Emergent Social Dynamics of LLM Agents in the El Farol Bar Problem
arXiv:2509.04537v2 Announce Type: replace-cross Abstract: We investigate the emergent social dynamics of Large Language Model (LLM) agents in a spatially…
HoPE: Hyperbolic Rotary Positional Encoding for Stable Long-Range Dependency Modeling in Large Language Models
arXiv:2509.05218v2 Announce Type: replace-cross Abstract: Positional encoding mechanisms enable Transformers to model sequential structure and long-range dependencies in text. While…
Explained, yet misunderstood: How AI Literacy shapes HR Managers’ interpretation of User Interfaces in Recruiting Recommender Systems
arXiv:2509.06475v1 Announce Type: cross Abstract: AI-based recommender systems increasingly influence recruitment decisions. Thus, transparency and responsible adoption in Human Resource…
AttestLLM: Efficient Attestation Framework for Billion-scale On-device LLMs
arXiv:2509.06326v1 Announce Type: cross Abstract: As on-device LLMs(e.g., Apple on-device Intelligence) are widely adopted to reduce network dependency, improve privacy,…
Augmented Structure Preserving Neural Networks for cell biomechanics
arXiv:2509.05388v1 Announce Type: cross Abstract: Cell biomechanics involve a great number of complex phenomena that are fundamental to the evolution…
The Ethical Compass of the Machine: Evaluating Large Language Models for Decision Support in Construction Project Management
arXiv:2509.04505v1 Announce Type: new Abstract: The integration of Artificial Intelligence (AI) into construction project management (CPM) is accelerating, with Large…
CEHR-XGPT: A Scalable Multi-Task Foundation Model for Electronic Health Records
arXiv:2509.03643v2 Announce Type: replace-cross Abstract: Electronic Health Records (EHRs) provide a rich, longitudinal view of patient health and hold significant…
PropVG: End-to-End Proposal-Driven Visual Grounding with Multi-Granularity Discrimination
arXiv:2509.04833v1 Announce Type: cross Abstract: Recent advances in visual grounding have largely shifted away from traditional proposal-based two-stage frameworks due…
Exploring Non-Local Spatial-Angular Correlations with a Hybrid Mamba-Transformer Framework for Light Field Super-Resolution
arXiv:2509.04824v1 Announce Type: cross Abstract: Recently, Mamba-based methods, with its advantage in long-range information modeling and linear complexity, have shown…
Adaptive Learning Strategies for Mitotic Figure Classification in MIDOG2025 Challenge
arXiv:2509.02640v2 Announce Type: replace-cross Abstract: Atypical mitotic figures (AMFs) are clinically relevant indicators of abnormal cell division, yet their reliable…