arXiv subjects

Tien Nguyen

Publications and source records attributed to Tien Nguyen.

11 recordsLinked to original sources

arXiv2026

LEXIC: Lightweight Eye-tracking eXtension via Injected Complexity

On the recent EyeBench benchmark, predicting reading comprehension from eye movements exposes a stark gap: text-aware models using pretrained language models reach 56--63% AUROC, while gaze-only models operate at chance. We ask how far a gaze-only model can be pushed by lightweight, language-model-free conditioning. Building on the EyeBench AhnCNN baseline, LEXIC-Base, we propose two mechanisms to inject three precomputed word-level difficulty signals, GPT-2 surprisal, word frequency, and word length, into the per-fixation input: direct concatenation, LEXIC-Concat, and a residual mechanism, LEXIC-Res, where a small head predicts typical-reader gaze response and the encoder is conditioned on the deviation. On the OneStop reading comprehension task, with K=5 seed-ensemble training across ten folds, both mechanisms produce statistically consistent AUROC gains on Unseen Text, +1.8 to +2.2 percentage points, Wilcoxon p <= 0.065. LEXIC-Concat additionally lifts Unseen Reader by +2.9 percentage points, p = 0.010. We trace an architectural boundary in LEXIC-Res on Unseen Reader, +1.8 percentage points, p = 0.19, to the prediction head being calibrated to training readers, transferring imperfectly to out-of-distribution readers.

cs.CL↗

arXiv2026

Assessing Large Language Models for Stabilizing Numerical Expressions in Scientific Software

Scientific software relies on high-precision computation, yet finite floating-point representations introduce precision errors that propagate in safety-critical domains. Despite growing use of large language models (LLMs) in scientific applications, their reliability in handling floating-point numerical stability has not been systematically evaluated. This paper evaluates LLMs' reasoning through two tasks: (1) detecting instability in numerical expressions by generating error-inducing inputs (detection), and (2) rewriting expressions to improve numerical stability (stabilization). Building on popular numerical benchmarks, we assess 4 state-of-the-art LLMs on 2,037numerical structures, including nested conditionals, high-precision literals, and multi-variable arithmetic, across 469,000 tasks. Our results show that LLMs complement traditional approaches in detecting and stabilizing numerically unstable computations. Notably, LLMs outperform baseline methods precisely where the latter fail, stabilizing 61.2% of expressions the baseline fails to improve. More broadly, however, traditional baselines outperform LLMs: Herbie stabilizes 93.7% of the expressions compared to 67.2% by LLMs, and on expressions that both stabilize, Herbie achieves higher accuracy in 42.7% of cases. LLMs struggle with control flow and high-precision literals, consistently removing such structures rather than reasoning about their numerical implications, while performing substantially better on purely symbolic expressions. Even when LLMs preserve structure, their numerical reasoning falters, yielding semantically inequivalent expressions in over 46% of cases. These findings suggest LLMs are effective at stabilizing expressions that classical techniques cannot, yet struggle when high-precision magnitudes and control-flow semantics demand precise reasoning, since such concrete patterns are rarely seen during training.

cs.SE↗

arXiv2025

Are the Majority of Public Computational Notebooks Pathologically Non-Executable?

Computational notebooks are the de facto platforms for exploratory data science, offering an interactive programming environment where users can create, modify, and execute code cells in any sequence. However, this flexibility often introduces code quality issues, with prior studies showing that approximately 76% of public notebooks are non-executable, raising significant concerns about reusability. We argue that the traditional notion of executability - requiring a notebook to run fully and without error - is overly rigid, misclassifying many notebooks and overestimating their non-executability. This paper investigates pathological executability issues in public notebooks under varying notions and degrees of executability. Even partially improving executability can improve code comprehension and offer a pathway for dynamic analyses. With this insight, we first categorize notebooks into potentially restorable and pathological non-executable notebooks and then measure how removing misconfiguration and superficial execution issues in notebooks can improve their executability (i.e., additional cells executed without error). In a dataset of 42,546 popular public notebooks containing 34,659 non-executable notebooks, only 21.3% are truly pathologically non-executable. For restorable notebooks, LLM-based methods fully restore 5.4% of previously non-executable notebooks. Among the partially restored, the executability of notebooks improves by 42.7% and 28% by installing the correct modules and generating synthetic data. These findings challenge prior assumptions, suggesting that notebooks have higher executability than previously reported, many of which offer valuable partial execution, and that their executability should be evaluated within the interactive notebook paradigm rather than through traditional software executability standards.

