arXiv:2508.13234v2 Announce Type: replace-cross Abstract: The acceleration of artificial intelligence (AI) in science is recognized and many scholars have begun to explore its role in interdisciplinary collaboration. However, the mechanisms and extent of this impact are still unclear. This study, using AlphaFold’s impact on structural biologists, examines how AI technologies influence interdisciplinary collaborative patterns. By […]
Transitive RL: Value Learning via Divide and Conquer
arXiv:2510.22512v1 Announce Type: cross Abstract: In this work, we present Transitive Reinforcement Learning (TRL), a new value learning algorithm based on a divide-and-conquer paradigm. TRL is designed for offline goal-conditioned reinforcement learning (GCRL) problems, where the aim is to find a policy that can reach any state from any other state in the smallest number […]
Limitations of Proprioceptive Working Memory
arXiv:2510.21996v1 Announce Type: new Abstract: Recalling previously experienced movements is essential for a range of activities, including sports, music, and rehabilitation, yet little is known about the accuracy and decay of proprioceptive working memory. We examined how introducing a short-term memory component affected movement reproduction accuracy by comparing movement reproduction under two conditions: simultaneous reproduction […]
Cross-Species Transfer Learning in Agricultural AI: Evaluating ZebraPose Adaptation for Dairy Cattle Pose Estimation
arXiv:2510.22618v1 Announce Type: cross Abstract: Pose estimation serves as a cornerstone of computer vision for understanding animal posture, behavior, and welfare. Yet, agricultural applications remain constrained by the scarcity of large, annotated datasets for livestock, especially dairy cattle. This study evaluates the potential and limitations of cross-species transfer learning by adapting ZebraPose – a vision […]
Efficient and Encrypted Inference using Binarized Neural Networks within In-Memory Computing Architectures
arXiv:2510.23034v1 Announce Type: cross Abstract: Binarized Neural Networks (BNNs) are a class of deep neural networks designed to utilize minimal computational resources, which drives their popularity across various applications. Recent studies highlight the potential of mapping BNN model parameters onto emerging non-volatile memory technologies, specifically using crossbar architectures, resulting in improved inference performance compared to […]
$textE^2textRank$: Your Text Embedding can Also be an Effective and Efficient Listwise Reranker
arXiv:2510.22733v1 Announce Type: cross Abstract: Text embedding models serve as a fundamental component in real-world search applications. By mapping queries and documents into a shared embedding space, they deliver competitive retrieval performance with high efficiency. However, their ranking fidelity remains limited compared to dedicated rerankers, especially recent LLM-based listwise rerankers, which capture fine-grained query-document and […]
Foundation of Intelligence: Review of Math Word Problems from Human Cognition Perspective
arXiv:2510.21999v1 Announce Type: new Abstract: Math word problem (MWP) serves as a fundamental research topic in artificial intelligence (AI) dating back to 1960s. This research aims to advance the reasoning abilities of AI by mirroring the human-like cognitive intelligence. The mainstream technological paradigm has evolved from the early rule-based methods, to deep learning models, and […]
Long-Term PM2.5 Forecasting Using a DTW-Enhanced CNN-GRU Model
arXiv:2510.22863v1 Announce Type: cross Abstract: Reliable long-term forecasting of PM2.5 concentrations is critical for public health early-warning systems, yet existing deep learning approaches struggle to maintain prediction stability beyond 48 hours, especially in cities with sparse monitoring networks. This paper presents a deep learning framework that combines Dynamic Time Warping (DTW) for intelligent station similarity […]
FRBNet: Revisiting Low-Light Vision through Frequency-Domain Radial Basis Network
arXiv:2510.23444v1 Announce Type: cross Abstract: Low-light vision remains a fundamental challenge in computer vision due to severe illumination degradation, which significantly affects the performance of downstream tasks such as detection and segmentation. While recent state-of-the-art methods have improved performance through invariant feature learning modules, they still fall short due to incomplete modeling of low-light conditions. […]
The Reasoning Trap: How Enhancing LLM Reasoning Amplifies Tool Hallucination
arXiv:2510.22977v1 Announce Type: cross Abstract: Enhancing the reasoning capabilities of Large Language Models (LLMs) is a key strategy for building Agents that “think then act.” However, recent observations, like OpenAI’s o3, suggest a paradox: stronger reasoning often coincides with increased hallucination, yet no prior work has systematically examined whether reasoning enhancement itself causes tool hallucination. […]