Papers
Research papers from arXiv and related sources
Prosodic Boundary-Aware Streaming Generation for LLM-Based TTS with Streaming Text Input
Streaming TTS that receives streaming text is essential for interactive systems, yet this scheme faces two major challenges: unnatural prosody due to missing lookahead and long-form collapse due to...
Changsong Liu, Tianrui Wang, Ye Ni, Yizhou Peng, Eng Siong Chng
Abductive Reasoning with Syllogistic Forms in Large Language Models
Research in AI using Large-Language Models (LLMs) is rapidly evolving, and the comparison of their performance with human reasoning has become a key concern. Prior studies have indicated that LLMs ...
Hirohiko Abe, Risako Ando, Takanobu Morishita Kentaro Ozeki, Koji Mineshima, Mitsuhiro Okada
From Prompting to Preference Optimization: A Comparative Study of LLM-based Automated Essay Scoring
Large language models (LLMs) have recently reshaped Automated Essay Scoring (AES), yet prior studies typically examine individual techniques in isolation, limiting understanding of their relative m...
Minh Hoang Nguyen, Vu Hoang Pham, Xuan Thanh Huynh, Phuc Hong Mai, Vinh The Nguyen, Quang Nhut Hu...
Before You Hand Over the Wheel: Evaluating LLMs for Security Incident Analysis
Security incident analysis (SIA) poses a major challenge for security operations centers, which must manage overwhelming alert volumes, large and diverse data sources, complex toolchains, and limit...
Sourov Jajodia, Madeena Sultana, Suryadipta Majumdar, Adrian Taylor, Grant Vandenberghe
Evaluation of Deontic Conditional Reasoning in Large Language Models: The Case of Wason's Selection Task
As large language models (LLMs) advance in linguistic competence, their reasoning abilities are gaining increasing attention. In humans, reasoning often performs well in domain specific settings, p...
Hirohiko Abe, Kentaro Ozeki, Risako Ando, Takanobu Morishita, Koji Mineshima, Mitsuhiro Okada
Physical Simulator In-the-Loop Video Generation
Recent advances in diffusion-based video generation have achieved remarkable visual realism but still struggle to obey basic physical laws such as gravity, inertia, and collision. Generated objects...
Lin Geng Foo, Mark He Huang, Alexandros Lattas, Stylianos Moschoglou, Thabo Beeler, Christian The...
Efficient, Property-Aligned Fan-Out Retrieval via RL-Compiled Diffusion
Many modern retrieval problems are set-valued: given a broad intent, the system must return a collection of results that optimizes higher-order properties (e.g., diversity, coverage, complementar...
Pengcheng Jiang, Judith Yue Li, Moonkyung Ryu, R. Lily Hu, Kun Su, Zhong Yi Wan, Liam Hebert, Hao...
Talk Freely, Execute Strictly: Schema-Gated Agentic AI for Flexible and Reproducible Scientific Workflows
Large language models (LLMs) can now translate a researcher's plain-language goal into executable computation, yet scientific workflows demand determinism, provenance, and governance that are diffi...
Joel Strickland, Arjun Vijeta, Chris Moores, Oliwia Bodek, Bogdan Nenchev, Thomas Whitehead, Char...
Kinetic-based regularization: Learning spatial derivatives and PDE applications
Accurate estimation of spatial derivatives from discrete and noisy data is central to scientific machine learning and numerical solutions of PDEs. We extend kinetic-based regularization (KBR), a lo...
Abhisek Ganguly, Santosh Ansumali, Sauro Succi
Doctor or Patient? Synergizing Diarization and ASR for Code-Switched Hinglish Medical Conditions Extraction
Extracting patient medical conditions from code-switched clinical spoken dialogues is challenging due to rapid turn-taking and highly overlapped speech. We present a robust system evaluated on the ...
Séverin Baroudi, Yanis Labrak, Shashi Kumar, Joonas Kalda, Sergio Burdisso, Pawel Cyrta, Juan Ign...
ESAA-Security: An Event-Sourced, Verifiable Architecture for Agent-Assisted Security Audits of AI-Generated Code
AI-assisted software generation has increased development speed, but it has also amplified a persistent engineering problem: systems that are functionally correct may still be structurally insecure...
Elzo Brito dos Santos Filho
CLAIRE: Compressed Latent Autoencoder for Industrial Representation and Evaluation -- A Deep Learning Framework for Smart Manufacturing
Accurate fault detection in high-dimensional industrial environments remains a major challenge due to the inherent complexity, noise, and redundancy in sensor data. This paper introduces CLAIRE, i....
Mohammadhossein Ghahramani, Mengchu Zhou
A Scalable Benchmark for Repository-Oriented Long-Horizon Conversational Context Management
In recent years, large language models (LLMs) have advanced rapidly, substantially enhancing their code understanding and generation capabilities and giving rise to powerful code assistants. Howeve...
Yang Liu, Li Zhang, Fang Liu, Ping Lin, Xinyi Li
MoEless: Efficient MoE LLM Serving via Serverless Computing
Large Language Models (LLMs) have become a cornerstone of AI, driving progress across diverse domains such as content creation, search and recommendation systems, and AI-assisted workflows. To alle...
Hanfei Yu, Bei Ouyang, Shwai He, Ang Li, Hao Wang
Transparent AI for Mathematics: Transformer-Based Large Language Models for Mathematical Entity Relationship Extraction with XAI
Mathematical text understanding is a challenging task due to the presence of specialized entities and complex relationships between them. This study formulates mathematical problem interpretation a...
Tanjim Taharat Aurpa
How students use generative AI for computational modeling in physics
Generative artificial intelligence (genAI) is becoming increasingly prevalent and capable in physics, particularly for programming-related tasks. How, then, does genAI affect students' computationa...
Karl Henrik Fredly, Tor Ole Odden, Benjamin M. Zwickl
AI End-to-End Radiation Treatment Planning Under One Second
Artificial intelligence-based radiation therapy (RT) planning has the potential to reduce planning time and inter-planner variability, improving efficiency and consistency in clinical workflows. Mo...
Simon Arberet, Riqiang Gao, Martin Kraus, Florin C. Ghesu, Wilko Verbakel, Mamadou Diallo, Anthon...
SAHOO: Safeguarded Alignment for High-Order Optimization Objectives in Recursive Self-Improvement
Recursive self-improvement is moving from theory to practice: modern systems can critique, revise, and evaluate their own outputs, yet iterative self-modification risks subtle alignment drift. We i...
Subramanyam Sahoo, Aman Chadha, Vinija Jain, Divya Chaudhary
Structured Exploration vs. Generative Flexibility: A Field Study Comparing Bandit and LLM Architectures for Personalised Health Behaviour Interventions
Behaviour Change Techniques (BCTs) are central to digital health interventions, yet selecting and delivering effective techniques remains challenging. Contextual bandits enable statistically ground...
Dominik P. Hofer, Haochen Song, Rania Islambouli, Laura Hawkins, Ananya Bhattacharjee, Meredith F...
The Art That Poses Back: Assessing AI Pastiches after Contemporary Artworks
This study explores artificial visual creativity, focusing on ChatGPT's ability to generate new images intentionally pastiching original artworks such as paintings, drawings, sculptures and install...
Anca Dinu, Andreiana Mihail, Andra-Maria Florescu, Claudiu Creanga