Research

Papers

Research papers from arXiv and related sources

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

Incidental Reverberations: Poetic Similarities in AI Art

Contemporary AI art's diverse and widely recognized repertoire features numerous artworks that share conceptual, thematic, narrative, procedural, or presentational properties with other artworks ac...

Dejan Grba

2602.19769 2026-02-23
AI LLM

Hexagon-MLIR: An AI Compilation Stack For Qualcomm's Neural Processing Units (NPUs)

In this paper, we present Hexagon-MLIR,an open-source compilation stack that targets Qualcomm Hexagon Neural Processing Unit (NPU) and provides unified support for lowering Triton kernels and PyTor...

Mohammed Javed Absar, Muthu Baskaran, Abhikrant Sharma, Abhilash Bhandari, Ankit Aggarwal, Arun R...

2602.19762 2026-02-23
AI LLM

AI-Powered Conflict Management in Open RAN: Detection, Classification, and Mitigation

Open Radio Access Network (RAN) was designed with native Artificial Intelligence (AI) as a core pillar, enabling AI- driven xApps and rApps to dynamically optimize network performance. However, the...

Abdul Wadud, Nima Afraz, Fatemeh Golpayegani

2602.19758 2026-02-23
AI LLM

Deep Else: A Critical Framework for AI Art

From a small community of pioneering artists who experimented with artificial intelligence (AI) in the 1970s, AI art has expanded, gained visibility, and attained socio-cultural relevance since the...

Dejan Grba

2602.19754 2026-02-23
AI LLM

NILE: Formalizing Natural-Language Descriptions of Formal Languages

This paper explores how natural-language descriptions of formal languages can be compared to their formal representations and how semantic differences can be explained. This is motivated from educa...

Tristan Kneisel, Marko Schmellenkamp, Fabian Vehlken, Thomas Zeume

2602.19743 2026-02-23
AI LLM

Carbon-Aware Governance Gates: An Architecture for Sustainable GenAI Development

The rapid adoption of Generative AI (GenAI) in the software development life cycle (SDLC) increases computational demand, which can raise the carbon footprint of development activities. At the same...

Mateen A. Abbasi, Tommi J. Mikkonen, Petri J. Ihantola, Muhammad Waseem, Pekka Abrahamsson, Niko ...

2602.19718 2026-02-23
AI LLM

All Cities are Equal: A Unified Human Mobility Generation Model Enabled by LLMs

Synthetic human mobility generation is gaining traction as an ethical and practical approach to supporting the data needs of intelligent urban systems. Existing methods perform well primarily in da...

Bo Liu, Tong Li, Zhu Xiao, Ruihui Li, Geyong Min, Zhuo Tang, Kenli Li

2602.19694 2026-02-23
AI LLM

"The explanation makes sense": An Empirical Study on LLM Performance in News Classification and its Influence on Judgment in Human-AI Collaborative Annotation

The spread of media bias is a significant concern as political discourse shapes beliefs and opinions. Addressing this challenge computationally requires improved methods for interpreting news. Whil...

Qile Wang, Prerana Khatiwada, Avinash Chouhan, Ashrey Mahesh, Joy Mwaria, Duy Duc Tran, Kenneth E...

2602.19690 2026-02-23
AI LLM

Beyond the Binary: A nuanced path for open-weight advanced AI

Open-weight advanced AI models -- systems whose parameters are freely available for download and adaptation -- are reshaping the global AI landscape. As these models rapidly close the performance g...

Bengüsu Özcan, Alex Petropoulos, Max Reddel

2602.19682 2026-02-23
AI LLM

SkillOrchestra: Learning to Route Agents via Skill Transfer

Compound AI systems promise capabilities beyond those of individual models, yet their success depends critically on effective orchestration. Existing routing approaches face two limitations: (1) in...

