Research

Papers

Research papers from arXiv and related sources

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

Multilingual KokoroChat: A Multi-LLM Ensemble Translation Method for Creating a Multilingual Counseling Dialogue Dataset

To address the critical scarcity of high-quality, publicly available counseling dialogue datasets, we created Multilingual KokoroChat by translating KokoroChat, a large-scale manually authored Japa...

Ryoma Suzuki, Zhiyang Qi, Michimasa Inaba

2603.22913 2026-03-24
AI LLM

From the AI Act to a European AI Agency: Completing the Union's Regulatory Architecture

As artificial intelligence (AI) technologies continue to advance, effective risk assessment, regulation, and oversight are necessary to ensure that AI development and deployment align with ethical ...

Georgios Pavlidis

2603.22912 2026-03-24
AI LLM

EchoKV: Efficient KV Cache Compression via Similarity-Based Reconstruction

The increasing memory demand of the Key-Value (KV) cache poses a significant bottleneck for Large Language Models (LLMs) in long-context applications. Existing low-rank compression methods often re...

Yixuan Wang, Shiyu Ji, Yijun Liu, Qingfu Zhu, Wanxiang Che

2603.22910 2026-03-24
AI LLM

Dual-Teacher Distillation with Subnetwork Rectification for Black-Box Domain Adaptation

Assuming that neither source data nor the source model is accessible, black box domain adaptation represents a highly practical yet extremely challenging setting, as transferable information is res...

Zhe Zhang, Jing Li, Wanli Xue, Xu Cheng, Jianhua Zhang, Qinghua Hu, Shengyong Chen

2603.22908 2026-03-24
AI LLM

Separating Diagnosis from Control: Auditable Policy Adaptation in Agent-Based Simulations with LLM-Based Diagnostics

Mitigating elderly loneliness requires policy interventions that achieve both adaptability and auditability. Existing methods struggle to reconcile these objectives: traditional agent-based models ...

Shaoxin Zhong, Yuchen Su, Michael Witbrock

2603.22904 2026-03-24
AI LLM

Task-Aware Positioning for Improvisational Tasks in Mobile Construction Robots via an AI Agent with Multi-LMM Modules

Due to the ever-changing nature of construction, many tasks on sites occur in an improvisational manner. Existing mobile construction robot studies remain limited in addressing improvisational task...

Seongju Jang, Francis Baek, SangHyun Lee

2603.22903 2026-03-24
TESTING

A diffuse-interface model for N-phase flows with liquid-solid phase change

In this work, we first propose a diffuse interface model for simulating N phase flows with solid liquid phase change. In this model, a phase field approach is adopted to capture multiphase fluid in...

Jiangxu Huang, Chengjie Zhan, Zhenhua Chai, Changsheng Huang, Xi Liu

2603.22902 2026-03-24
TESTING

Critical LAN and Score Tests for Mixed Fractional Models under High-Frequency Observation at H=3/4

We study the critical boundary $H=3/4$ for two mixed fractional models under high-frequency observation, namely mixed fractional Brownian motion and mixed fractional Ornstein--Uhlenbeck. For differ...

Chunhao Cai, Yiwu Shang, Cong Zhang

2603.22888 2026-03-24
TESTING

TreeTeaming: Autonomous Red-Teaming of Vision-Language Models via Hierarchical Strategy Exploration

The rapid advancement of Vision-Language Models (VLMs) has brought their safety vulnerabilities into sharp focus. However, existing red teaming methods are fundamentally constrained by an inherent ...

Chunxiao Li, Lijun Li, Jing Shao

2603.22882 2026-03-24
TESTING

Portfolio Optimization under Recursive Utility via Reinforcement Learning

We study whether a risk-sensitive objective from asset-pricing theory -- recursive utility -- improves reinforcement learning for portfolio allocation. The Bellman equation under recursive utility ...

