Research

Papers

Research papers from arXiv and related sources

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

Improving Implicit Discourse Relation Recognition with Natural Language Explanations from LLMs

Implicit Discourse Relation Recognition (IDRR) remains a challenging task due to the requirement for deep semantic understanding in the absence of explicit discourse markers. A further limitation i...

Heng Wang, Changxing Wu

2602.21763 2026-02-25
AI LLM

SAPNet++: Evolving Point-Prompted Instance Segmentation with Semantic and Spatial Awareness

Single-point annotation is increasingly prominent in visual tasks for labeling cost reduction. However, it challenges tasks requiring high precision, such as the point-prompted instance segmentatio...

Zhaoyang Wei, Xumeng Han, Xuehui Yu, Xue Yang, Guorong Li, Zhenjun Han, Jianbin Jiao

2602.21762 2026-02-25
AI LLM

Offline Reasoning for Efficient Recommendation: LLM-Empowered Persona-Profiled Item Indexing

Recent advances in large language models (LLMs) offer new opportunities for recommender systems by capturing the nuanced semantics of user interests and item characteristics through rich semantic u...

Deogyong Kim, Junseong Lee, Jeongeun Lee, Changhoe Kim, Junguel Lee, Jungseok Lee, Dongha Lee

2602.21756 2026-02-25
AI LLM

From Words to Amino Acids: Does the Curse of Depth Persist?

Protein language models (PLMs) have become widely adopted as general-purpose models, demonstrating strong performance in protein engineering and de novo design. Like large language models (LLMs), t...

Aleena Siji, Amir Mohammad Karimi Mamaghan, Ferdinand Kapl, Tobias Höppe, Emmanouil Angelis, Andr...

2602.21750 2026-02-25
AI LLM

fEDM+: A Risk-Based Fuzzy Ethical Decision Making Framework with Principle-Level Explainability and Pluralistic Validation

In a previous work, we introduced the fuzzy Ethical Decision-Making framework (fEDM), a risk-based ethical reasoning architecture grounded in fuzzy logic. The original model combined a fuzzy Ethica...

Abeer Dyoub, Francesca A. Lisi

2602.21746 2026-02-25
AI LLM

The ASIR Courage Model: A Phase-Dynamic Framework for Truth Transitions in Human and AI Systems

We introduce the ASIR (Awakened Shared Intelligence Relationship) Courage Model, a phase-dynamic framework that formalizes truth-disclosure as a state transition rather than a personality trait. Th...

Hyo Jin Kim

2602.21745 2026-02-25
AI LLM

Enhancing Multi-Modal LLMs Reasoning via Difficulty-Aware Group Normalization

Reinforcement Learning with Verifiable Rewards (RLVR) and Group Relative Policy Optimization (GRPO) have significantly advanced the reasoning capabilities of large language models. Extending these ...

Jinghan Li, Junfeng Fang, Jinda Lu, Yuan Wang, Xiaoyan Guo, Tianyu Zhang, Xiang Wang, Xiangnan He

2602.21743 2026-02-25
AI LLM

Explore-on-Graph: Incentivizing Autonomous Exploration of Large Language Models on Knowledge Graphs with Path-refined Reward Modeling

The reasoning process of Large Language Models (LLMs) is often plagued by hallucinations and missing facts in question-answering tasks. A promising solution is to ground LLMs' answers in verifiable...

Shiqi Yan, Yubo Chen, Ruiqi Zhou, Zhengxi Yao, Shuai Chen, Tianyi Zhang, Shijie Zhang, Wei Qiang ...

2602.21728 2026-02-25
AI LLM

TranX-Adapter: Bridging Artifacts and Semantics within MLLMs for Robust AI-generated Image Detection

Rapid advances in AI-generated image (AIGI) technology enable highly realistic synthesis, threatening public information integrity and security. Recent studies have demonstrated that incorporating ...

Wenbin Wang, Yuge Huang, Jianqing Xu, Yue Yu, Jiangtao Yan, Shouhong Ding, Pan Zhou, Yong Luo

2602.21716 2026-02-25
AI LLM

Two-Stage Active Distribution Network Voltage Control via LLM-RL Collaboration: A Hybrid Knowledge-Data-Driven Approach

The growing integration of distributed photovoltaics (PVs) into active distribution networks (ADNs) has exacerbated operational challenges, making it imperative to coordinate diverse equipment to m...