cs.SE↗

arXiv2024

From Federated Learning to Quantum Federated Learning for Space-Air-Ground Integrated Networks

6G wireless networks are expected to provide seamless and data-based connections that cover space-air-ground and underwater networks. As a core partition of future 6G networks, Space-Air-Ground Integrated Networks (SAGIN) have been envisioned to provide countless real-time intelligent applications. To realize this, promoting AI techniques into SAGIN is an inevitable trend. Due to the distributed and heterogeneous architecture of SAGIN, federated learning (FL) and then quantum FL are emerging AI model training techniques for enabling future privacy-enhanced and computation-efficient SAGINs. In this work, we explore the vision of using FL/QFL in SAGINs. We present a few representative applications enabled by the integration of FL and QFL in SAGINs. A case study of QFL over UAV networks is also given, showing the merit of quantum-enabled training approach over the conventional FL benchmark. Research challenges along with standardization for QFL adoption in future SAGINs are also highlighted.

cs.LG↗

arXiv2024

Wireless Federated Learning over UAV-enabled Integrated Sensing and Communication

This paper studies a new latency optimization problem in unmanned aerial vehicles (UAVs)-enabled federated learning (FL) with integrated sensing and communication. In this setup, distributed UAVs participate in model training using sensed data and collaborate with a base station (BS) serving as FL aggregator to build a global model. The objective is to minimize the FL system latency over UAV networks by jointly optimizing UAVs' trajectory and resource allocation of both UAVs and the BS. The formulated optimization problem is troublesome to solve due to its non-convexity. Hence, we develop a simple yet efficient iterative algorithm to find a high-quality approximate solution, by leveraging block coordinate descent and successive convex approximation techniques. Simulation results demonstrate the effectiveness of our proposed joint optimization strategy under practical parameter settings, saving the system latency up to 68.54\% compared to benchmark schemes.

cs.IT↗

arXiv2024

ExGra-Med: Extended Context Graph Alignment for Medical Vision-Language Models

State-of-the-art medical multi-modal LLMs (med-MLLMs), such as LLaVA-Med and BioMedGPT, primarily depend on scaling model size and data volume, with training driven largely by autoregressive objectives. However, we reveal that this approach can lead to weak vision-language alignment, making these models overly dependent on costly instruction-following data. To address this, we introduce ExGra-Med, a novel multi-graph alignment framework that jointly aligns images, instruction responses, and extended captions in the latent space, advancing semantic grounding and cross-modal coherence. To scale to large LLMs (e.g., LLaMA-7B), we develop an efficient end-to-end training scheme using black-box gradient estimation, enabling fast and scalable optimization. Empirically, ExGra-Med matches LLaVA-Med's performance using just 10% of the pre-training data, achieving a 20.13% gain on VQA-RAD and approaching full-data performance. It also outperforms strong baselines like BioMedGPT and RadFM on visual chatbot and zero-shot classification tasks, demonstrating its promise for efficient, high-quality vision-language integration in medical AI.

cs.LG↗

arXiv2024

KAT: Dependency-aware Automated API Testing with Large Language Models

API testing has increasing demands for software companies. Prior API testing tools were aware of certain types of dependencies that needed to be concise between operations and parameters. However, their approaches, which are mostly done manually or using heuristic-based algorithms, have limitations due to the complexity of these dependencies. In this paper, we present KAT (Katalon API Testing), a novel AI-driven approach that leverages the large language model GPT in conjunction with advanced prompting techniques to autonomously generate test cases to validate RESTful APIs. Our comprehensive strategy encompasses various processes to construct an operation dependency graph from an OpenAPI specification and to generate test scripts, constraint validation scripts, test cases, and test data. Our evaluation of KAT using 12 real-world RESTful services shows that it can improve test coverage, detect more undocumented status codes, and reduce false positives in these services in comparison with a state-of-the-art automated test generation tool. These results indicate the effectiveness of using the large language model for generating test scripts and data for API testing.

