activity
20142025
most citedOn the Properties of Neural Machine Translation: Encoder-Decoder Approaches

1.1k citations · 1.9k across the 31 of their papers we have counts for

collaborators

30 papers

cs.LG20251 cited

Supervised Contrastive Block Disentanglement

Taro Makino, Ji Won Park, Natasa Tagasovska +11

Real-world datasets often combine data collected under different experimental conditions. This yields larger datasets, but also introduces spurious correlations that make it diffic…

cs.CL20251 cited

HERITAGE: An End-to-End Web Platform for Processing Korean Historical Documents in Hanja

Seyoung Song, Haneul Yoo, Jiho Jin +2

While Korean historical documents are invaluable cultural heritage, understanding those documents requires in-depth Hanja expertise. Hanja is an ancient language used in Korea befo…

cs.LG20243 cited

Concept Bottleneck Language Models For protein design

Aya Abdelsalam Ismail, Tuomas Oikarinen, Amy Wang +8

We introduce Concept Bottleneck Protein Language Models (CB-pLM), a generative masked language model with a layer where each neuron corresponds to an interpretable concept. Our arc…

q-bio.BM20243 cited

Antibody DomainBed: Out-of-Distribution Generalization in Therapeutic Protein Design

Nataša Tagasovska, Ji Won Park, Matthieu Kirchmeyer +8

Machine learning (ML) has demonstrated significant promise in accelerating drug design. Active ML-guided optimization of therapeutic molecules typically relies on a surrogate model…

cs.LG2024

Closed-Form Test Functions for Biophysical Sequence Optimization Algorithms

Samuel Stanton, Robert Alberstein, Nathan Frey +2

There is a growing body of work seeking to replicate the success of machine learning (ML) on domains like computer vision (CV) and natural language processing (NLP) to applications…

cs.CL20242 cited

Following Length Constraints in Instructions

Weizhe Yuan, Ilia Kulikov, Ping Yu +4

Aligned instruction following models can better fulfill user requests than their unaligned counterparts. However, it has been shown that there is a length bias in evaluation of suc…