcement Learning using SILVER with RL-Guided Labeling: A Model-level Approach to High-dimensional and Multi-action Environments

Authors: Yiyu Qian, Su Nguyen, Chao Chen, Qinyue Zhou, Liyuan Zhao

Abstract: Deep reinforcement learning (RL) achieves remarkable performance but lacks interpretability, limiting trust in policy behavior. The existing SILVER framework (Li, Siddique, and Cao 2025) explains RL policy via Shapley-based regression but remains restricted to low-dimensional, binary-action domains. We propose SILVER with RL-guided labeling, an enhanced variant that extends SILVER to multi-action… ▽ More Deep reinforcement learning (RL) achieves remarkable performance but lacks interpretability, limiting trust in policy behavior. The existing SILVER framework (Li, Siddique, and Cao 2025) explains RL policy via Shapley-based regression but remains restricted to low-dimensional, binary-action domains. We propose SILVER with RL-guided labeling, an enhanced variant that extends SILVER to multi-action and high-dimensional environments by incorporating the RL policy's own action outputs into the boundary points identification. Our method first extracts compact feature representations from image observations, performs SHAP-based feature attribution, and then employs RL-guided labeling to generate behaviorally consistent boundary datasets. Surrogate models, such as decision trees and regression-based functions, are subsequently trained to interpret RL policy's decision structure. We evaluate the proposed framework on two Atari environments using three deep RL algorithms and conduct human-subject study to assess the clarity and trustworthiness of the derived interpretable policy. Results show that our approach maintains competitive task performance while substantially improving transparency and human understanding of agent behavior. This work advances explainable RL by transforming SILVER into a scalable and behavior-aware framework for interpreting deep RL agents in high-dimensional, multi-action settings. △ Less

Submitted 18 July, 2026; v1 submitted 22 October, 2025; originally announced October 2025.

Comments: Some co-authors do not agree with uploading this paper to arXiv

Model-Agnostic Correctness Assessment for LLM-Generated Code via Dynamic Internal Representation Selection

Authors: Thanh Trong Vu, Tuan-Dung Bui, Thu-Trang Nguyen, Son Nguyen, Hieu Dinh Vo

Abstract: Large Language Models (LLMs) have demonstrated impressive capabilities in code generation and are increasingly integrated into the software development process. However, ensuring the correctness of LLM-generated code remains a critical concern. Prior work has shown that the internal representations of LLMs encode meaningful signals for assessing code correctness. Nevertheless, the existing methods… ▽ More Large Language Models (LLMs) have demonstrated impressive capabilities in code generation and are increasingly integrated into the software development process. However, ensuring the correctness of LLM-generated code remains a critical concern. Prior work has shown that the internal representations of LLMs encode meaningful signals for assessing code correctness. Nevertheless, the existing methods rely on representations from pre-selected/fixed layers and token positions, which could limit its generalizability across diverse model architectures and tasks. In this work, we introduce AUTOPROBE, a novel model-agnostic approach that dynamically selects the most informative internal representations for code correctness assessment. AUTOPROBE employs an attention-based mechanism to learn importance scores for hidden states, enabling it to focus on the most relevant features. These weighted representations are then aggregated and passed to a probing classifier to predict code correctness across multiple dimensions, including compilability, functionality, and security. To evaluate the performance of AUTOPROBE, we conduct extensive experiments across multiple benchmarks and code LLMs. Our experimental results show that AUTOPROBE consistently outperforms the baselines. For security assessment, AUTOPROBE surpasses the state-of-the-art white-box approach by 18%. For compilability and functionality assessment, AUTOPROBE demonstrates its highest robustness to code complexity, with the performance higher than the other approaches by up to 19% and 111%, respectively. These findings highlight that dynamically selecting important internal signals enables AUTOPROBE to serve as a robust and generalizable solution for assessing the correctness of code generated by various LLMs. △ Less

Submitted 3 October, 2025; originally announced October 2025.

Approximating Electoral Control Problems

Authors: Huy Vu Bui, Michael C. Chavrimootoo, Kien T. Le, Son M. Nguyen

Abstract: Much research in electoral control---one of the most studied form of electoral attacks, in which an entity running an election alters the structure of that election to yield a preferred outcome---has focused on giving decision complexity results, e.g., membership in P, NP-completeness, or fixed-parameter tractability. Approximability on the other hand has received little attention in electoral con… ▽ More Much research in electoral control---one of the most studied form of electoral attacks, in which an entity running an election alters the structure of that election to yield a preferred outcome---has focused on giving decision complexity results, e.g., membership in P, NP-completeness, or fixed-parameter tractability. Approximability on the other hand has received little attention in electoral control, despite its prevalence in the study of other forms of electoral attacks, such as manipulation and bribery. Early work established preliminary results about popular voting rules such as plurality, approval, and Condorcet. In this paper, we completely determine for each of the "standard" control problems under plurality, approval, and Condorcet, whether they are approximable, and we prove our results in both the weighted and unweighted voter settings. △ Less

Submitted 20 August, 2026; v1 submitted 23 September, 2025; originally announced September 2025.

