Research

Papers

Research papers from arXiv and related sources

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

Momentum Memory for Knowledge Distillation in Computational Pathology

Multimodal learning that integrates genomics and histopathology has shown strong potential in cancer diagnosis, yet its clinical translation is hindered by the limited availability of paired histol...

Yongxin Guo, Hao Lu, Onur C. Koyun, Zhengjie Zhu, Muhammet Fatih Demir, Metin Nafi Gurcan

2602.21395 2026-02-24
TESTING

Defensive Generation

We study the problem of efficiently producing, in an online fashion, generative models of scalar, multiclass, and vector-valued outcomes that cannot be falsified on the basis of the observed data a...

Gabriele Farina, Juan Carlos Perdomo

2602.21390 2026-02-24
TESTING

The Mean is the Mirage: Entropy-Adaptive Model Merging under Heterogeneous Domain Shifts in Medical Imaging

Model merging under unseen test-time distribution shifts often renders naive strategies, such as mean averaging unreliable. This challenge is especially acute in medical imaging, where models are f...

Sameer Ambekar, Reza Nasirigerdeh, Peter J. Schuffler, Lina Felsner, Daniel M. Lang, Julia A. Sch...

2602.21372 2026-02-24
TESTING

Some Asymptotic Results on Multiple Testing under Weak Dependence

This paper studies the means-testing problem under weakly correlated Normal setups. Although quite common in genomic applications, test procedures having exact FWER control under such dependence st...

Swarnadeep Datta, Monitirtha Dey

2602.21359 2026-02-24
TESTING

Precedence-Constrained Decision Trees and Coverings

This work considers a number of optimization problems and reductive relations between them. The two main problems we are interested in are the \emph{Optimal Decision Tree} and \emph{Set Cover}. We ...

Michał Szyfelbein, Dariusz Dereniowski

2602.21312 2026-02-24
TESTING

Coherent Quantum Evaluation of Collider Amplitudes for Effective Field Theory Constraints

Precision measurements at electron-positron colliders provide stringent tests of the Standard Model and powerful probes of possible higher-dimensional interactions. We present a hybrid quantum-clas...

Yacine Haddad, Kaidi Xu, Vincent Croft, Jad C. Halimeh, Michele Grossi

2602.21311 2026-02-24
TESTING

Implications for PBH Dark Matter from a single Sub-Solar$\unicode{x2013}$GW Detection in LVK O1$\unicode{x2013}$O4

The detection of sub-solar mass black holes is a milestone of modern astrophysics as it would open a window either onto new stellar physics or could potentially unveil the nature of Dark Matter as ...

Alberto Magaraggia, Nico Cappelluti

2602.21295 2026-02-24
TESTING

Evolution of Cosmic Voids: Structure, Galaxies, and Dynamics

We investigate the structural, photometric, and dynamical evolution of cosmic voids and their galaxy populations from $z=2.09$ to the present, focusing on void size as a key evolutionary parameter....

Saeed Tavasoli

2602.21292 2026-02-24
TESTING

Testing models for fully and partially stripped low-mass stars with Gaia: Implications for hot subdwarfs, binary RR Lyrae, and black hole impostors

When low-mass ($\lesssim 2$ $M_{\odot}$) red giants lose their envelopes to a companion just before the helium flash, the resulting mass transfer can produce binaries hosting hot subdwarfs, horizon...

Pranav Nagarajan, Kareem El-Badry, Alexey Bobrick, Giuliano Iorio, Francisco Molina, Joris Vos, M...

2602.21289 2026-02-24
TESTING

Test-Time Training with KV Binding Is Secretly Linear Attention

Test-time training (TTT) with KV binding as sequence modeling layer is commonly interpreted as a form of online meta-learning that memorizes a key-value mapping at test time. However, our analysis ...

Junchen Liu, Sven Elflein, Or Litany, Zan Gojcic, Ruilong Li

2602.21204 2026-02-24
AI LLM

Aletheia tackles FirstProof autonomously

We report the performance of Aletheia (Feng et al., 2026b), a mathematics research agent powered by Gemini 3 Deep Think, on the inaugural FirstProof challenge. Within the allowed timeframe of the c...

