Research

Papers

Research papers from arXiv and related sources

Total: 4694 AI/LLM: 2583 Testing: 2111
TESTING

Self-testing with untrusted random number generators

Self-testing--the attractive possibility to infer the underlying physics of a quantum device in a black-box scenario--has gained increased traction in recent years, with applications to device-inde...

Moisés Bermejo Morán, Ravishankar Ramanathan

2603.10663 2026-03-11
TESTING

Planning for isolation? The role of urban form and function in shaping mobility in Brasília

Brasília offers a rare test of how urban form shapes experienced segregation. Built almost at once around modernist neighbourhood units, then expanded through planned satellites and informal periph...

Andrew Renninger

2603.10657 2026-03-11
AI LLM

ESG Reporting Lifecycle Management with Large Language Models and AI Agents

Environmental, Social, and Governance (ESG) standards have been increasingly adopted by organizations to demonstrate accountability towards ethical, social, and sustainability goals. However, gener...

Thong Hoang, Mykhailo Klymenko, Xiwei Xu, Shidong Pan, Yi Ding, Xushuo Tang, Zhengyi Yang, Jieke ...

2603.10646 2026-03-11
AI LLM

Making Bielik LLM Reason (Better): A Field Report

This paper presents a research program dedicated to evaluating and advancing the reasoning capabilities of Bielik, a Polish large language model. The study describes a number of stages of work: ini...

Adam Trybus, Bartosz Bartnicki, Remigiusz Kinas

2603.10640 2026-03-11
AI LLM

Splat2Real: Novel-view Scaling for Physical AI with 3D Gaussian Splatting

Physical AI faces viewpoint shift between training and deployment, and novel-view robustness is essential for monocular RGB-to-3D perception. We cast Real2Render2Real monocular depth pretraining as...

Hansol Lim, Jongseong Brad Choi

2603.10638 2026-03-11
TESTING

Flexible Multi-Target Angular Emulation for Over-the-Air Testing of Large-Scale ISAC Base Stations: Principle and Experimental Verification

Over-the-air (OTA) emulation of diverse sensing target characteristics in a controlled laboratory environment is pivotal for advancing integrated sensing and communication (ISAC) technology, as it ...

Chunhui Li, Hao Sun, Wei Fan

2603.10629 2026-03-11
TESTING

Reinforcement Learning with Conditional Expectation Reward

Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective in enhancing the reasoning capabilities of large language models, particularly in domains such as mathematics where reliab...

Changyi Xiao, Caijun Xu, Yixin Cao

2603.10624 2026-03-11
TESTING

QuantumX: an experience for the consolidation of Quantum Computing and Quantum Software Engineering as an emerging discipline

The first edition of the QuantumX track, held within the XXIX Jornadas de Ingeniería del Software y Bases de Datos (JISBD 2025), brought together leading Spanish research groups working at the inte...

Juan M. Murillo, Ignacio García Rodríguez de Guzmán, Enrique Moguel, Javier Romero-Álvarez, Jaime...

2603.10621 2026-03-11
AI LLM

Disentangling Similarity and Relatedness in Topic Models

The recent advancement of large language models has spurred a growing trend of integrating pre-trained language model (PLM) embeddings into topic models, fundamentally reshaping how topics capture ...

Hanlin Xiao, Mauricio A. Álvarez, Rainer Breitling

2603.10619 2026-03-11
AI LLM

Formulation of intrinsic nonlinear thermal conductivity for bosonic systems using quantum kinetic equation

Nonlinear responses in transport phenomena have attracted significant attention because they can arise even when linear responses are forbidden by symmetry, with the quantum geometry of Bloch wave ...

Aoi Kuwabara, Joji Nasu

2603.10605 2026-03-11
AI LLM

Trajectory-Informed Memory Generation for Self-Improving Agent Systems

LLM-powered agents face a persistent challenge: learning from their execution experiences to improve future performance. While agents can successfully complete many tasks, they often repeat ineffic...

