Research

Papers

Research papers from arXiv and related sources

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

COLD-Steer: Steering Large Language Models via In-Context One-step Learning Dynamics

Activation steering methods enable inference-time control of large language model (LLM) behavior without retraining, but current approaches face a fundamental trade-off: sample-efficient methods su...

Kartik Sharma, Rakshit S. Trivedi

2603.06495 2026-03-06
AI LLM

NOBLE: Accelerating Transformers with Nonlinear Low-Rank Branches

We introduce NOBLE (Nonlinear lOw-rank Branch for Linear Enhancement), an architectural augmentation that adds nonlinear low-rank branches to transformer linear layers. Unlike LoRA and other parame...

Ethan Smith

2603.06492 2026-03-06
TESTING

PONTE: Personalized Orchestration for Natural Language Trustworthy Explanations

Explainable Artificial Intelligence (XAI) seeks to enhance the transparency and accountability of machine learning systems, yet most methods follow a one-size-fits-all paradigm that neglects user d...

Vittoria Vineis, Matteo Silvestri, Lorenzo Antonelli, Filippo Betello, Gabriele Tolomei

2603.06485 2026-03-06
TESTING

Match4Annotate: Propagating Sparse Video Annotations via Implicit Neural Feature Matching

Acquiring per-frame video annotations remains a primary bottleneck for deploying computer vision in specialized domains such as medical imaging, where expert labeling is slow and costly. Label prop...

Zhuorui Zhang, Roger Pallarès-López, Praneeth Namburi, Brian W. Anthony

2603.06471 2026-03-06
TESTING

Unbiased Bayesian Inference of Peculiar Motions of Galaxies from Type Ia Supernovae Observations

The peculiar motions of galaxies are powerful cosmological probes that trace the growth of structures and the distribution of matter in the universe, providing a means to investigate the nature of ...

Ujjwal Upadhyay, Tarun Deep Saini, Shiv K. Sethi

2603.06469 2026-03-06
TESTING

Completeness for Prime-Dimensional Phase-Affine Circuits

Equational reasoning about circuits is central in quantum software for validation, optimisation, and verification. For qubits, the CNOT-dihedral fragment supports efficient rewriting via phase poly...

Colin Blake

2603.06466 2026-03-06
AI LLM

Do Foundation Models Know Geometry? Probing Frozen Features for Continuous Physical Measurement

Vision-language models encode continuous geometry that their text pathway fails to express: a 6,000-parameter linear probe extracts hand joint angles at 6.1 degrees MAE from frozen features, while ...

Yakov Pyotr Shkolnikov

2603.06459 2026-03-06
AI LLM

Prosodic Boundary-Aware Streaming Generation for LLM-Based TTS with Streaming Text Input

Streaming TTS that receives streaming text is essential for interactive systems, yet this scheme faces two major challenges: unnatural prosody due to missing lookahead and long-form collapse due to...

Changsong Liu, Tianrui Wang, Ye Ni, Yizhou Peng, Eng Siong Chng

2603.06444 2026-03-06
AI LLM

Abductive Reasoning with Syllogistic Forms in Large Language Models

Research in AI using Large-Language Models (LLMs) is rapidly evolving, and the comparison of their performance with human reasoning has become a key concern. Prior studies have indicated that LLMs ...

Hirohiko Abe, Risako Ando, Takanobu Morishita Kentaro Ozeki, Koji Mineshima, Mitsuhiro Okada

2603.06428 2026-03-06
AI LLM

From Prompting to Preference Optimization: A Comparative Study of LLM-based Automated Essay Scoring

Large language models (LLMs) have recently reshaped Automated Essay Scoring (AES), yet prior studies typically examine individual techniques in isolation, limiting understanding of their relative m...

Minh Hoang Nguyen, Vu Hoang Pham, Xuan Thanh Huynh, Phuc Hong Mai, Vinh The Nguyen, Quang Nhut Hu...

2603.06424 2026-03-06
AI LLM

Before You Hand Over the Wheel: Evaluating LLMs for Security Incident Analysis

Security incident analysis (SIA) poses a major challenge for security operations centers, which must manage overwhelming alert volumes, large and diverse data sources, complex toolchains, and limit...