Minkey Chang

2603.22880 2026-03-24
TESTING

Continuous Optimization for Satisfiability Modulo Theories on Linear Real Arithmetic

Efficient solutions for satisfiability modulo theories (SMT) are integral in industrial applications such as hardware verification and design automation. Existing approaches are predominantly based...

Yunuo Cen, Daniel Ebler, Xuanyao Fong

2603.22877 2026-03-24
TESTING

Grounding Sim-to-Real Generalization in Dexterous Manipulation: An Empirical Study with Vision-Language-Action Models

Learning a generalist control policy for dexterous manipulation typically relies on large-scale datasets. Given the high cost of real-world data collection, a practical alternative is to generate s...

Ruixing Jin, Zicheng Zhu, Ruixiang Ouyang, Sheng Xu, Bo Yue, Zhizheng Wu, Guiliang Liu

2603.22876 2026-03-24
TESTING

Designing to Forget: Deep Semi-parametric Models for Unlearning

Recent advances in machine unlearning have focused on developing algorithms to remove specific training samples from a trained model. In contrast, we observe that not all models are equally easy to...

Amber Yijia Zheng, Yu-Shan Tai, Raymond A. Yeh

2603.22870 2026-03-24
TESTING

Breaking news

This paper examines how regulatory interventions in high-frequency financial markets affect price discovery. We focus on Breaking news, where dynamic circuit breakers trigger trading halts immediat...

Lars Winkelmann, Wenying Yao

2603.22835 2026-03-24
TESTING

Probing the Bias of Large-Scale Structure with Unlocalized Fast Radio Bursts

Large-scale structure (LSS) and tracer bias connect observable populations to the cosmic matter distribution. While galaxies are standard tracers, transient events such as gravitational-wave source...

Yu-Tong Su, Zhengxiang Li

2603.22832 2026-03-24
TESTING

When AI Shows Its Work, Is It Actually Working? Step-Level Evaluation Reveals Frontier Language Models Frequently Bypass Their Own Reasoning

Language models increasingly "show their work" by writing step-by-step reasoning before answering. But are these reasoning steps genuinely used, or decorative narratives generated after the model h...

Abhinaba Basu, Pavan Chakraborty

2603.22816 2026-03-24
TESTING

Universal and efficient graph neural networks with dynamic attention for machine learning interatomic potentials

The core of molecular dynamics simulation fundamentally lies in the interatomic potential. Traditional empirical potentials lack accuracy, while first-principles methods are computationally prohibi...

Shuyu Bi, Zhede Zhao, Qiangchao Sun, Tao Hu, Xionggang Lu, Hongwei Cheng

2603.22810 2026-03-24
TESTING

The Costs of Early-career Disciplinary Pivots: Evidence from PhD Admissions

Scientific innovation often comes from researchers who pivot across disciplines. However, prior work found that established researchers face productivity penalties when pivoting. Here, we investiga...

Sidney Xiang, Nicholas David, Dallas Card, Wenhao Sun, Daniel M Romero, Misha Teplitskiy

2603.22805 2026-03-24
TESTING

Search for the radiative decays $D^0\to γ\bar K_1(1270)^0$ and $D^+\to γK_1(1270)^+$

A search for the radiative decays $D^0\to γ\bar K_1(1270)^0$ and $D^+\to γK_1(1270)^+$ is conducted using $20.3~\mathrm{fb}^{-1}$ of $e^+e^-$ annihilation data collected at the center-of-mass energ...

BESIII Collaboration, M. Ablikim, M. N. Achasov, P. Adlarson, X. C. Ai, R. Aliberti, A. Amoroso,...

2603.22804 2026-03-24
TESTING

ABSTRAL: Automatic Design of Multi-Agent Systems Through Iterative Refinement and Topology Optimization

How should multi-agent systems be designed, and can that design knowledge be captured in a form that is inspectable, revisable, and transferable? We introduce ABSTRAL, a framework that treats MAS a...

Weijia Song, Jiashu Yue, Zhe Pang

2603.22791 2026-03-24