Research

Papers

Research papers from arXiv and related sources

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

A Comparative Analysis of LLM Memorization at Statistical and Internal Levels: Cross-Model Commonalities and Model-Specific Signatures

Memorization is a fundamental component of intelligence for both humans and LLMs. However, while LLM performance scales rapidly, our understanding of memorization lags. Due to limited access to the...

Bowen Chen, Namgi Han, Yusuke Miyao

2603.21658 2026-03-23
AI LLM

TrustFed: Enabling Trustworthy Medical AI under Data Privacy Constraints

Protecting patient privacy remains a fundamental barrier to scaling machine learning across healthcare institutions, where centralizing sensitive data is often infeasible due to ethical, legal, and...

Vagish Kumar, Syed Bahauddin Alam, Souvik Chakraborty

2603.21656 2026-03-23
TESTING

Towards Secure Retrieval-Augmented Generation: A Comprehensive Review of Threats, Defenses and Benchmarks

Retrieval-Augmented Generation (RAG) significantly mitigates the hallucinations and domain knowledge deficiency in large language models by incorporating external knowledge bases. However, the mult...

Yanming Mu, Hao Hu, Feiyang Li, Qiao Yuan, Jiang Wu, Zichuan Liu, Pengcheng Liu, Mei Wang, Hongwe...

2603.21654 2026-03-23
AI LLM

Are AI-assisted Development Tools Immune to Prompt Injection?

Prompt injection is listed as the number-one vulnerability class in the OWASP Top 10 for LLM Applications that can subvert LLM guardrails, disclose sensitive data, and trigger unauthorized tool use...

Charoes Huang, Xin Huang, Amin Milani Fard

2603.21642 2026-03-23
AI LLM

Auditing MCP Servers for Over-Privileged Tool Capabilities

The Model Context Protocol (MCP) has emerged as a standard for connecting Large Language Models (LLMs) to external tools and data. However, MCP servers often expose privileged capabilities, such as...

Charoes Huang, Xin Huang, Amin Milani Fard

2603.21641 2026-03-23
AI LLM

Engineering Distributed Governance for Regional Prosperity: A Socio-Technical Framework for Mitigating Under-Vibrancy via Human Data Engines

Most research in urban informatics and tourism focuses on mitigating overtourism in dense global cities. However, for regions experiencing demographic decline and structural stagnation, the primary...

Amil Khanzada, Takuji Takemoto

2603.21639 2026-03-23
TESTING

No Dense Tensors Needed: Fully Sparse Object Detection on Event-Camera Voxel Grids

Event cameras produce asynchronous, high-dynamic-range streams well suited for detecting small, fast-moving drones, yet most event-based detectors convert the sparse event stream into dense tensors...

Mohamad Yazan Sadoun, Sarah Sharif, Yaser Mike Banad

2603.21638 2026-03-23
AI LLM

Silicon Bureaucracy and AI Test-Oriented Education: Contamination Sensitivity and Score Confidence in LLM Benchmarks

Public benchmarks increasingly govern how large language models (LLMs) are ranked, selected, and deployed. We frame this benchmark-centered regime as Silicon Bureaucracy and AI Test-Oriented Educat...

Yiliang Song, Hongjun An, Jiangan Chen, Xuanchen Yan, Huan Song, Jiawei Shao, Xuelong Li

2603.21636 2026-03-23
AI LLM

EnterpriseLab: A Full-Stack Platform for developing and deploying agents in Enterprises

Deploying AI agents in enterprise environments requires balancing capability with data sovereignty and cost constraints. While small language models offer privacy-preserving alternatives to frontie...

Ankush Agarwal, Harsh Vishwakarma, Suraj Nagaje, Chaitanya Devaguptapu

2603.21630 2026-03-23
TESTING

Dual-level Adaptation for Multi-Object Tracking: Building Test-Time Calibration from Experience and Intuition

Multiple Object Tracking (MOT) has long been a fundamental task in computer vision, with broad applications in various real-world scenarios. However, due to distribution shifts in appearance, motio...

