Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Kyunghyun Cho

Kyunghyun Cho

Joint Embedding Predictive Architectures Focus on Slow Features

Nov 20, 2022
Vlad Sobal, Jyothir S V, Siddhartha Jalagam, Nicolas Carion, Kyunghyun Cho, Yann LeCun

Figure 1 for Joint Embedding Predictive Architectures Focus on Slow Features

Figure 2 for Joint Embedding Predictive Architectures Focus on Slow Features

Figure 3 for Joint Embedding Predictive Architectures Focus on Slow Features

Figure 4 for Joint Embedding Predictive Architectures Focus on Slow Features

* 4 pages (3 figures) short paper for SSL Theory and Practice workshop at NeurIPS 2022. Code is available at https://github.com/vladisai/JEPA_SSL_NeurIPS_2022

Access Paper or Ask Questions

Language Model Classifier Aligns Better with Physician Word Sensitivity than XGBoost on Readmission Prediction

Nov 15, 2022
Grace Yang, Ming Cao, Lavender Y. Jiang, Xujin C. Liu, Alexander T. M. Cheung, Hannah Weiss, David Kurland, Kyunghyun Cho, Eric K. Oermann

Figure 1 for Language Model Classifier Aligns Better with Physician Word Sensitivity than XGBoost on Readmission Prediction

Figure 2 for Language Model Classifier Aligns Better with Physician Word Sensitivity than XGBoost on Readmission Prediction

Figure 3 for Language Model Classifier Aligns Better with Physician Word Sensitivity than XGBoost on Readmission Prediction

Figure 4 for Language Model Classifier Aligns Better with Physician Word Sensitivity than XGBoost on Readmission Prediction

* Extended Abstract presented at Machine Learning for Health (ML4H) symposium 2022, November 28th, 2022, New Orleans, United States & Virtual, http://www.ml4h.cc, 13 pages

Access Paper or Ask Questions

HUE: Pretrained Model and Dataset for Understanding Hanja Documents of Ancient Korea

Oct 11, 2022
Haneul Yoo, Jiho Jin, Juhee Son, JinYeong Bak, Kyunghyun Cho, Alice Oh

Figure 1 for HUE: Pretrained Model and Dataset for Understanding Hanja Documents of Ancient Korea

Figure 2 for HUE: Pretrained Model and Dataset for Understanding Hanja Documents of Ancient Korea

Figure 3 for HUE: Pretrained Model and Dataset for Understanding Hanja Documents of Ancient Korea

Figure 4 for HUE: Pretrained Model and Dataset for Understanding Hanja Documents of Ancient Korea

* Findings of NAACL 2022

Access Paper or Ask Questions

PropertyDAG: Multi-objective Bayesian optimization of partially ordered, mixed-variable properties for biological sequence design

Oct 08, 2022
Ji Won Park, Samuel Stanton, Saeed Saremi, Andrew Watkins, Henri Dwyer, Vladimir Gligorijevic, Richard Bonneau, Stephen Ra, Kyunghyun Cho

Figure 1 for PropertyDAG: Multi-objective Bayesian optimization of partially ordered, mixed-variable properties for biological sequence design

Figure 2 for PropertyDAG: Multi-objective Bayesian optimization of partially ordered, mixed-variable properties for biological sequence design

Figure 3 for PropertyDAG: Multi-objective Bayesian optimization of partially ordered, mixed-variable properties for biological sequence design

Figure 4 for PropertyDAG: Multi-objective Bayesian optimization of partially ordered, mixed-variable properties for biological sequence design

* 9 pages, 7 figures. Submitted to NeurIPS 2022 AI4Science Workshop

Access Paper or Ask Questions

A Non-monotonic Self-terminating Language Model

Oct 03, 2022
Eugene Choi, Cheolhyoung Lee, Kyunghyun Cho

Figure 1 for A Non-monotonic Self-terminating Language Model

Figure 2 for A Non-monotonic Self-terminating Language Model

Figure 3 for A Non-monotonic Self-terminating Language Model

Figure 4 for A Non-monotonic Self-terminating Language Model

* 10 pages, 6 figures

Access Paper or Ask Questions