Results 111 to 120 of about 3,000 (250)

Local Search and the Evolution of World Models

Topics in Cognitive Science, EarlyView., 2023
Abstract An open question regarding how people develop their models of the world is how new candidates are generated for consideration out of infinitely many possibilities. We discuss the role that evolutionary mechanisms play in this process. Specifically, we argue that when it comes to developing a global world model, innovation is necessarily ...
Neil R. Bramley, Bonan Zhao, Tadeg Quillien, Christopher G. Lucas   +3 more
wiley   +1 more source

WASTELAND ACTIVISM: Political Weeds and Ecological Imaginaries in Montreal

International Journal of Urban and Regional Research, EarlyView.
Abstract Drawing on ethnographic fieldwork in Montreal, this article examines the ways in which urban dwellers and activists engage with the living materialities of wastelands to illuminate evolving ecological imaginaries and their political potentials.
Daniela Giudici
wiley   +1 more source

MEIL-NeRF: Memory-Efficient Incremental Learning of Neural Radiance Fields

IEEE Access
Hinged on the representation power of neural networks, neural radiance fields (NeRF) have recently emerged as one of the promising and widely applicable methods for 3D object and scene representation.
Jaeyoung Chung, Kanggeon Lee, Sungyong Baik, Kyoung Mu Lee   +3 more
doaj   +1 more source

Dynamic memory to alleviate catastrophic forgetting in continual learning with medical imaging. [PDF]

Nat Commun, 2021
Perkonigg M, Hofmanninger J, Herold CJ, Brink JA, Pianykh O, Prosch H, Langs G.   +6 more
europepmc   +1 more source

Mitigating Catastrophic Forgetting in Large Language Models with Forgetting-aware Pruning

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
Accepted by ...
Wei Huang 0039, Anda Cheng, Yinggui Wang
openaire   +2 more sources

Bridging the Late Antique Gap in Northwest Arabia: New Archaeological Evidence on the Occupation of Wādī al‐Qurā (al‐ʿUlā [AlUla], Saudi Arabia) Between the Third and Seventh Centuries CE

Arabian Archaeology and Epigraphy, EarlyView.
ABSTRACT In 2019, the Dadan Archaeological Project (CNRS/RCU/AFALULA) identified a Late Antique village 1 km south of ancient Dadan in the al‐ʿUlā valley (northwest Saudi Arabia). Three excavation seasons at this site (2021–2023) have uncovered a massive building constructed in the late third or early fourth cent.
Jérôme Rohmer, Abdulrahman Alsuhaibani, Charlène Bouchaud, Elora Chambraud, Vladimir Dabrowski, Hatem Djerbi, Fabien Lesguer, Hervé Monchot, Paul Picavet, Louise Purdue, Bertrand Riba, Shadi Shabo   +11 more
wiley   +1 more source

Class-Incremental Learning-Based Few-Shot Underwater-Acoustic Target Recognition

Journal of Marine Science and Engineering
This paper proposes an underwater-acoustic class-incremental few-shot learning (UACIL) method for streaming data processing in practical underwater-acoustic target recognition scenarios. The core objective is to expand classification capabilities for new
Wenbo Wang, Ye Li, Tongsheng Shen, Dexin Zhao   +3 more
doaj   +1 more source

What is (de)politicization and what is wrong with it?

American Journal of Political Science, EarlyView.
Abstract This article attempts to clarify the meaning of (de)politicization. Politicization sometimes refers to the inappropriate intrusion of partisan loyalties in nonpolitical social domains (affective politicization). Politicization can also constitute an ideal of civic agency and energy (contestatory politicization).
Dimitrios Halikias
wiley   +1 more source

Sequencing to Mitigate Catastrophic Forgetting in Continual Learning

CoRR
To cope with real-world dynamics, an intelligent system needs to incrementally acquire, update, and exploit knowledge throughout its lifetime. This ability, known as Continual learning, provides a foundation for AI systems to develop themselves adaptively.
Hesham G. Moussa, Aroosa Hameed, Arashmid Akhavain   +2 more
openaire   +2 more sources

Story2Board: A Training‐Free Approach for Expressive Visual Storytelling

Computer Graphics Forum, EarlyView.
Abstract We present Story2Board, a training‐free framework for expressive storyboard generation from natural language. Existing methods narrowly focus on subject identity, overlooking key aspects of visual storytelling such as spatial composition, background evolution, and narrative pacing.
D. Dinkevich, M. Levy, O. Avrahami, D. Samuel, D. Lischinski   +4 more
wiley   +1 more source