Sourov Jajodia, Madeena Sultana, Suryadipta Majumdar, Adrian Taylor, Grant Vandenberghe

2603.06422 2026-03-06
AI LLM

Evaluation of Deontic Conditional Reasoning in Large Language Models: The Case of Wason's Selection Task

As large language models (LLMs) advance in linguistic competence, their reasoning abilities are gaining increasing attention. In humans, reasoning often performs well in domain specific settings, p...

Hirohiko Abe, Kentaro Ozeki, Risako Ando, Takanobu Morishita, Koji Mineshima, Mitsuhiro Okada

2603.06416 2026-03-06
AI LLM

Physical Simulator In-the-Loop Video Generation

Recent advances in diffusion-based video generation have achieved remarkable visual realism but still struggle to obey basic physical laws such as gravity, inertia, and collision. Generated objects...

Lin Geng Foo, Mark He Huang, Alexandros Lattas, Stylianos Moschoglou, Thabo Beeler, Christian The...

2603.06408 2026-03-06
AI LLM

Efficient, Property-Aligned Fan-Out Retrieval via RL-Compiled Diffusion

Many modern retrieval problems are set-valued: given a broad intent, the system must return a collection of results that optimizes higher-order properties (e.g., diversity, coverage, complementar...

Pengcheng Jiang, Judith Yue Li, Moonkyung Ryu, R. Lily Hu, Kun Su, Zhong Yi Wan, Liam Hebert, Hao...

2603.06397 2026-03-06
AI LLM

Talk Freely, Execute Strictly: Schema-Gated Agentic AI for Flexible and Reproducible Scientific Workflows

Large language models (LLMs) can now translate a researcher's plain-language goal into executable computation, yet scientific workflows demand determinism, provenance, and governance that are diffi...

Joel Strickland, Arjun Vijeta, Chris Moores, Oliwia Bodek, Bogdan Nenchev, Thomas Whitehead, Char...

2603.06394 2026-03-06
TESTING

CHMv2: Improvements in Global Canopy Height Mapping using DINOv3

Accurate canopy height information is essential for quantifying forest carbon, monitoring restoration and degradation, and assessing habitat structure, yet high-fidelity measurements from airborne ...

John Brandt, Seungeun Yi, Jamie Tolan, Xinyuan Li, Peter Potapov, Jessica Ertel, Justine Spore, H...

2603.06382 2026-03-06
AI LLM

Kinetic-based regularization: Learning spatial derivatives and PDE applications

Accurate estimation of spatial derivatives from discrete and noisy data is central to scientific machine learning and numerical solutions of PDEs. We extend kinetic-based regularization (KBR), a lo...

Abhisek Ganguly, Santosh Ansumali, Sauro Succi

2603.06380 2026-03-06
TESTING

A Scheduler for the Active Volume Architecture

We improve the accuracy of Active Volume resource estimates by explicitly scheduling when Active Volume blocks execute. We present software that uses a greedy strategy to assign each logical qubit ...

Sam Heavey, Athena Caesura

2603.06376 2026-03-06
TESTING

Recent GasPM advances: photon-feedback mitigation and LaB$_{6}$ photocathode studies

We report recent developments and tests with beams and cosmic rays of the gaseous photomultiplier (GasPM). The GasPM is a photosensor that combines a photocathode with the avalanche-multiplication ...

Simone Garnero, Kenji Inami, Kodai Matsuoka, Ryogo Okubo, Koichi Ueda

2603.06375 2026-03-06
AI LLM

Doctor or Patient? Synergizing Diarization and ASR for Code-Switched Hinglish Medical Conditions Extraction

Extracting patient medical conditions from code-switched clinical spoken dialogues is challenging due to rapid turn-taking and highly overlapped speech. We present a robust system evaluated on the ...

Séverin Baroudi, Yanis Labrak, Shashi Kumar, Joonas Kalda, Sergio Burdisso, Pawel Cyrta, Juan Ign...

2603.06373 2026-03-06