Universal in-context approximation by prompting fully recurrent models by Petrov, A, Lamb, TA, Paren, A, Torr, PHS, Bibi, A

“…Zero-shot and in-context learning enable solving tasks without model fine-tuning, making them essential for developing generative model solutions. …”

Language models as hierarchy encoders by He, Y, Yuan, Z, Chen, J, Horrocks, I

“…We evaluate HITs against pre-trained LMs, standard fine-tuned LMs, and several hyperbolic embedding baselines, focusing on their capabilities in simulating transitive inference, predicting subsumptions, and transferring knowledge across hierarchies. …”

AI-assisted discovery of quantitative and formal models in social science by Balla, J, Huang, S, Dugan, O, Dangovski, R, Soljačić, M

“…We propose that this AI-assisted framework can bridge parametric and non-parametric models commonly employed in social science research by systematically exploring the space of non-linear models and enabling fine-grained control over expressivity and interpretability.…”

UWB antipodal Vivaldi antenna for monostatic configuration of through wall imaging applications by AHMED, SAJJAD, JORET, ARIFFUDDIN, KATIRAN, NORSHIDAH, PONNIRAN, ASMARASHID, ABDULLAH, M. F. L., ZAKARIA, ZAHRILADHA, SULONG, MUHAMMAD SUHAIMI

“…A specific stable gain of around 11.7 dB is achieved with good directivity and fine radiation patterns. Using this monostatic UWB antenna design, a TWI simulation-based experiment was carried out. …”
Get full text

Immobilization of cyclodextrin glucanotransferase on electrospun polyvinyl alcohol nanofibers by Saallah, Suryani

“…In this study, cyclodextrin glucanotransferase (CGTase) enzyme was successfully immobilised on PVA nanofibers via post-spinning and simultaneous electrospraying and electrospinning. …”
Get full text

Structure and phase engineering of 2D transition metal chalcogenides by Tang, Bijun

“…Moreover, the morphology of heterostructures can be engineered by fine-tuning the synthesis conditions. WS2 quantum well is also identified in the synthesized heterostructures, providing opportunities for studying novel optical properties and quantum confinement effects. …”
Get full text

Physics-informed machine learning for green data center operations by Wang, Ruihang

“…The evaluation shows that our approach saves 5.7% to 13.8% power usage compared with conventional feedback control and adapts 8x to 10x faster than native fine-tuning with at most 0.74C temperature overshoot. …”
Get full text

The Economics of Tropical Deforestation by Balboni, Clare, Berman, Aaron, Burgess, Robin, Olken, Benjamin A.

“…We begin by reviewing the methodological advances that have enabled measurement of forest loss at a fine spatial resolution across the globe. We then develop a simple benchmark model of deforestation based on classic models of natural resource extraction. …”
Get full text

An Energy and Area Estimation Plugin for Accelerator Architecture Simulation by Wu, Wendy

“…Accelergy is a tool that provides a good general framework for fine-grained energy and area estimation. However, output from simulation tools may not be compatible with Accelergy’s expected input format, which is the case for the custom simulator Accelsim. …”
Get full text

MLTCP: A Distributed Technique to Approximate Centralized Flow Scheduling For Machine Learning by Rajasekaran, Sudarsanan, Narang, Sanjoli, Zabreyko, Anton A., Ghobadi, Manya

Get full text

Unearthing roots by Lim, Ling Ern

Get full text

Looking Glass by Nur Mariyah Muhamad Afandi

Get full text

悟 · Know my heart by Wang, Ruimeng

Get full text

Bridging the gap between animation mediums in 'Wait.' by Teoh, Soon Heng

Get full text

Memento by Lim, Benjamin Yong Quan

Get full text

Textures of being: fostering hair texture inclusivity in Singapore by Shreya, Menon

Get full text

With lots of love by Sum, Mun Cheng

Get full text

Let's get crackin' by Wong, Gwendolyn Jeng Teng

Get full text

Federated learning for natural language processing in medical domain by Saraf, Ishita

“…The study compares the performance of centralized training and federated learning for fine-tuning a BERT-based conversational agent on a medical conversation dataset, serving as a stepping-stone for future research into federated learning for LLM-led NLP applications.…”
Get full text

Information embedded scalable to lossless (SLS) audio by Hoo, Qing Yu.

“…SLS is able to achieve lossy to lossless and fine granular bit-rate scalability, and allows encapsulation of side information such as lyrics, album art, or even low-resolution music video. …”
Get full text