Gaodan Fang, Vatche Isahagian, K. R. Jayaram, Ritesh Kumar, Vinod Muthusamy, Punleuk Oum, Gegi Th...

2603.10600 2026-03-11
AI LLM

Layer Consistency Matters: Elegant Latent Transition Discrepancy for Generalizable Synthetic Image Detection

Recent rapid advancement of generative models has significantly improved the fidelity and accessibility of AI-generated synthetic images. While enabling various innovative applications, the unprece...

Yawen Yang, Feng Li, Shuqi Kong, Yunfeng Diao, Xinjian Gao, Zenglin Shi, Meng Wang

2603.10598 2026-03-11
TESTING

Strong Gaussian approximation for U-statistics in high dimensions and beyond

We establish a strong Gaussian approximation for high-dimensional non-degenerate U-statistics with diverging dimension. Under mild assumptions, we construct, on a sufficiently rich probability spac...

Weijia Li, Leheng Cai, Qirui Hu

2603.10595 2026-03-11
TESTING

The Asteroid Framing Cameras on ESA's Hera mission

As the first asteroid deflection test, NASA's successfully hit asteroid Dimorphos (secondary of the binary asteroid 65803 Didymos) with the DART kinetic impactor on September 26, 2022. To fully cha...

Jean-Baptiste Vincent, Gábor Kovács, Balázs V. Nagy, Frank Preusker, Naomi Murdoch, Maurizio Pajo...

2603.10594 2026-03-11
TESTING

Exact Interpolation under Noise: A Reproducible Comparison of Clough-Tocher and Multiquadric RBF Surfaces

This paper presents a reproducible comparison of cubic and radial basis function (RBF) interpolants for multivariate surface analysis. To eliminate evaluation bias, both methods are assessed under ...

Mirkan Emir Sancak

2603.10590 2026-03-11
AI LLM

Does LLM Alignment Really Need Diversity? An Empirical Study of Adapting RLVR Methods for Moral Reasoning

Reinforcement learning with verifiable rewards (RLVR) has achieved remarkable success in logical reasoning tasks, yet whether large language model (LLM) alignment requires fundamentally different a...

Zhaowei Zhang, Xiaohan Liu, Xuekai Zhu, Junchao Huang, Ceyao Zhang, Zhiyuan Feng, Yaodong Yang, X...

2603.10588 2026-03-11
AI LLM

Distilling LLM Semantic Priors into Encoder-Only Multi-Talker ASR with Talker-Count Routing

Large language models (LLMs) provide strong semantic priors that can improve multi-talker automatic speech recognition (MT-ASR), but using an LLM as an autoregressive decoder is computationally exp...

Hao Shi, Yusuke Fujita, Roman Koshkin, Mengjie Zhao, Yuan Gao, Lianbo Liu, Yui Sudo

2603.10587 2026-03-11
TESTING

Need for Speed: Zero-Shot Depth Completion with Single-Step Diffusion

We introduce Marigold-SSD, a single-step, late-fusion depth completion framework that leverages strong diffusion priors while eliminating the costly test-time optimization typically associated with...

Jakub Gregorek, Paraskevas Pegios, Nando Metzger, Konrad Schindler, Theodora Kontogianni, Lazaros...

2603.10584 2026-03-11
AI LLM

Attribution as Retrieval: Model-Agnostic AI-Generated Image Attribution

With the rapid advancement of AIGC technologies, image forensics will encounter unprecedented challenges. Traditional methods are incapable of dealing with increasingly realistic images generated b...

Hongsong Wang, Renxi Cheng, Chaolei Han, Jie Gui

2603.10583 2026-03-11
TESTING

Implicit Statistical Inference in Transformers: Approximating Likelihood-Ratio Tests In-Context

In-context learning (ICL) allows Transformers to adapt to novel tasks without weight updates, yet the underlying algorithms remain poorly understood. We adopt a statistical decision-theoretic persp...

Faris Chaudhry, Siddhant Gadkari

2603.10573 2026-03-11