Selected work

Representative Papers

The Minimum Subgraph Complementation Problem

Dec 29, 2025

This paper studies the Minimum Subgraph Completion problem: given a graph $G$ and a target graph class $mathcal{C}$, find a smallest vertex subset $S$ such that the completion of the induced subgraph $G[S]$ belongs to $mathcal{C}$. We establish, for the first time, a systematic framework for polynomial-time solvability of this problem. Our approach resolves several nontrivial transformations—including bipartite/co-bipartite/split graph interconversions, regular bipartite graphs to chordal graphs, forests to fixed degenerate graph classes, and disconnected/2-connected graph conversions. Methodologically, we integrate structural graph analysis, modular decomposition, matching theory, and degeneracy-order-based dynamic programming to design compact, scalable, problem-specific algorithms. Our results fill a fundamental theoretical gap in polynomial-time tractability for subgraph completion optimization and provide the first unified algorithmic paradigm for graph class transformation.

0 citationsRead paper

Mini Autonomous Car Driving based on 3D Convolutional Neural Networks

Aug 28, 2025

To address weak model generalization and insufficient control stability in micro autonomous cars (MACs) operating within simulation environments, this paper proposes an end-to-end driving framework leveraging RGB-D data and a 3D convolutional neural network (3D CNN). Unlike conventional RNN-based approaches, the method directly learns driving policies from spatiotemporally continuous RGB-D image sequences, thereby enhancing modeling of dynamic track scenes through intrinsic spatiotemporal feature extraction. Experiments conducted on two simulated tracks with distinct complexity levels demonstrate that the proposed approach achieves high lap completion rates and consistent lap times. It significantly outperforms RNN baselines in task success rate and trajectory smoothness. These results validate the efficacy of 3D CNNs in improving control accuracy and environmental adaptability for resource-constrained, miniature autonomous driving systems.

0 citationsRead paper

AI-Driven Generation of Old English: A Framework for Low-Resource Languages

Jul 26, 2025

The scarcity of Old English corpora severely limits its applicability in modern NLP. To address this, we propose a dual-agent generative framework that decouples content generation from stylistic transfer: one agent employs LoRA-efficient fine-tuning of large language models to generate authentic Old English exemplars; the other enhances linguistic fidelity via back-translation. Our approach integrates parameter-efficient fine-tuning, back-translation-based data augmentation, and automated evaluation (BLEU, METEOR, chrF), validated by linguistics experts. Experiments demonstrate a substantial improvement in Old English translation quality—BLEU scores rise significantly from 26 to over 65—while achieving high grammatical accuracy and stylistic consistency. The method effectively expands high-quality, reproducible Old English resources, establishing a novel paradigm for computational research on historical languages.

0 citationsRead paper

Robusto-1 Dataset: Comparing Humans and VLMs on real out-of-distribution Autonomous Driving VQA from Peru

Mar 10, 2025

This study investigates the cognitive response alignment between foundational vision-language models (VLMs) and human drivers under out-of-distribution (OoD) autonomous driving scenarios. Method: We introduce the first cross-distribution visual question answering (VQA) benchmark grounded in real-world Peruvian traffic conditions—featuring non-synthetic, high-difficulty anomalous traffic videos—and pioneer the application of representational similarity analysis (RSA), a neuroscience-inspired technique, to quantify fine-grained human-AI cognitive alignment in multimodal VQA evaluation. Results: Human-VLM response consistency is strongly problem-type-dependent; systematic misalignment emerges in high-level cognitive tasks such as anomalous object recognition and driver intent inference, exposing fundamental limitations of current VLMs in realistic, long-tailed driving environments. Our core contributions are (1) a novel, interpretable human-AI cognitive comparison paradigm, and (2) the first OoD VQA benchmark explicitly targeting complex, infrastructure-constrained road conditions in developing countries.

0 citationsRead paper

Recent publications

Latest Papers

The Minimum Subgraph Complementation Problem

Dec 29, 2025

This paper studies the Minimum Subgraph Completion problem: given a graph $G$ and a target graph class $mathcal{C}$, find a smallest vertex subset $S$ such that the completion of the induced subgraph $G[S]$ belongs to $mathcal{C}$. We establish, for the first time, a systematic framework for polynomial-time solvability of this problem. Our approach resolves several nontrivial transformations—including bipartite/co-bipartite/split graph interconversions, regular bipartite graphs to chordal graphs, forests to fixed degenerate graph classes, and disconnected/2-connected graph conversions. Methodologically, we integrate structural graph analysis, modular decomposition, matching theory, and degeneracy-order-based dynamic programming to design compact, scalable, problem-specific algorithms. Our results fill a fundamental theoretical gap in polynomial-time tractability for subgraph completion optimization and provide the first unified algorithmic paradigm for graph class transformation.

0 citationsRead paper

Mini Autonomous Car Driving based on 3D Convolutional Neural Networks

Aug 28, 2025

To address weak model generalization and insufficient control stability in micro autonomous cars (MACs) operating within simulation environments, this paper proposes an end-to-end driving framework leveraging RGB-D data and a 3D convolutional neural network (3D CNN). Unlike conventional RNN-based approaches, the method directly learns driving policies from spatiotemporally continuous RGB-D image sequences, thereby enhancing modeling of dynamic track scenes through intrinsic spatiotemporal feature extraction. Experiments conducted on two simulated tracks with distinct complexity levels demonstrate that the proposed approach achieves high lap completion rates and consistent lap times. It significantly outperforms RNN baselines in task success rate and trajectory smoothness. These results validate the efficacy of 3D CNNs in improving control accuracy and environmental adaptability for resource-constrained, miniature autonomous driving systems.

0 citationsRead paper

AI-Driven Generation of Old English: A Framework for Low-Resource Languages

Jul 26, 2025

The scarcity of Old English corpora severely limits its applicability in modern NLP. To address this, we propose a dual-agent generative framework that decouples content generation from stylistic transfer: one agent employs LoRA-efficient fine-tuning of large language models to generate authentic Old English exemplars; the other enhances linguistic fidelity via back-translation. Our approach integrates parameter-efficient fine-tuning, back-translation-based data augmentation, and automated evaluation (BLEU, METEOR, chrF), validated by linguistics experts. Experiments demonstrate a substantial improvement in Old English translation quality—BLEU scores rise significantly from 26 to over 65—while achieving high grammatical accuracy and stylistic consistency. The method effectively expands high-quality, reproducible Old English resources, establishing a novel paradigm for computational research on historical languages.

0 citationsRead paper

Robusto-1 Dataset: Comparing Humans and VLMs on real out-of-distribution Autonomous Driving VQA from Peru

Mar 10, 2025

This study investigates the cognitive response alignment between foundational vision-language models (VLMs) and human drivers under out-of-distribution (OoD) autonomous driving scenarios. Method: We introduce the first cross-distribution visual question answering (VQA) benchmark grounded in real-world Peruvian traffic conditions—featuring non-synthetic, high-difficulty anomalous traffic videos—and pioneer the application of representational similarity analysis (RSA), a neuroscience-inspired technique, to quantify fine-grained human-AI cognitive alignment in multimodal VQA evaluation. Results: Human-VLM response consistency is strongly problem-type-dependent; systematic misalignment emerges in high-level cognitive tasks such as anomalous object recognition and driver intent inference, exposing fundamental limitations of current VLMs in realistic, long-tailed driving environments. Our core contributions are (1) a novel, interpretable human-AI cognitive comparison paradigm, and (2) the first OoD VQA benchmark explicitly targeting complex, infrastructure-constrained road conditions in developing countries.

0 citationsRead paper