Tony Feng, Junehyuk Jung, Sang-hyun Kim, Carlo Pagano, Sergei Gukov, Chiang-Chiang Tsai, David Wo...

2602.21201 2026-02-24
AI LLM

Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs

Embodied LLMs endow robots with high-level task reasoning, but they cannot reflect on what went wrong or why, turning deployment into a sequence of independent trials where mistakes repeat rather t...

Yining Hong, Huang Huang, Manling Li, Li Fei-Fei, Jiajun Wu, Yejin Choi

2602.21198 2026-02-24
TESTING

Variants of Raviart-Thomas mixed elements for curved domains using straight-edged tetrahedra

A numerical study of tetrahedral Raviart-Thomas mixed finite element methods is presented in the solution of model second order boundary value problems posed in a curved spatial domain. An emphasis...

Vittoriano Ruas

2602.21197 2026-02-24
AI LLM

On Data Engineering for Scaling LLM Terminal Capabilities

Despite rapid recent progress in the terminal capabilities of large language models, the training data strategies behind state-of-the-art terminal agents remain largely undisclosed. We address this...

Renjie Pi, Grace Lam, Mohammad Shoeybi, Pooya Jannaty, Bryan Catanzaro, Wei Ping

2602.21193 2026-02-24
AI LLM

Why Pass@k Optimization Can Degrade Pass@1: Prompt Interference in LLM Post-training

Pass@k is a widely used performance metric for verifiable large language model tasks, including mathematical reasoning, code generation, and short-answer reasoning. It defines success if any of $k$...

Anas Barakat, Souradip Chakraborty, Khushbu Pahwa, Amrit Singh Bedi

2602.21189 2026-02-24
AI LLM

XMorph: Explainable Brain Tumor Analysis Via LLM-Assisted Hybrid Deep Intelligence

Deep learning has significantly advanced automated brain tumor diagnosis, yet clinical adoption remains limited by interpretability and computational constraints. Conventional models often act as o...

Sepehr Salem Ghahfarokhi, M. Moein Esfahani, Raj Sunderraman, Vince Calhoun, Mohammed Alser

2602.21178 2026-02-24
AI LLM

NoRD: A Data-Efficient Vision-Language-Action Model that Drives without Reasoning

Vision-Language-Action (VLA) models are advancing autonomous driving by replacing modular pipelines with unified end-to-end architectures. However, current VLAs face two expensive requirements: (1)...

Ishaan Rawal, Shubh Gupta, Yihan Hu, Wei Zhan

2602.21172 2026-02-24
TESTING

Revisiting CPL with sign-switching density: to cross or not to cross the NECB

Recent DESI DR2 BAO measurements, when combined with CMB and SNeIa data, exhibit a $3.2σ$-$3.4σ$ preference for dynamical dark energy (DE) described by the CPL-parametrized equation of state. A par...

Mine Gökçen, Özgür Akarsu, Eleonora Di Valentino

2602.21169 2026-02-24
TESTING

A Novel Explicit Filter for the Approximate Deconvolution in Large-Eddy Simulation on General Unstructured Grids: A posteriori tests on highly stretched grids

Explicit filters play a pivotal role in the scale separation and numerical stability of advanced Large Eddy Simulation (LES) closures, such as dynamic eddy-viscosity or Approximate Deconvolution (A...

Mohammad Bagher Molaei, Ehsan Amani, Morteza Ghorbani

2602.21166 2026-02-24
AI LLM

ActionReasoning: Robot Action Reasoning in 3D Space with LLM for Robotic Brick Stacking

Classical robotic systems typically rely on custom planners designed for constrained environments. While effective in restricted settings, these systems lack generalization capabilities, limiting t...

Guangming Wang, Qizhen Ying, Yixiong Jing, Olaf Wysocki, Brian Sheil

2602.21161 2026-02-24