Research

Papers

Research papers from arXiv and related sources

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

Dialect-Agnostic SQL Parsing via LLM-Based Segmentation

SQL is a widely adopted language for querying data, which has led to the development of various SQL analysis and rewriting tools. However, due to the diversity of SQL dialects, such tools often fai...

Junwen An, Kabilan Mahathevan, Manuel Rigger

2603.16155 2026-03-17
TESTING

Mechanical anisotropy of 3D-printed digital materials at large strains

3D-printed digital materials whose mechanical behavior travels between those from thermoplastic to rubbery polymers have become increasingly important. However, their mechanical functionalities hav...

Seunghwan Lee, Gisoo Lee, Seounghee Yun, Sumin Lee, Jeonyoon Lee, Hansohl Cho

2603.16149 2026-03-17
TESTING

Noisy Data is Destructive to Reinforcement Learning with Verifiable Rewards

Reinforcement learning with verifiable rewards (RLVR) has driven recent capability advances of large language models across various domains. Recent studies suggest that improved RLVR algorithms all...

Yuxuan Zhu, Daniel Kang

2603.16140 2026-03-17
TESTING

SIA: A Synthesize-Inject-Align Framework for Knowledge-Grounded and Secure E-commerce Search LLMs with Industrial Deployment

Large language models offer transformative potential for e-commerce search by enabling intent-aware recommendations. However, their industrial deployment is hindered by two critical challenges: (1)...

Zhouwei Zhai, Mengxiang Chen, Anmeng Zhang

2603.16137 2026-03-17
TESTING

Language Models Don't Know What You Want: Evaluating Personalization in Deep Research Needs Real Users

Deep Research (DR) tools (e.g. OpenAI DR) help researchers cope with ballooning publishing counts. Such tools can synthesize scientific papers to answer researchers' queries, but lack understanding...

Nishant Balepur, Malachi Hamada, Varsha Kishore, Sergey Feldman, Amanpreet Singh, Pao Siangliulue...

2603.16120 2026-03-17
TESTING

CounterRefine: Answer-Conditioned Counterevidence Retrieval for Inference-Time Knowledge Repair in Factual Question Answering

In factual question answering, many errors are not failures of access but failures of commitment: the system retrieves relevant evidence, yet still settles on the wrong answer. We present CounterRe...

Tianyi Huang, Ying Kai Deng

2603.16091 2026-03-17
TESTING

Towards the Vision-Sound-Language-Action Paradigm: The HEAR Framework for Sound-Centric Manipulation

While recent Vision-Language-Action (VLA) models have begun to incorporate audio, they typically treat sound as static pre-execution prompts or focus exclusively on human speech. This leaves a sign...

Chang Nie, Tianchen Deng, Guangming Wang, Zhe Liu, Hesheng Wang

2603.16086 2026-03-17
TESTING

SEAHateCheck: Functional Tests for Detecting Hate Speech in Low-Resource Languages of Southeast Asia

Hate speech detection relies heavily on linguistic resources, which are primarily available in high-resource languages such as English and Chinese, creating barriers for researchers and platforms d...

Ri Chi Ng, Aditi Kumaresan, Yujia Hu, Roy Ka-Wei Lee

2603.16070 2026-03-17
TESTING

Large Reward Models: Generalizable Online Robot Reward Generation with Vision-Language Models

Reinforcement Learning (RL) has shown great potential in refining robotic manipulation policies, yet its efficacy remains strongly bottlenecked by the difficulty of designing generalizable reward f...

Yanru Wu, Weiduo Yuan, Ang Qi, Vitor Guizilini, Jiageng Mao, Yue Wang

2603.16065 2026-03-17
TESTING

A Context Alignment Pre-processor for Enhancing the Coherence of Human-LLM Dialog

Large language models (LLMs) have made remarkable progress in generating fluent text, but they still face a critical challenge of contextual misalignment in long-term and dynamic dialogue. When hum...

Ding Wei

2603.16052 2026-03-17
TESTING

An immersed peridynamics method for fluid-driven damage and failure of anisotropic materials

The immersed peridynamics (IPD) method is a fluid-structure interaction (FSI) model to simulate fluid-driven material damage and failure of an immersed structure, in which a peridynamic (PD) consti...

Keon Ho Kim, Boyce E. Griffith

2603.16046 2026-03-17
TESTING

Power Analysis for Prediction-Powered Inference

Modern studies increasingly leverage outcomes predicted by machine learning and artificial intelligence (AI/ML) models, and recent work, such as prediction-powered inference (PPI), has developed va...

Yiqun T. Chen, Moran Guo, Shengy Li

2603.16041 2026-03-17
TESTING

Compact Optical Single-axis Joint Torque Sensor Using Redundant Photo-Reflectors and Quadratic-Programming Calibration

This study proposes a non-contact photo-reflector-based joint torque sensor for precise joint-level torque control and safe physical interaction. Current-sensor-based torque estimation in many coll...

Hyun-Bin Kim, Byeong-Il Ham, Kyung-Soo Kim

2603.16040 2026-03-17
TESTING

Identification Verification for Structural Vector Autoregressions with Sparse Heterogeneous Markov Switching Heteroskedasticity

We propose a structural vector autoregressive model with a new and flexible specification of the volatility process which we call Sparse Heterogeneous Markov-Switching Heteroskedasticity. In this m...

Fei Shang, Tomasz Woźniak

2603.16035 2026-03-17
TESTING

Geometry-Aligned LLM Fine-Tuning for Sequential Narrow-Opening Planning

We study rigid-body motion planning through multiple sequential narrow openings, which requires long-horizon geometric reasoning because the configuration used to traverse an early opening constrai...

Al Jaber Mahmud, Xuan Wang

2603.16028 2026-03-17
TESTING

Ringdown bounds and spectral density limits from GWTC-3

We establish the first observational bounds on causal nonlocal extensions of gravity characterized by retarded Stieltjes-type kernels with positive spectral density rho(mu) >= 0, using two compleme...

Christian Balfagon

2603.16026 2026-03-17
TESTING

Making Software Metrics Useful

Most engineers use measurements to make decisions. However, measurements are rarely used for decisions about constructing software products. While many approaches to measuring attributes of softwar...

Ewan Tempero, Paul Ralph

2603.16012 2026-03-16
TESTING

A minimal fractional deformation of Newtonian gravity

We consider a minimal fractional deformation of Newtonian gravity characterized by a single parameter $α$. In the limit $α\to 1$, the theory reduces to standard Newtonian gravity. Previous works sh...

S. M. M. Rasouli

2603.16009 2026-03-16
TESTING

Emulation of SPHEREx Galaxy Power Spectra I: Neural Network Details and Optimization

We present neural networks to generate redshift-space galaxy power spectrum multipoles for multiple tracer and redshift bins simultaneously given a set of input cosmology and galaxy bias parameters...

Joseph Adamo, Grace Gibbins, Anne Moore, Tim Eifler

2603.16003 2026-03-16
TESTING

NLP Occupational Emergence Analysis: How Occupations Form and Evolve in Real Time -- A Zero-Assumption Method Demonstrated on AI in the US Technology Workforce, 2022-2026

Occupations form and evolve faster than classification systems can track. We propose that a genuine occupation is a self-reinforcing structure (a bipartite co-attractor) in which a shared professio...

David Nordfors

2603.15998 2026-03-16