Research

Papers

Research papers from arXiv and related sources

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

Coherent Human-Scene Reconstruction from Multi-Person Multi-View Video in a Single Pass

Recent advances in 3D foundation models have led to growing interest in reconstructing humans and their surrounding environments. However, most existing approaches focus on monocular inputs, and ex...

Sangmin Kim, Minhyuk Hwang, Geonho Cha, Dongyoon Wee, Jaesik Park

2603.12789 2026-03-13
AI LLM

The RIGID Framework: Research-Integrated, Generative AI-Mediated Instructional Design

Instructional Design (ID) often faces challenges in incorporating research-based knowledge and pedagogical best practices. Although educational researchers and government agencies emphasize groundi...

Yerin Kwak, Zachary A. Pardos

2603.12781 2026-03-13
TESTING

Functional CLT for general sample covariance matrices

This paper studies the central limit theorems (CLTs) for linear spectral statistics (LSSs) of general sample covariance matrices, when the test functions belong to $C^3$, the class of functions wit...

Jian Cui, Zhijun Liu, Jiang Hu, Zhidong Bai

2603.12780 2026-03-13
AI LLM

SectEval: Evaluating the Latent Sectarian Preferences of Large Language Models

As Large Language Models (LLMs) becomes a popular source for religious knowledge, it is important to know if it treats different groups fairly. This study is the first to measure how LLMs handle th...

Aditya Maheshwari, Amit Gajkeshwar, Kaushal Sharma, Vivek Patel

2603.12768 2026-03-13
TESTING

FC-Track: Overlap-Aware Post-Association Correction for Online Multi-Object Tracking

Reliable multi-object tracking (MOT) is essential for robotic systems operating in complex and dynamic environments. Despite recent advances in detection and association, online MOT methods remain ...

Cheng Ju, Zejing Zhao, Akio Namiki

2603.12758 2026-03-13
TESTING

Chemical Properties and Sagittarius-induced Dynamical Perturbations of the GD-1 Stream

In this study, we investigate the chemical properties of the GD-1 stream using cross-matched, data-driven elemental abundances. The results reveal no clear $α$-knee in the [Mg/Fe]-[Fe/H] plane, and...

Haoyang Liu, Cuihua Du

2603.12757 2026-03-13
AI LLM

AI Model Modulation with Logits Redistribution

Large-scale models are typically adapted to meet the diverse requirements of model owners and users. However, maintaining multiple specialized versions of the model is inefficient. In response, we ...

Zihan Wang, Zhongkui Ma, Xinguo Feng, Zhiyang Mei, Ethan Ma, Derui Wang, Minhui Xue, Guangdong Bai

2603.12755 2026-03-13
TESTING

Balancing the privacy-utility trade-off: How to draw reliable conclusions from private data

Absolute anonymization, conceived as an irreversible transformation that prevents re-identification and sensitive value disclosure, has proven to be a broken promise. Consequently, modern data prot...

Raphaël de Fondeville

2603.12753 2026-03-13
AI LLM

Taming the Long Tail: Efficient Item-wise Sharpness-Aware Minimization for LLM-based Recommender Systems

Large Language Model-based Recommender Systems (LRSs) have recently emerged as a new paradigm in sequential recommendation by directly adopting LLMs as backbones. While LRSs demonstrate strong know...

Jiaming Zhang, Yuyuan Li, Xiaohua Feng, Li Zhang, Longfei Li, Jun Zhou, Chaochao Chen

2603.12752 2026-03-13
TESTING

Bolometric corrections of stellar oscillation mode amplitudes as observed by the PLATO mission. I. Planck-spectrum estimates

We derive bolometric correction functions for oscillation mode amplitudes observed by the different cameras of the ESA PLATO mission. Such corrections between bolometric (full light) and mission in...

Mikkel N. Lund, Jérôme Ballot, William J. Chaplin

2603.12750 2026-03-13
TESTING

SLICE: Semantic Latent Injection via Compartmentalized Embedding for Image Watermarking

Watermarking the initial noise of diffusion models has emerged as a promising approach for image provenance, but content-independent noise patterns can be forged via inversion and regeneration atta...

