Results 91 to 100 of about 89,825 (246)

CoSP: Reconfigurable Metamaterial Inverse Design via Contrastive Pretrained Large Language Model

Advanced Science, EarlyView.
In this work, CoSP (contrastive multi‐state pretrain), an intelligent inverse design method for reconfigurable metamaterials based on a contrastive pretrained large language model, is proposed. Numerical experiments demonstrate that CoSP can design reconfigurable metamaterial structures for multi‐state, multi‐band optical responses, showing great ...
Shujie Yang, Yuqi Zhang, Xuzhe Zhao, Yansong Tang, Kaichen Dong   +4 more
wiley   +1 more source

Trust & Safety of LLMs and LLMs in Trust & Safety

CoRR
11 ...
Doohee You, Dan Chon
openaire   +2 more sources

Neuromorphic Devices and Computing for Sensing, Memory, and Control

Advanced Science, EarlyView.
This review introduces neuromorphic devices made from diverse materials. These devices mimic neuronal functions and architectures and, when integrated with artificial or biological computing, can form closed loops with neurons for pressure, optical, acoustic, and biochemical sensing and modulation.
Zhengguang Zhu, Nicholas Schaffer, Xiao Yang   +2 more
wiley   +1 more source

Large Language Models in Generating Differential Diagnoses in the Emergency Department: A Comparative Study of ChatGPT, Copilot, and Emergency Physician

Eurasian Journal of Emergency Medicine
Aim: Accurate diagnosis in emergency departments relies heavily on clinical decision-making, yet cognitive errors contribute to a significant proportion of diagnostic mistakes.
Banu Arslan, Büşra Erdem, Merve Osoydan Satıcı, Çağatay Nuhoğlu, Hasan Yasin Soylu   +4 more
doaj   +1 more source

LLM-Vectorizer: LLM-Based Verified Loop Vectorizer

Proceedings of the 23rd ACM/IEEE International Symposium on Code Generation and Optimization
Vectorization is a powerful optimization technique that significantly boosts the performance of high performance computing applications operating on large data arrays. Despite decades of research on auto-vectorization, compilers frequently miss opportunities to vectorize code.
Jubi Taneja, Avery Laird, Cong Yan, Madan Musuvathi, Shuvendu K. Lahiri   +4 more
openaire   +3 more sources

Universal Battery Capacity Degradation Forecasting Driven by Foundation Models Across Diverse Chemistries and Conditions

Advanced Science, EarlyView.
A unified time‐series forecasting framework learns transferable battery capacity‐degradation patterns from 20 heterogeneous datasets spanning chemistries, formats, temperatures, and cycling conditions. A single model delivers competitive predictions on both known and previously unseen datasets, while physics‐guided representation learning improves ...
Joey Chan, Huan Wang, Zhen Chen, Haoyu Pan, Wei Wu, Zirong Wang, Ershun Pan, Min Xie, Lifeng Xi   +8 more
wiley   +1 more source

Foregrounding doctoral knowledge and knower in the age of Generative Artificial Intelligence

Transformation in Higher Education
While Generative Artificial Intelligence (AI) presents new challenges for doctoral education, it also offers an opportunity to refocus doctoral programmes on their fundamental purposes: contributing to knowledge and developing critical researchers.
Sioux McKenna
doaj   +1 more source

Densing law of LLMs

Nature Machine Intelligence
Abstract Large language models (LLMs) have emerged as a milestone in artificial intelligence. The scaling law indicates that the performance of LLMs can continually improve as the model size increases, which poses challenges for training and deployment.
Chaojun Xiao, Jie Cai, Weilin Zhao, Biyuan Lin, Guoyang Zeng, Jie Zhou, Zhi Zheng, Xu Han, Zhiyuan Liu, Maosong Sun   +9 more
openaire   +3 more sources

Structural Divergence Between the Moltbook AI‐Agent Network and Human Social Networks

Advanced Science, EarlyView.
Analysis of the Moltbook AI‐agent network reveals a striking combination of familiar global scaling and distinct internal organization. Attention is highly concentrated, reciprocity is limited, connected triads are suppressed, and communities are strongly modular.
Wenpin Hou, Zhicheng Ji
wiley   +1 more source

Can Editing LLMs Inject Harm? [PDF]

Knowledge editing has been increasingly adopted to correct the false or outdated knowledge in Large Language Models (LLMs). Meanwhile, one critical but under-explored question is: can knowledge editing be used to inject harm into LLMs?
Xu, Xiongxiao, Huang, Baixiang, Xiao, Chaowei, Wang, William Yang, Gu, Jia-Chen, Lai, Shiyang, Song, Dawn, Gu, Jindong, Yao, Huaxiu, Shu, Kai, Li, Zekun, Chen, Canyu, Chen, Zhaorun, Yan, Xifeng, Torr, Philip   +14 more
core