Jiayu Wang, Yifei Ming, Zixuan Ke, Shafiq Joty, Aws Albarghouthi, Frederic Sala

2602.19672 2026-02-23
AI LLM

PaReGTA: An LLM-based EHR Data Encoding Approach to Capture Temporal Information

Temporal information in structured electronic health records (EHRs) is often lost in sparse one-hot or count-based representations, while sequence models can be costly and data-hungry. We propose P...

Kihyuk Yoon, Lingchao Mao, Catherine Chong, Todd J. Schwedt, Chia-Chun Chiang, Jing Li

2602.19661 2026-02-23
AI LLM

KGHaluBench: A Knowledge Graph-Based Hallucination Benchmark for Evaluating the Breadth and Depth of LLM Knowledge

Large Language Models (LLMs) possess a remarkable capacity to generate persuasive and intelligible language. However, coherence does not equate to truthfulness, as the responses often contain subtl...

Alex Robertson, Huizhi Liang, Mahbub Gani, Rohit Kumar, Srijith Rajamohan

2602.19643 2026-02-23
AI LLM

Cooperation After the Algorithm: Designing Human-AI Coexistence Beyond the Illusion of Collaboration

Generative artificial intelligence systems increasingly participate in research, law, education, media, and governance. Their fluent and adaptive outputs create an experience of collaboration. Howe...

Tatia Codreanu

2602.19629 2026-02-23
AI LLM

Nacrith: Neural Lossless Compression via Ensemble Context Modeling and High-Precision CDF Coding

We present Nacrith, a lossless compression system that combines a 135M-parameter transformer language model (SmolLM2-135M) with an ensemble of lightweight online predictors and a 32-bit arithmetic ...

Roberto Tacconelli

2602.19626 2026-02-23
AI LLM

PedaCo-Gen: Scaffolding Pedagogical Agency in Human-AI Collaborative Video Authoring

While advancements in Text-to-Video (T2V) generative AI offer a promising path toward democratizing content creation, current models are often optimized for visual fidelity rather than instructiona...

Injun Baek, Yearim Kim, Nojun Kwak

2602.19623 2026-02-23
AI LLM

Rules or Weights? Comparing User Understanding of Explainable AI Techniques with the Cognitive XAI-Adaptive Model

Rules and Weights are popular XAI techniques for explaining AI decisions. Yet, it remains unclear how to choose between them, lacking a cognitive framework to compare their interpretability. In an ...

Louth Bin Rawshan, Zhuoyu Wang, Brian Y Lim

2602.19620 2026-02-23
AI LLM

Seeing Clearly, Reasoning Confidently: Plug-and-Play Remedies for Vision Language Model Blindness

Vision language models (VLMs) have achieved remarkable success in broad visual understanding, yet they remain challenged by object-centric reasoning on rare objects due to the scarcity of such inst...

Xin Hu, Haomiao Ni, Yunbei Zhang, Jihun Hamm, Zechen Li, Zhengming Ding

2602.19615 2026-02-23
AI LLM

Workflow-Level Design Principles for Trustworthy GenAI in Automotive System Engineering

The adoption of large language models in safety-critical system engineering is constrained by trustworthiness, traceability, and alignment with established verification practices. We propose workfl...

Chih-Hong Cheng, Brian Hsuan-Cheng Liao, Adam Molin, Hasan Esen

2602.19614 2026-02-23
AI LLM

Anatomy of Unlearning: The Dual Impact of Fact Salience and Model Fine-Tuning

Machine Unlearning (MU) enables Large Language Models (LLMs) to remove unsafe or outdated information. However, existing work assumes that all facts are equally forgettable and largely ignores whet...

Borisiuk Anna, Andrey Savchenko, Alexander Panchecko, Elena Tutubalina

2602.19612 2026-02-23
AI LLM

ISO-Bench: Can Coding Agents Optimize Real-World Inference Workloads?

We introduce ISO-Bench, a benchmark for coding agents to test their capabilities on real-world inference optimization tasks. These tasks were taken from vLLM and SGLang, two of the most popular LLM...

Ayush Nangia, Shikhar Mishra, Aman Gokrani, Paras Chopra

2602.19594 2026-02-23