Comments: Accepted at ADT 2026

KRAST: Knowledge-Augmented Robotic Action Recognition with Structured Text for Vision-Language Models

Authors: Son Hai Nguyen, Diwei Wang, Jinhyeok Jang, Hyewon Seo

Abstract: Accurate vision-based action recognition is crucial for developing autonomous robots that can operate safely and reliably in complex, real-world environments. In this work, we advance video-based recognition of indoor daily actions for robotic perception by leveraging vision-language models (VLMs) enriched with domain-specific knowledge. We adapt a prompt-learning framework in which class-level te… ▽ More Accurate vision-based action recognition is crucial for developing autonomous robots that can operate safely and reliably in complex, real-world environments. In this work, we advance video-based recognition of indoor daily actions for robotic perception by leveraging vision-language models (VLMs) enriched with domain-specific knowledge. We adapt a prompt-learning framework in which class-level textual descriptions of each action are embedded as learnable prompts into a frozen pre-trained VLM backbone. Several strategies for structuring and encoding these textual descriptions are designed and evaluated. Experiments on the ETRI-Activity3D dataset demonstrate that our method, using only RGB video inputs at test time, achieves over 95\% accuracy and outperforms state-of-the-art approaches. These results highlight the effectiveness of knowledge-augmented prompts in enabling robust action recognition with minimal supervision. △ Less

Submitted 19 September, 2025; originally announced September 2025.

Feature Impact Analysis on Top Long-Jump Performances with Quantile Random Forest and Explainable AI Techniques

Authors: Qi Gan, Stephan Clémençon, Mounîm A. El-Yacoubi, Sao Mai Nguyen, Eric Fenaux, Ons Jelassi

Abstract: Biomechanical features have become important indicators for evaluating athletes' techniques. Traditionally, experts propose significant features and evaluate them using physics equations. However, the complexity of the human body and its movements makes it challenging to explicitly analyze the relationships between some features and athletes' final performance. With advancements in modern machine… ▽ More Biomechanical features have become important indicators for evaluating athletes' techniques. Traditionally, experts propose significant features and evaluate them using physics equations. However, the complexity of the human body and its movements makes it challenging to explicitly analyze the relationships between some features and athletes' final performance. With advancements in modern machine learning and statistics, data analytics methods have gained increasing importance in sports analytics. In this study, we leverage machine learning models to analyze expert-proposed biomechanical features from the finals of long jump competitions in the World Championships. The objectives of the analysis include identifying the most important features contributing to top-performing jumps and exploring the combined effects of these key features. Using quantile regression, we model the relationship between the biomechanical feature set and the target variable (effective distance), with a particular focus on elite-level jumps. To interpret the model, we apply SHapley Additive exPlanations (SHAP) alongside Partial Dependence Plots (PDPs) and Individual Conditional Expectation (ICE) plots. The findings reveal that, beyond the well-documented velocity-related features, specific technical aspects also play a pivotal role. For male athletes, the angle of the knee of the supporting leg before take-off is identified as a key factor for achieving top 10% performance in our dataset, with angles greater than 169°contributing significantly to jump performance. In contrast, for female athletes, the landing pose and approach step technique emerge as the most critical features influencing top 10% performances, alongside velocity. This study establishes a framework for analyzing the impact of various features on athletic performance, with a particular emphasis on top-performing events. △ Less

Submitted 13 August, 2025; originally announced August 2025.

Comments: 15 pages, 6 figures

CABENCH: Benchmarking Composable AI for Solving Complex Tasks through Composing Ready-to-Use Models

Authors: Tung-Thuy Pham, Duy-Quan Luong, Minh-Quan Duong, Trung-Hieu Nguyen, Thu-Trang Nguyen, Son Nguyen, Hieu Dinh Vo

Abstract: Composable AI offers a scalable and effective paradigm for tackling complex AI tasks by decomposing them into sub-tasks and solving each sub-task using ready-to-use well-trained models. However, systematically evaluating methods under this setting remains largely unexplored. In this paper, we introduce CABENCH, the first public benchmark comprising 70 realistic composable AI tasks, along with a cu… ▽ More Composable AI offers a scalable and effective paradigm for tackling complex AI tasks by decomposing them into sub-tasks and solving each sub-task using ready-to-use well-trained models. However, systematically evaluating methods under this setting remains largely unexplored. In this paper, we introduce CABENCH, the first public benchmark comprising 70 realistic composable AI tasks, along with a curated pool of 700 models across multiple modalities and domains. We also propose an evaluation framework to enable end-to-end assessment of composable AI solutions. To establish initial baselines, we provide human-designed reference solutions and compare their performance with two LLM-based approaches. Our results illustrate the promise of composable AI in addressing complex real-world problems while highlighting the need for methods that can fully unlock its potential by automatically generating effective execution pipelines. △ Less

Submitted 4 August, 2025; originally announced August 2025.

