activity
20172023
most citedThe Impact of Positional Encoding on Length Generalization in Transformers

33 citations · 212 across the 29 of their papers we have counts for

collaborators
Showing 2023Show all

7 papers · 1 filter

cs.LG2023★ 2 cited

Hierarchical Grammar-Induced Geometry for Data-Efficient Molecular Property Prediction

Minghao Guo, Veronika Thost, Samuel W Song +4

The prediction of molecular properties is a crucial task in the field of material and drug discovery. The potential benefits of using deep learning techniques are reflected in the…

cs.CL2023★ 33 cited

The Impact of Positional Encoding on Length Generalization in Transformers

Amirhossein Kazemnejad, Inkit Padhi, Karthikeyan Natesan Ramamurthy +2

Length generalization, the ability to generalize from small training context sizes to larger ones, is a critical challenge in the development of Transformer-based language models.…

cs.LG2023

Efficient Equivariant Transfer Learning from Pretrained Models

Sourya Basu, Pulkit Katdare, Prasanna Sattigeri +4

Efficient transfer learning algorithms are key to the success of foundation models on diverse downstream tasks even with limited data. Recent works of Basu et al. (2023) and Kaba e…

q-bio.QM2023★ 27 cited

A Systematic Study of Joint Representation Learning on Protein Sequences and Structures

Zuobai Zhang, Chuanrui Wang, Minghao Xu +4

Learning effective protein representations is critical in a variety of tasks in biology such as predicting protein functions. Recent sequence representation learning methods based…

cs.LG2023★ 1 cited

AI Maintenance: A Robustness Perspective

Pin-Yu Chen, Payel Das

With the advancements in machine learning (ML) methods and compute resources, artificial intelligence (AI) empowered systems are becoming a prevailing technology. However, current…

cs.LG2023★ 4 cited

Reprogramming Pretrained Language Models for Protein Sequence Representation Learning

Ria Vinod, Pin-Yu Chen, Payel Das

Machine Learning-guided solutions for protein learning tasks have made significant headway in recent years. However, success in scientific discovery tasks is limited by the accessi…