Xu Yang, Chenhui Lin, Xiang Ma, Dong Liu, Ran Zheng, Haotian Liu, Wenchuan Wu

2602.21715 2026-02-25
TESTING

Learning spatially adaptive sparsity level maps for arbitrary convolutional dictionaries

State-of-the-art learned reconstruction methods often rely on black-box modules that, despite their strong performance, raise questions about their interpretability and robustness. Here, we build o...

Joshua Schulz, David Schote, Christoph Kolbitsch, Kostas Papafitsoros, Andreas Kofler

2602.21707 2026-02-25
AI LLM

SurGo-R1: Benchmarking and Modeling Contextual Reasoning for Operative Zone in Surgical Video

Minimally invasive surgery has dramatically improved patient operative outcomes, yet identifying safe operative zones remains challenging in critical phases, requiring surgeons to integrate visual ...

Guanyi Qin, Xiaozhen Wang, Zhu Zhuo, Chang Han Low, Yuancan Xiao, Yibing Fu, Haofeng Liu, Kai Wan...

2602.21706 2026-02-25
TESTING

Learning Complex Physical Regimes via Coverage-oriented Uncertainty Quantification: An application to the Critical Heat Flux

A central challenge in scientific machine learning (ML) is the correct representation of physical systems governed by multi-regime behaviours. In these scenarios, standard data analysis techniques ...

Michele Cazzola, Alberto Ghione, Lucia Sargentini, Julien Nespoulous, Riccardo Finotello

2602.21701 2026-02-25
AI LLM

E-comIQ-ZH: A Human-Aligned Dataset and Benchmark for Fine-Grained Evaluation of E-commerce Posters with Chain-of-Thought

Generative AI is widely used to create commercial posters. However, rapid advances in generation have outpaced automated quality assessment. Existing models emphasize generic esthetics or low level...

Meiqi Sun, Mingyu Li, Junxiong Zhu

2602.21698 2026-02-25
AI LLM

EditFlow: Benchmarking and Optimizing Code Edit Recommendation Systems via Reconstruction of Developer Flows

Large language models (LLMs) for code editing have achieved remarkable progress, yet recent empirical studies reveal a fundamental disconnect between technical accuracy and developer productivity. ...

Chenyan Liu, Yun Lin, Jiaxin Chang, Jiawei Liu, Binhang Qi, Bo Jiang, Zhiyong Huang, Jin Song Dong

2602.21697 2026-02-25
TESTING

Combining matrix product states and mean-field theory to capture magnetic order in quasi-1D cuprates

We study quasi-one-dimensional strongly correlated materials using a multi-step approach based on density functional theory, downfolding techniques, and tensor-network simulations. The downfolding ...

Quentin Staelens, Daan Verraes, Daan Vrancken, Tom Braeckevelt, Jutho Haegeman, Veronique Van Spe...

2602.21695 2026-02-25
AI LLM

TiMi: Empower Time Series Transformers with Multimodal Mixture of Experts

Multimodal time series forecasting has garnered significant attention for its potential to provide more accurate predictions than traditional single-modality models by leveraging rich information i...

Jiafeng Lin, Yuxuan Wang, Huakun Luo, Zhongyi Pei, Jianmin Wang

2602.21693 2026-02-25
AI LLM

"Without AI, I Would Never Share This Online": Unpacking How LLMs Catalyze Women's Sharing of Gendered Experiences on Social Media

Sharing gendered experiences on social media has been widely recognized as supporting women's personal sense-making and contributing to digital feminism. However, there are known concerns, such as ...

Runhua Zhang, Ziqi Pan, Huiran Yi, Huamin Qu, Xiaojuan Ma

2602.21686 2026-02-25
AI LLM

AkiraRust: Re-thinking LLM-aided Rust Repair Using a Feedback-guided Thinking Switch

Eliminating undefined behaviors (UBs) in Rust programs requires a deep semantic understanding to enable accurate and reliable repair. While existing studies have demonstrated the potential of LLMs ...

Renshuang Jiang, Yichong Wang, Pan Dong, Xiaoxiang Fang, Zhenling Duan, Tinglue Wang, Yuchen Hu, ...

2602.21681 2026-02-25
AI LLM

Trie-Aware Transformers for Generative Recommendation

Generative recommendation (GR) aligns with advances in generative AI by casting next-item prediction as token-level generation rather than score-based ranking. Most GR methods adopt a two-stage pip...

Zhenxiang Xu, Jiawei Chen, Sirui Chen, Yong He, Jieyu Yang, Chuan Yuan, Ke Ding, Can Wang

2602.21677 2026-02-25