Research

Papers

Research papers from arXiv and related sources

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

Using Global Gravitational Potential Weighted Correlation Function to Constrain Modified Gravity Models

We propose a new marked two-point correlation function weighted by the global gravitational potential as a probe for testing gravity models. Using the LCDM model based on general relativity (GR) as...

Yizhao Yang, Yu Yu, Pengjie Zhang

2603.22138 2026-03-23
AI LLM

The Semantic Ladder: A Framework for Progressive Formalization of Natural Language Content for Knowledge Graphs and AI Systems

Semantic data and knowledge infrastructures must reconcile two fundamentally different forms of representation: natural language, in which most knowledge is created and communicated, and formal sem...

Lars Vogt

2603.22136 2026-03-23
AI LLM

Navigational Thinking as an Emerging Paradigm of Computer Science in the Age of Generative AI

Generative AI systems produce meaning with a quality indistinguishable from - and occasionally surpassing - human performance, yet the epistemic mechanism through which this occurs remains poorly u...

Ilya Levin

2603.22133 2026-03-23
AI LLM

DQN Based Joint UAV Trajectory and Association Planning in NTN Assisted Networks

Advanced Air Mobility (AAM) has emerged as a key pillar of next-generation transportation systems, encompassing a wide range of uncrewed aerial vehicle (UAV) applications. To enable AAM, maintainin...

Afsoon Alidadi Shamsabadi, Cosmas Mwaba, Thomas Nugent, Jie Gao, Pablo Madoery, Halim Yanikomerog...

2603.22127 2026-03-23
TESTING

ROBOGATE: Adaptive Failure Discovery for Safe Robot Policy Deployment via Two-Stage Boundary-Focused Sampling

Deploying learned robot manipulation policies in industrial settings requires rigorous pre-deployment validation, yet exhaustive testing across high-dimensional parameter spaces is intractable. We ...

Byungjin Kim

2603.22126 2026-03-23
AI LLM

Mamba-VMR: Multimodal Query Augmentation via Generated Videos for Precise Temporal Grounding

Text-driven video moment retrieval (VMR) remains challenging due to limited capture of hidden temporal dynamics in untrimmed videos, leading to imprecise grounding in long sequences. Traditional me...

Yunzhuo Sun, Xinyue Liu, Yanyang Li, Nanding Wu, Yifang Xu, Linlin Zong, Xianchao Zhang, Wenxin L...

2603.22121 2026-03-23
AI LLM

Programming Manufacturing Robots with Imperfect AI: LLMs as Tuning Experts for FDM Print Configuration Selection

We use fused deposition modeling (FDM) 3D printing as a case study of how manufacturing robots can use imperfect AI to acquire process expertise. In FDM, print configuration strongly affects output...

Ekta U. Samani, Christopher G. Atkeson

2603.22118 2026-03-23
AI LLM

On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation

Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning capabilities of large language models. While existing analyses identify that RLVR-induced changes are ...

Kexin Huang, Haoming Meng, Junkang Wu, Jinda Lu, Chiyu Ma, Ziqian Chen, Xue Wang, Bolin Ding, Jia...

2603.22117 2026-03-23
AI LLM

Lemma Discovery in Agentic Program Verification

Deductive verification provides strong correctness guarantees for code by extracting verification conditions (VCs) and writing formal proofs for them. The expertise-intensive task of VC proving is ...

Huan Zhao, Haoxin Tu, Zhengyao Liu, Martin Rinard, Abhik Roychoudhury

2603.22114 2026-03-23
AI LLM

From Technical Debt to Cognitive and Intent Debt: Rethinking Software Health in the Age of AI

Over time, the shared understanding that makes a software system safe to change quietly erodes. This gradual loss of understanding across a team increases cognitive debt, while the loss of captured...

Margaret-Anne Storey

2603.22106 2026-03-23
AI LLM

Multiperspectivity as a Resource for Narrative Similarity Prediction

Predicting narrative similarity can be understood as an inherently interpretive task: different, equally valid readings of the same text can produce divergent interpretations and thus different sim...

Max Upravitelev, Veronika Solopova, Jing Yang, Charlott Jakob, Premtim Sahitaj, Ariana Sahitaj, V...

2603.22103 2026-03-23
TESTING

Overcoming sampling limitations using machine-learned interatomic potentials: the case of water-in-salt electrolytes

Machine-learned interatomic potentials hold the promise to enable the modeling of highly concentrated liquids over meaningful timescales, far from reach for current ab initio electronic structure m...

Luca Brugnoli, Mathieu Salanne, A. Marco Saitta, Alessandra Serva, Arthur France-Lanord

2603.22099 2026-03-23
AI LLM

GSEM: Graph-based Self-Evolving Memory for Experience Augmented Clinical Reasoning

Clinical decision-making agents can benefit from reusing prior decision experience. However, many memory-augmented methods store experiences as independent records without explicit relational struc...

Xiao Han, Yuzheng Fan, Sendong Zhao, Haochun Wang, Bing Qin

2603.22096 2026-03-23
TESTING

Bounded Structural Model Finding with Symbolic Data Constraints

Bounded model finding is a key technique for validating software designs, usually obtained by translating high-level specifications into SAT/SMT problems. Although effective, such translations intr...

Artur Boronat

2603.22093 2026-03-23
AI LLM

P-Flow: Prompting Visual Effects Generation

Recent advancements in video generation models have significantly improved their ability to follow text prompts. However, the customization of dynamic visual effects, defined as temporally evolving...

Rui Zhao, Mike Zheng Shou

2603.22091 2026-03-23
AI LLM

A Context Engineering Framework for Improving Enterprise AI Agents based on Digital-Twin MDP

Despite rapid progress in AI agents for enterprise automation and decision-making, their real-world deployment and further performance gains remain constrained by limited data quality and quantity,...

Xi Yang, Aurelie Lozano, Naoki Abe, Bhavya, Saurabh Jha, Noah Zheutlin, Rohan R. Arora, Yu Deng,...

2603.22083 2026-03-23
AI LLM

Adapting Point Cloud Analysis via Multimodal Bayesian Distribution Learning

Multimodal 3D vision-language models show strong generalization across diverse 3D tasks, but their performance still degrades notably under domain shifts. This has motivated recent studies on test-...

Xingyu Zhu, Liang Yi, Shuo Wang, Wenbo Zhu, Yonglinag Wu, Beier Zhu, Hanwang Zhang

2603.22070 2026-03-23
AI LLM

On the Failure of Topic-Matched Contrast Baselines in Multi-Directional Refusal Abliteration

Inasmuch as the removal of refusal behavior from instruction-tuned language models by directional abliteration requires the extraction of refusal-mediating directions from the residual stream activ...

Valentin Petrov

2603.22061 2026-03-23
AI LLM

SpatialBoost: Enhancing Visual Representation through Language-Guided Reasoning

Despite the remarkable success of large-scale pre-trained image representation models (i.e., vision encoders) across various vision tasks, they are predominantly trained on 2D image data and theref...

Byungwoo Jeon, Dongyoung Kim, Huiwon Jang, Insoo Kim, Jinwoo Shin

2603.22057 2026-03-23
AI LLM

Dual-Space Knowledge Distillation with Key-Query Matching for Large Language Models with Vocabulary Mismatch

Large language models (LLMs) achieve state-of-the-art (SOTA) performance across language tasks, but are costly to deploy due to their size and resource demands. Knowledge Distillation (KD) addresse...

Stella Eva Tsiapali, Cong-Thanh Do, Kate Knill

2603.22056 2026-03-23