Research

Papers

Research papers from arXiv and related sources

Total: 4513 AI/LLM: 2483 Testing: 2030
TESTING

Teacher-Student Diffusion Model for Text-Driven 3D Hand Motion Generation

Generating realistic 3D hand motion from natural language is vital for VR, robotics, and human-computer interaction. Existing methods either focus on full-body motion, overlooking detailed hand ges...

Ching-Lam Cheng, Bin Zhu, Shengfeng He

2603.24407 2026-03-25
AI LLM

AI-Supervisor: Autonomous AI Research Supervision via a Persistent Research World Model

Existing automated research systems operate as stateless, linear pipelines, generating outputs without maintaining a persistent understanding of the research landscape. They process papers sequenti...

Yunbo Long

2603.24402 2026-03-25
TESTING

Exploring How Fair Model Representations Relate to Fair Recommendations

One of the many fairness definitions pursued in recent recommender system research targets mitigating demographic information encoded in model representations. Models optimized for this definition ...

Bjørnar Vassøy, Benjamin Kille, Helge Langseth

2603.24396 2026-03-25
AI LLM

The enrichment paradox: critical capability thresholds and irreversible dependency in human-AI symbiosis

As artificial intelligence assumes cognitive labor, no quantitative framework predicts when human capability loss becomes catastrophic. We present a two-variable dynamical systems model coupling ca...

Jeongju Park, Musu Kim, Sekyung Han

2603.24391 2026-03-25
AI LLM

When AI Meets Early Childhood Education: Large Language Models as Assessment Teammates in Chinese Preschools

High-quality teacher-child interaction (TCI) is fundamental to early childhood development, yet traditional expert-based assessment faces a critical scalability challenge. In large systems like Chi...

Xingming Li, Runke Huang, Yanan Bao, Yuye Jin, Yuru Jiao, Qingyong Hu

2603.24389 2026-03-25
AI LLM

Causal Transfer in Medical Image Analysis

Medical imaging models frequently fail when deployed across hospitals, scanners, populations, or imaging protocols due to domain shift, limiting their clinical reliability. While transfer learning ...

Mohammed M. Abdelsamea, Daniel Tweneboah Anyimadu, Tasneem Selim, Saif Alzubi, Lei Zhang, Ahmed K...

2603.24388 2026-03-25
AI LLM

MolEvolve: LLM-Guided Evolutionary Search for Interpretable Molecular Optimization

Despite deep learning's success in chemistry, its impact is hindered by a lack of interpretability and an inability to resolve activity cliffs, where minor structural nuances trigger drastic proper...

Xiangsen Chen, Ruilong Wu, Yanyan Lan, Ting Ma, Yang Liu

2603.24382 2026-03-25
AI LLM

Towards Reward Modeling for AI Tutors in Math Mistake Remediation

Evaluating the pedagogical quality of AI tutors remains challenging: standard NLG metrics do not determine whether responses identify mistakes, scaffold reasoning, or avoid revealing the answers. F...

Kseniia Petukhova, Ekaterina Kochmar

2603.24375 2026-03-25
AI LLM

Improving Lean4 Autoformalization via Cycle Consistency Fine-tuning

Autoformalization - automatically translating natural language mathematical texts into formal proof language such as Lean4 - can help accelerate AI-assisted mathematical research, be it via proof v...

Arsen Shebzukhov

2603.24372 2026-03-25
TESTING

Adaptive decision-making for stochastic service network design

This paper addresses the Service Network Design (SND) problem for a logistics service provider (LSP) operating in a multimodal freight transport network, considering uncertain travel times and limi...

Javier Duran Micco, Bilge Atasoy

2603.24369 2026-03-25
AI LLM

LATS: Large Language Model Assisted Teacher-Student Framework for Multi-Agent Reinforcement Learning in Traffic Signal Control

Adaptive Traffic Signal Control (ATSC) aims to optimize traffic flow and minimize delays by adjusting traffic lights in real time. Recent advances in Multi-agent Reinforcement Learning (MARL) have ...

Yifeng Zhang, Peizhuo Li, Tingguang Zhou, Mingfeng Fan, Guillaume Sartoretti

2603.24361 2026-03-25
TESTING

Aluminum solidification and nanopolycrystal deformation via a Graph Neural Network Potential and Million-Atom Simulations

Solidification governs the microstructure and, therefore, the mechanical response of metal components, yet the atomistic details of nucleation and defect formation are often difficult to determine ...

Ian Störmer, Julija Zavadlav

2603.24360 2026-03-25
AI LLM

Gendered Prompting and LLM Code Review: How Gender Cues in the Prompt Shape Code Quality and Evaluation

LLMs are increasingly embedded in programming workflows, from code generation to automated code review. Yet, how gendered communication styles interact with LLM-assisted programming and code review...

Lynn Janzen, Üveys Eroglu, Dorothea Kolossa, Pia Knöferle, Sebastian Möller, Vera Schmitt, Veroni...

2603.24359 2026-03-25
AI LLM

Language-Guided Structure-Aware Network for Camouflaged Object Detection

Camouflaged Object Detection (COD) aims to segment objects that are highly integrated with the background in terms of color, texture, and structure, making it a highly challenging task in computer ...

Min Zhang

2603.24355 2026-03-25
AI LLM

Evidence of an Emergent "Self" in Continual Robot Learning

A key challenge to understanding self-awareness has been a principled way of quantifying whether an intelligent system has a concept of a "self," and if so how to differentiate the "self" from othe...

Adidev Jhunjhunwala, Judah Goldfeder, Hod Lipson

2603.24350 2026-03-25
TESTING

Effects of the initial-state geometry on D-meson production in pp and pPb collisions

Going from lower to higher multiplicity events in proton-proton and proton-lead collisions, the data show a stronger than linear growth of the D-meson normalized yields. In this contribution we try...

R. Terra, A. V. Giannini, F. S. Navarra

2603.24344 2026-03-25
AI LLM

Enhancing Efficiency and Performance in Deepfake Audio Detection through Neuron-level dropin & Neuroplasticity Mechanisms

Current audio deepfake detection has achieved remarkable performance using diverse deep learning architectures such as ResNet, and has seen further improvements with the introduction of large model...

Yupei Li, Shuaijie Shao, Manuel Milling, Björn Schuller

2603.24343 2026-03-25
AI LLM

Generative Artificial Intelligence and the Knowledge Gap: Toward a New Form of Informational Inequality

The knowledge gap hypothesis suggests that the diffusion of information tends to increase rather than reduce social inequalities. Subsequent research on the digital divide has extended this perspec...

Raphael Morisco

2603.24335 2026-03-25
TESTING

Lyman-$α$ Forest Constraint on Dark Matter from Dark Sector Decay

By exploiting small-scale structure formation probed by Lyman-$α$ forest observations, we study constraints on a model of dark matter from dark sector decay. We compute the phase space distribution...

Si-Yuan Zhao, Yi-Cheng Dai, Wei Liao, Yi-Song Lu

2603.24331 2026-03-25
AI LLM

On the Quartic Invariant of Odd Degree Binary Forms

We determine the squarefree part of the scalar factor that arises when the quartic invariant of the generic binary form $F$ of odd degree $2n+1$ is expressed as the discriminant of the unique quadr...

Ashvin Swaminathan

2603.24330 2026-03-25