Wen Guo, Pengfei Zhao, Zongmeng Wang, Yufan Hu, Junyu Gao

2603.21629 2026-03-23
AI LLM

Efficient Zero-Shot AI-Generated Image Detection

The rapid progress of text-to-image models has made AI-generated images increasingly realistic, posing significant challenges for accurate detection of generated content. While training-based detec...

Ryosuke Sonoda, Ramya Srinivasan

2603.21619 2026-03-23
TESTING

4DGS360: 360° Gaussian Reconstruction of Dynamic Objects from a Single Video

We introduce 4DGS360, a diffusion-free framework for 360$^{\circ}$ dynamic object reconstruction from casual monocular video. Existing methods often fail to reconstruct consistent 360$^{\circ}$ geo...

Jae Won Jang, Yeonjin Chang, Wonsik Shin, Juhwan Cho, Nojun Kwak

2603.21618 2026-03-23
AI LLM

INTRYGUE: Induction-Aware Entropy Gating for Reliable RAG Uncertainty Estimation

While retrieval-augmented generation (RAG) significantly improves the factual reliability of LLMs, it does not eliminate hallucinations, so robust uncertainty quantification (UQ) remains essential....

Alexandra Bazarova, Andrei Volodichev, Daria Kotova, Alexey Zaytsev

2603.21607 2026-03-23
AI LLM

Riemannian Geometry Speaks Louder Than Words: From Graph Foundation Model to Next-Generation Graph Intelligence

Graphs provide a natural description of the complex relationships among objects, and play a pivotal role in communications, transportation, social computing, the life sciences, etc. Currently, ther...

Philip S. Yu, Li Sun

2603.21601 2026-03-23
TESTING

Conditional Wasserstein GAN for Simulating Neutrino Event Summaries using Incident Energy of Electron Neutrinos

Event simulation for electron neutrino interactions plays a foundational role in precision measurements in particle physics experiments, yet the computational demand of traditional Monte Carlo meth...

Dipthi S., Kalyani Desikan

2603.21599 2026-03-23
AI LLM

A Multidisciplinary AI Board for Multimodal Dementia Characterization and Risk Assessment

Modern clinical practice increasingly depends on reasoning over heterogeneous, evolving, and incomplete patient data. Although recent advances in multimodal foundation models have improved performa...

Sheng Liu, Long Chen, Zeyun Zhao, Qinglin Gou, Qingyue Wei, Arjun Masurkar, Kevin M. Spiegler, Ph...

2603.21597 2026-03-23
AI LLM

Overview of TREC 2025 Biomedical Generative Retrieval (BioGen) Track

Recent advances in large language models (LLMs) have made significant progress across multiple biomedical tasks, including biomedical question answering, lay-language summarization of the biomedica...

Deepak Gupta, Dina Demner-Fushman, William Hersh, Steven Bedrick, Kirk Roberts

2603.21582 2026-03-23
TESTING

Improved cycling stability and lithium utilization in trilayer Al-LLZO revealed by Electrochemical cycling performance

Garnet-type Li$_{6.25}$Al$_{0.25}$La$_3$Zr$_2$O$_{12}$ (Al-LLZO) solid electrolytes are promising for all-solid-state batteries but are limited by interfacial resistance. In this work, dense and gr...

Naisargi Kanabar, Seiichiro Higashiya, Haralabos Efstathiadis

2603.21578 2026-03-23
AI LLM

Mind over Space: Can Multimodal Large Language Models Mentally Navigate?

Despite the widespread adoption of MLLMs in embodied agents, their capabilities remain largely confined to reactive planning from immediate observations, consistently failing in spatial reasoning a...

Qihui Zhu, Shouwei Ruan, Xiao Yang, Hao Jiang, Yao Huang, Shiji Zhao, Hanwei Fan, Hang Su, Xingxi...

2603.21577 2026-03-23
AI LLM

PRISM: Breaking the O(n) Memory Wall in Long-Context LLM Inference via O(1) Photonic Block Selection

Long-context LLM inference is bottlenecked not by compute but by the O(n) memory bandwidth cost of scanning the KV cache at every decode step -- a wall that no amount of arithmetic scaling can brea...

Hyoseok Park, Yeonsang Park

2603.21576 2026-03-23