English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Molecular dynamics simulations have emerged as a fundamental instrument forstudying biomolecules. At the same time, it is desirable to perform simulationsof a collection of particles under various conditions in which the moleculescan fluctuate. In this paper, we explore and adapt the soft prompt-basedlearning method to molecular dynamics tasks. Our model can remarkablygeneralize to unseen and out-of-distribution scenarios with limited trainingdata. While our work focuses on temperature as a test case, the versatility ofour approach allows for efficient simulation through any continuous dynamicconditions, such as pressure and volumes. Our framework has two stages: 1)Pre-trains with data mixing technique, augments molecular structure data andtemperature prompts, then applies a curriculum learning method by increasingthe ratio of them smoothly. 2) Meta-learning-based fine-tuning frameworkimproves sample-efficiency of fine-tuning process and gives the softprompt-tuning better initialization points. Comprehensive experiments revealthat our framework excels in accuracy for in-domain data and demonstratesstrong generalization capabilities for unseen and out-of-distribution samples.

Mixup-Augmented Meta-Learning for Sample-Efficient Fine-Tuning of Protein Simulators