Zheng Gao, Yifan Yang, Xiaoyu Li, Xiaoyan Feng, Haoran Fan, Yang Song, Jiaojiao Jiang

2603.12749 2026-03-13
AI LLM

TaoBench: Do Automated Theorem Prover LLMs Generalize Beyond MathLib?

Automated theorem proving (ATP) benchmarks largely consist of problems formalized in MathLib, so current ATP training and evaluation are heavily biased toward MathLib's definitional framework. Howe...

Alexander K Taylor, Junyi Zhang, Ethan Ji, Vigyan Sahai, Haikang Deng, Yuanzhou Chen, Yifan Yuan,...

2603.12744 2026-03-13
AI LLM

What You Prompt is What You Get: Increasing Transparency of Prompting Using Prompt Cards

The rapid advancement and impressive capabilities of large language models (LLMs) have given rise to the field of prompt engineering, the practice of crafting inputs to guide LLMs toward high-quali...

Amandine M. Caut, Beimnet Zenebe, Amy Rouillard, David J. T. Sumpter

2603.12741 2026-03-13
AI LLM

ToolTree: Efficient LLM Agent Tool Planning via Dual-Feedback Monte Carlo Tree Search and Bidirectional Pruning

Large Language Model (LLM) agents are increasingly applied to complex, multi-step tasks that require interaction with diverse external tools across various domains. However, current LLM agent tool ...

Shuo Yang, Soyeon Caren Han, Yihao Ding, Shuhe Wang, Eduard Hoy

2603.12740 2026-03-13
TESTING

Purely Baryonic Weak Decays of Heavy Baryons in Skyrme Model

Purely baryonic weak decays of heavy baryons are investigated within the framework of the Skyrme model. These decays belong to a new class of unobserved decay channels, which would help us to test ...

Chao-Qiang Geng, Chao Han

2603.12735 2026-03-13
TESTING

On Using Machine Learning to Early Detect Catastrophic Failures in Marine Diesel Engines

Catastrophic failures of marine engines imply severe loss of functionality and destroy or damage the systems irreversibly. Being sudden and often unpredictable events, they pose a severe threat to ...

Francesco Maione, Paolo Lino, Giuseppe Giannino, Guido Maione

2603.12733 2026-03-13
TESTING

Two-photon dual-comb LiDAR imaging

Conventional LiDAR uses time-of-flight data from laser pulses scanned across a scene to provide accurate multi-meter-scale three-dimensional models at cm precision, limited by the tens-of-picosecon...

Alexander J. M. Nelmes, Simon Fletcher, Andrew Longstaff, Jake M. Charsley, Hollie Wright, Derryc...

2603.12729 2026-03-13
TESTING

SciDesignBench: Benchmarking and Improving Language Models for Scientific Inverse Design

Many of the most important problems in science and engineering are inverse problems: given a desired outcome, find a design that achieves it. Evaluating whether a candidate meets the spec is often ...

David van Dijk, Ivan Vrkic

2603.12724 2026-03-13
AI LLM

Altered Thoughts, Altered Actions: Probing Chain-of-Thought Vulnerabilities in VLA Robotic Manipulation

Recent Vision-Language-Action (VLA) models increasingly adopt chain-of-thought (CoT) reasoning, generating a natural-language plan before decoding motor commands. This internal text channel between...

Tuan Duong Trinh, Naveed Akhtar, Basim Azam

2603.12717 2026-03-13
TESTING

Deep Learning Based Estimation of Blood Glucose Levels from Multidirectional Scleral Blood Vessel Imaging

Regular monitoring of glycemic status is essential for diabetes management, yet conventional blood-based testing can be burdensome for frequent assessment. The sclera contains superficial microvasc...

Muhammad Ahmed Khan, Manqiang Peng, Ding Lin, Saif Ur Rehman Khan

2603.12715 2026-03-13