cs.SE↗

arXiv2024

Natural Is The Best: Model-Agnostic Code Simplification for Pre-trained Large Language Models

Pre-trained Large Language Models (LLM) have achieved remarkable successes in several domains. However, code-oriented LLMs are heavy in computational complexity, and quadratically with the length of the input. Toward simplifying the input program of an LLM, the state-of-the-art approach has the strategies to filter the input code tokens based on the attention scores given by the LLM. The decision to simplify the input should not rely on the attention patterns of an LLM, as these patterns are influenced by both the model architecture and the pre-training dataset. Since the model and dataset are part of the solution domain, not the problem domain where the input belongs, the outcome may differ when the model is pre-trained on a different dataset. We propose SlimCode, a model-agnostic code simplification solution for LLMs that depends on the nature of input code tokens. As an empirical study on the LLMs including CodeBERT, CodeT5, and GPT-4 for two main tasks: code search and summarization, we reported that 1) the removal ratio of code has a linear-like relation with the saving ratio on training time, 2) the impact of categorized tokens on code simplification can vary significantly, 3) the impact of categorized tokens on code simplification is task-specific but model-agnostic, and 4) the above findings hold for the paradigm-prompt engineering and interactive in-context learning. The empirical results showed that SlimCode can improve the state-of-the-art technique by 9.46% and 5.15% in terms of MRR and BLEU score on code search and summarization. Moreover, SlimCode is 133 times faster than the state-of-the-art approach. Additionally, SlimCode can reduce the cost of invoking GPT-4 by up to 24% per API query, while still producing comparable results to those with the original code.

cs.SE↗

arXiv2021

Millions of 5-State n^3 Sequence Generators via Local Mappings

In this paper, we come back on the notion of local simulation allowing to transform a cellular automaton into a closely related one with different local encoding of information. In a previous paper, we applied it to the Firing Squad Synchronization Problem. In this paper, we show that the approach is not tied to this problem by applying it to the class of Real-Time Sequence Generation problems. We improve in particular on the generation of n 3 sequence by using local mappings to obtain millions of 5state solution, one of them using 58 transitions. It is based on the solution of Kamikawa and Umeo that uses 6 states and 74 transitions. Then, we explain in which sense even bigger classes of problems can be considered.

cs.DC↗

arXiv2019

User Session Identification Based on Strong Regularities in Inter-activity Time

Session identification is a common strategy used to develop metrics for web analytics and behavioral analyses of user-facing systems. Past work has argued that session identification strategies based on an inactivity threshold is inherently arbitrary or advocated that thresholds be set at about 30 minutes. In this work, we demonstrate a strong regularity in the temporal rhythms of user initiated events across several different domains of online activity (incl. video gaming, search, page views and volunteer contributions). We describe a methodology for identifying clusters of user activity and argue that regularity with which these activity clusters appear implies a good rule-of-thumb inactivity threshold of about 1 hour. We conclude with implications that these temporal rhythms may have for system design based on our observations and theories of goal-directed human activity.

cs.HC↗

arXiv2019

Recovering Variable Names for Minified Code with Usage Contexts

In modern Web technology, JavaScript (JS) code plays an important role. To avoid the exposure of original source code, the variable names in JS code deployed in the wild are often replaced by short, meaningless names, thus making the code extremely difficult to manually understand and analysis. This paper presents JSNeat, an information retrieval (IR)-based approach to recover the variable names in minified JS code. JSNeat follows a data-driven approach to recover names by searching for them in a large corpus of open-source JS code. We use three types of contexts to match a variable in given minified code against the corpus including the context of properties and roles of the variable, the context of that variable and relations with other variables under recovery, and the context of the task of the function to which the variable contributes. We performed several empirical experiments to evaluate JSNeat on the dataset of more than 322K JS files with 1M functions, and 3.5M variables with 176K unique variable names. We found that JSNeat achieves a high accuracy of 69.1%, which is the relative improvements of 66.1% and 43% over two state-of-the-art approaches JSNice and JSNaughty, respectively. The time to recover for a file or for a variable with JSNeat is twice as fast as with JSNice and 4x as fast as with JNaughty, respectively.

cs.SE↗