Bridging LLMs and Symbolic Reasoning in Educational QA Systems: Insights from the XAI Challenge at IJCNN 2025

Authors: Long S. T. Nguyen, Khang H. N. Vo, Thu H. A. Nguyen, Tuan C. Bui, Duc Q. Nguyen, Thanh-Tung Tran, Anh D. Nguyen, Minh L. Nguyen, Fabien Baldacci, Thang H. Bui, Emanuel Di Nardo, Angelo Ciaramella, Son H. Le, Ihsan Ullah, Lorenzo Di Rocco, Tho T. Quan

Abstract: The growing integration of Artificial Intelligence (AI) into education has intensified the need for transparency and interpretability. While hackathons have long served as agile environments for rapid AI prototyping, few have directly addressed eXplainable AI (XAI) in real-world educational contexts. This paper presents a comprehensive analysis of the XAI Challenge 2025, a hackathon-style competit… ▽ More The growing integration of Artificial Intelligence (AI) into education has intensified the need for transparency and interpretability. While hackathons have long served as agile environments for rapid AI prototyping, few have directly addressed eXplainable AI (XAI) in real-world educational contexts. This paper presents a comprehensive analysis of the XAI Challenge 2025, a hackathon-style competition jointly organized by Ho Chi Minh City University of Technology (HCMUT) and the International Workshop on Trustworthiness and Reliability in Neurosymbolic AI (TRNS-AI), held as part of the International Joint Conference on Neural Networks (IJCNN 2025). The challenge tasked participants with building Question-Answering (QA) systems capable of answering student queries about university policies while generating clear, logic-based natural language explanations. To promote transparency and trustworthiness, solutions were required to use lightweight Large Language Models (LLMs) or hybrid LLM-symbolic systems. A high-quality dataset was provided, constructed via logic-based templates with Z3 validation and refined through expert student review to ensure alignment with real-world academic scenarios. We describe the challenge's motivation, structure, dataset construction, and evaluation protocol. Situating the competition within the broader evolution of AI hackathons, we argue that it represents a novel effort to bridge LLMs and symbolic reasoning in service of explainability. Our findings offer actionable insights for future XAI-centered educational systems and competitive research initiatives. △ Less

Submitted 2 August, 2025; originally announced August 2025.

Comments: The XAI Challenge @ TRNS-AI Workshop, IJCNN 2025: Explainable AI for Educational Question Answering. Website: https://sites.google.com/view/trns-ai/challenge/

A Benchmark Dataset and Evaluation Framework for Vietnamese Large Language Models in Customer Support

Authors: Long S. T. Nguyen, Truong P. Hua, Thanh M. Nguyen, Toan Q. Pham, Nam K. Ngo, An X. Nguyen, Nghi D. M. Pham, Nghia H. Nguyen, Tho T. Quan

Abstract: With the rapid growth of Artificial Intelligence, Large Language Models (LLMs) have become essential for Question Answering (QA) systems, improving efficiency and reducing human workload in customer service. The emergence of Vietnamese LLMs (ViLLMs) highlights lightweight open-source models as a practical choice for their accuracy, efficiency, and privacy benefits. However, domain-specific evaluat… ▽ More With the rapid growth of Artificial Intelligence, Large Language Models (LLMs) have become essential for Question Answering (QA) systems, improving efficiency and reducing human workload in customer service. The emergence of Vietnamese LLMs (ViLLMs) highlights lightweight open-source models as a practical choice for their accuracy, efficiency, and privacy benefits. However, domain-specific evaluations remain limited, and the absence of benchmark datasets reflecting real customer interactions makes it difficult for enterprises to select suitable models for support applications. To address this gap, we introduce the Customer Support Conversations Dataset (CSConDa), a curated benchmark of over 9,000 QA pairs drawn from real interactions with human advisors at a large Vietnamese software company. Covering diverse topics such as pricing, product availability, and technical troubleshooting, CSConDa provides a representative basis for evaluating ViLLMs in practical scenarios. We further present a comprehensive evaluation framework, benchmarking 11 lightweight open-source ViLLMs on CSConDa with both automatic metrics and syntactic analysis to reveal model strengths, weaknesses, and linguistic patterns. This study offers insights into model behavior, explains performance differences, and identifies key areas for improvement, supporting the development of next-generation ViLLMs. By establishing a robust benchmark and systematic evaluation, our work enables informed model selection for customer service QA and advances research on Vietnamese LLMs. The dataset is publicly available at https://huggingface.co/datasets/ura-hcmut/Vietnamese-Customer-Support-QA. △ Less

Submitted 30 July, 2025; originally announced July 2025.

