paper-with-me

Papers

PRESTO: Progressive Pretraining Enhances Synthetic Chemistry Outcomes

2024-06-19 · He Cao, Yanjun Shao, Zhiyuan Liu, Zijing Liu, Xiangru Tang, Yuan YAO, Yu Li

Multimodal Large Language Models (MLLMs) have seen growing adoption across various scientific disciplines. These advancements encourage the investigation of molecule-text modeling within synthetic chemistry, a field dedicated to designing and conducting chemical reactions to synthesize new compounds with desired properties and applications. Current approaches, however, often neglect the critical role of multiple molecule graph interaction in understanding chemical reactions, leading to suboptimal performance in synthetic chemistry tasks. This study introduces PRESTO(Progressive Pretraining Enhances Synthetic Chemistry Outcomes), a new framework that bridges the molecule-text modality gap by integrating a comprehensive benchmark of pretraining strategies and dataset configurations. It progressively improves multimodal LLMs through cross-modal alignment and multi-graph understanding. Our extensive experiments demonstrate that PRESTO offers competitive results in downstream synthetic chemistry tasks. The code can be found at https://github.com/IDEA-XL/PRESTO.

📄 PDF Abstract BibTeX arXiv:2406.13193

Code (1)

idea-xl/presto 공식 구현 pytorch

Tasks

cross-modal alignment

Similar Papers 제목 키워드 기반

Long Video Diffusion Generation with Segmented Cross-Attention and Content-Rich Video Data Curation

2024-12-02 · CVPR 2025 1 · Xin Yan, Yuxuan Cai, Qiuyue Wang, Yuan Zhou 외

We introduce Presto, a novel video diffusion model designed to generate 15-second videos with long-range coherence and rich content. Extending video generation methods to maintain scenario diversity over long durations p…

DiversityVideo Generation

PRESTO: Preimage-Informed Instruction Optimization for Prompting Black-Box LLMs

2025-10-29 · Jaewon Chu, Seunghun Lee, Hyunwoo J. Kim arxiv

Large language models (LLMs) have achieved remarkable success across diverse domains, due to their strong instruction-following capabilities. This has led to increasing interest in optimizing instructions for black-box L…

PRESTO: A Multilingual Dataset for Parsing Realistic Task-Oriented Dialogs

2023-03-15 · Rahul Goel, Waleed Ammar, Aditya Gupta, Siddharth Vashishtha 외

Research interest in task-oriented dialogs has increased as systems such as Google Assistant, Alexa and Siri have become ubiquitous in everyday life. However, the impact of academic research in this area has been limited…

Lightweight, Pre-trained Transformers for Remote Sensing Timeseries

2023-04-27 · Gabriel Tseng, Ruben Cartuyvels, Ivan Zvonkov, Mirali Purohit 외

Machine learning methods for satellite data have a range of societally relevant applications, but labels used to train models can be difficult or impossible to acquire. Self-supervision is a natural solution in settings …

Crop ClassificationSelf-Supervised LearningTransfer Learning

Curriculum-Guided Layer Scaling for Language Model Pretraining

2025-06-13 · Karanpartap Singh, Neil Band, Ehsan Adeli arxiv

As the cost of pretraining large language models grows, there is continued interest in strategies to improve learning efficiency during this core training stage. Motivated by cognitive development, where humans gradually…