Research

Papers

Research papers from arXiv and related sources

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

Riding Brainwaves in LLM Space: Understanding Activation Patterns Using Individual Neural Signatures

Consumer-grade EEG is entering everyday devices, from earbuds to headbands, raising the question of whether language models can be adapted to individual neural responses. We test this by asking whe...

Ajan Subramanian, Sumukh Bettadapura, Rohan Sathish

2603.21847 2026-03-23
AI LLM

Agentic Personas for Adaptive Scientific Explanations with Knowledge Graphs

AI explanation methods often assume a static user model, producing non-adaptive explanations regardless of expert goals, reasoning strategies, or decision contexts. Knowledge graph-based explanatio...

Susana Nunes, Tiago Guerreiro, Catia Pesquita

2603.21846 2026-03-23
TESTING

On the Number of Conditional Independence Tests in Constraint-based Causal Discovery

Learning causal relations from observational data is a fundamental problem with wide-ranging applications across many fields. Constraint-based methods infer the underlying causal structure by perfo...

Marc Franquesa Monés, Jiaqi Zhang, Caroline Uhler

2603.21844 2026-03-23
TESTING

Select, Label, Evaluate: Active Testing in NLP

Human annotation cost and time remain significant bottlenecks in Natural Language Processing (NLP), with test data annotation being particularly expensive due to the stringent requirement for low-e...

Antonio Purificato, Maria Sofia Bucarelli, Andrea Bacciu, Amin Mantrach, Fabrizio Silvestri

2603.21840 2026-03-23
TESTING

A Unified Heterogeneous Implementation of Numerical Atomic Orbitals-Based Real-Time TDDFT within the ABACUS Package

We present a unified heterogeneous computing framework for real-time time-dependent density functional theory (RT-TDDFT) based on numerical atomic orbitals (NAOs), implemented in the ABACUS package...

Taoni Bao, Yuanbo Li, Zichao Deng, Haotian Zhao, Denghui Lu, Yike Huang, Chao Lian, Lixin He, Moh...

2603.21835 2026-03-23
TESTING

Publicly Understandable Electronic Voting: A Non-Cryptographic, End-to-End Verifiable Scheme

Modern democracies face an existential crisis of waning public trust in election results. While End-to-End Verifiable (E2E-V) voting systems promise mathematically secure elections, their reliance ...

Alon Gat

2603.21833 2026-03-23
TESTING

Can Renewable Energy Mitigate Inflationary Pressures from Energy Imports? Evidence from Türkiye

This study analyses the potential of renewable energy to reduce inflationary pressures arising from energy imports in Turkiye. Annual data for the period 1980-2022 are used in the analysis. In this...

Emre Akusta

2603.21815 2026-03-23
AI LLM

Take the Train: Africa at the Crossroad of Modern AI

Africa's participation in modern AI development is constrained by severe infrastructural and policy gaps. Important barriers include limited access to high-performance computing (HPC), restricted c...

Cédric Manouan, Miquilina Anagbah, N'guessan Yves-Roland Douha, João Barros

2603.21795 2026-03-23
TESTING

Using spatiotemporal Born rule for testing macroscopic realism: some applications to the pseudo-density matrices and nonclassical temporal correlations

We show that, given an evolving quantum system and the quasiprobability distribution generated by the spatiotemporal generalization of the Born rule in pseudo density-matrices (PDMs), this distribu...

Naim Elias Comar, Lucas C. Céleri, Mia Stamatova, Vlatko Vedral, Aditya Varna Iyer, Rafael Chaves

2603.21793 2026-03-23
TESTING

Why does it fail? Explanation of verification failures

Satisfiability solving is a common technique for formal verification forming the basis of many proof and model checking systems. Failure to show a proof obligation will produce a counterexample or ...

Lars-Henrik Eriksson

2603.21788 2026-03-23
TESTING

The Universal Normal Embedding

Generative models and vision encoders have largely advanced on separate tracks, optimized for different goals and grounded in different mathematical principles. Yet, they share a fundamental proper...

Chen Tasker, Roy Betser, Eyal Gofer, Meir Yossef Levi, Guy Gilboa

2603.21786 2026-03-23
AI LLM

A Curated List of Open-source Software-only Energy Efficiency Measurement Tools: A GitHub Mining Study

Energy efficiency has become a growing concern in software development, leading to the need for tools designed to measure energy consumption. While several energy measurement tools are available as...

Manuela Bechara Cannizza, Michel Albonico

2603.21772 2026-03-23
TESTING

Quantifying Uncertainty in FMEDA Safety Metrics: An Error Propagation Approach for Enhanced ASIC Verification

Accurate and reliable safety metrics are paramount for functional safety verification of ASICs in automotive systems. Traditional FMEDA (Failure Modes, Effects, and Diagnostic Analysis) metrics, su...

Antonino Armato, Christian Kehl, Sebastian Fischer

2603.21770 2026-03-23
TESTING

Strict Entropy Decrease of Clausius Entropy in an Isolated System with Energy-Form Conversion: Theoretical Proof, Numerical Illustration, and Critical Examination

This paper is accountable only to explicitly stated physical assumptions and strict logical inference. Its goal is to run a rigorous stress test of second-law claims within the Clausius framework. ...

Ting Peng

2603.21765 2026-03-23
TESTING

The fragility of the Uranian moons during the giant planet instability

It is thought that, sometime after their formation, the solar system's giant planets experienced a dynamical instability that caused their orbits to excite, diverge, and ejected one or more objects...

Matthew S. Clement, Nathan A. Kaib, Andre Izidoro, Rogerio Deienno

2603.21750 2026-03-23
AI LLM

The Presupposition Problem in Representation Genesis

Large language models are the first systems to achieve high cognitive performance without clearly undergoing representation genesis: the transition from a non-representing physical system to one wh...

Yiling Wu

2603.21745 2026-03-23
TESTING

CellFluxRL: Biologically-Constrained Virtual Cell Modeling via Reinforcement Learning

Building virtual cells with generative models to simulate cellular behavior in silico is emerging as a promising paradigm for accelerating drug discovery. However, prior image-based generative appr...

Dongxia Wu, Shiye Su, Yuhui Zhang, Elaine Sui, Emma Lundberg, Emily B. Fox, Serena Yeung-Levy

2603.21743 2026-03-23
AI LLM

The Reasoning Error About Reasoning: Why Different Types of Reasoning Require Different Representational Structures

Different types of reasoning impose different structural demands on representational systems, yet no systematic account of these demands exists across psychology, AI, and philosophy of mind. I prop...

Yiling Wu

2603.21736 2026-03-23
AI LLM

Cognitive Agency Surrender: Defending Epistemic Sovereignty via Scaffolded AI Friction

The proliferation of Generative Artificial Intelligence has transformed benign cognitive offloading into a systemic risk of cognitive agency surrender. Driven by the commercial dogma of "zero-frict...

Kuangzhe Xu, Yu Shen, Longjie Yan, Yinghui Ren

2603.21735 2026-03-23
AI LLM

EvoIdeator: Evolving Scientific Ideas through Checklist-Grounded Reinforcement Learning

Scientific idea generation is a cornerstone of autonomous knowledge discovery, yet the iterative evolution required to transform initial concepts into high-quality research proposals remains a form...

Andreas Sauter, Yuyue Zhao, Jacopo Urbani, Wenxiang Hu, Zaiqiao Meng, Lun Zhou, Xiaohui Yan, Youg...

2603.21728 2026-03-23