Comments: Under review at ICCCI 2025

Speaking in Words, Thinking in Logic: A Dual-Process Framework in QA Systems

Authors: Tuan Bui, Trong Le, Phat Thai, Sang Nguyen, Minh Hua, Ngan Pham, Thang Bui, Tho Quan

Abstract: Recent advances in large language models (LLMs) have significantly enhanced question-answering (QA) capabilities, particularly in open-domain contexts. However, in closed-domain scenarios such as education, healthcare, and law, users demand not only accurate answers but also transparent reasoning and explainable decision-making processes. While neural-symbolic (NeSy) frameworks have emerged as a p… ▽ More Recent advances in large language models (LLMs) have significantly enhanced question-answering (QA) capabilities, particularly in open-domain contexts. However, in closed-domain scenarios such as education, healthcare, and law, users demand not only accurate answers but also transparent reasoning and explainable decision-making processes. While neural-symbolic (NeSy) frameworks have emerged as a promising solution, leveraging LLMs for natural language understanding and symbolic systems for formal reasoning, existing approaches often rely on large-scale models and exhibit inefficiencies in translating natural language into formal logic representations. To address these limitations, we introduce Text-JEPA (Text-based Joint-Embedding Predictive Architecture), a lightweight yet effective framework for converting natural language into first-order logic (NL2FOL). Drawing inspiration from dual-system cognitive theory, Text-JEPA emulates System 1 by efficiently generating logic representations, while the Z3 solver operates as System 2, enabling robust logical inference. To rigorously evaluate the NL2FOL-to-reasoning pipeline, we propose a comprehensive evaluation framework comprising three custom metrics: conversion score, reasoning score, and Spearman rho score, which collectively capture the quality of logical translation and its downstream impact on reasoning accuracy. Empirical results on domain-specific datasets demonstrate that Text-JEPA achieves competitive performance with significantly lower computational overhead compared to larger LLM-based systems. Our findings highlight the potential of structured, interpretable reasoning frameworks for building efficient and explainable QA systems in specialized domains. △ Less

Submitted 27 July, 2025; originally announced July 2025.

Comments: 8 pages, 3 figures. Accepted at the International Joint Conference on Neural Networks (IJCNN) 2025, Workshop on Trustworthiness and Reliability in Neuro-Symbolic AI. https://2025.ijcnn.org

Low-Light Enhancement via Encoder-Decoder Network with Illumination Guidance

Authors: Le-Anh Tran, Chung Nguyen Tran, Ngoc-Luu Nguyen, Nhan Cach Dang, Jordi Carrabina, David Castells-Rufas, Minh Son Nguyen

Abstract: This paper introduces a novel deep learning framework for low-light image enhancement, named the Encoder-Decoder Network with Illumination Guidance (EDNIG). Building upon the U-Net architecture, EDNIG integrates an illumination map, derived from Bright Channel Prior (BCP), as a guidance input. This illumination guidance helps the network focus on underexposed regions, effectively steering the enha… ▽ More This paper introduces a novel deep learning framework for low-light image enhancement, named the Encoder-Decoder Network with Illumination Guidance (EDNIG). Building upon the U-Net architecture, EDNIG integrates an illumination map, derived from Bright Channel Prior (BCP), as a guidance input. This illumination guidance helps the network focus on underexposed regions, effectively steering the enhancement process. To further improve the model's representational power, a Spatial Pyramid Pooling (SPP) module is incorporated to extract multi-scale contextual features, enabling better handling of diverse lighting conditions. Additionally, the Swish activation function is employed to ensure smoother gradient propagation during training. EDNIG is optimized within a Generative Adversarial Network (GAN) framework using a composite loss function that combines adversarial loss, pixel-wise mean squared error (MSE), and perceptual loss. Experimental results show that EDNIG achieves competitive performance compared to state-of-the-art methods in quantitative metrics and visual quality, while maintaining lower model complexity, demonstrating its suitability for real-world applications. The source code for this work is available at https://github.com/tranleanh/ednig. △ Less

Submitted 4 July, 2025; originally announced July 2025.

Comments: 6 pages, 3 figures, ICCCE 2025