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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Kyunghyun Cho

Kyunghyun Cho

Endowing Language Models with Multimodal Knowledge Graph Representations



Ningyuan Huang , Yash R. Deshpande , Yibo Liu , Houda Alberts , Kyunghyun Cho , Clara Vania , Iacer Calixto

* 14 pages with appendix, 2 figures, 15 tables 
   Access Paper or Ask Questions

Linear Connectivity Reveals Generalization Strategies



Jeevesh Juneja , Rachit Bansal , Kyunghyun Cho , João Sedoc , Naomi Saphra

Figure 1 for Linear Connectivity Reveals Generalization Strategies
Figure 2 for Linear Connectivity Reveals Generalization Strategies
Figure 3 for Linear Connectivity Reveals Generalization Strategies
Figure 4 for Linear Connectivity Reveals Generalization Strategies

   Access Paper or Ask Questions

Translating Hanja historical documents to understandable Korean and English



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

Figure 1 for Translating Hanja historical documents to understandable Korean and English
Figure 2 for Translating Hanja historical documents to understandable Korean and English
Figure 3 for Translating Hanja historical documents to understandable Korean and English
Figure 4 for Translating Hanja historical documents to understandable Korean and English

   Access Paper or Ask Questions

Multi-segment preserving sampling for deep manifold sampler



Daniel Berenberg , Jae Hyeon Lee , Simon Kelow , Ji Won Park , Andrew Watkins , Vladimir Gligorijević , Richard Bonneau , Stephen Ra , Kyunghyun Cho

Figure 1 for Multi-segment preserving sampling for deep manifold sampler
Figure 2 for Multi-segment preserving sampling for deep manifold sampler
Figure 3 for Multi-segment preserving sampling for deep manifold sampler
Figure 4 for Multi-segment preserving sampling for deep manifold sampler

   Access Paper or Ask Questions

Training Language Models with Natural Language Feedback



Jérémy Scheurer , Jon Ander Campos , Jun Shern Chan , Angelica Chen , Kyunghyun Cho , Ethan Perez

Figure 1 for Training Language Models with Natural Language Feedback
Figure 2 for Training Language Models with Natural Language Feedback
Figure 3 for Training Language Models with Natural Language Feedback
Figure 4 for Training Language Models with Natural Language Feedback
* The First Workshop on Learning with Natural Language Supervision at ACL 2022 
   Access Paper or Ask Questions

Learning from Natural Language Feedback



Jérémy Scheurer , Jon Ander Campos , Jun Shern Chan , Angelica Chen , Kyunghyun Cho , Ethan Perez

Figure 1 for Learning from Natural Language Feedback
Figure 2 for Learning from Natural Language Feedback
Figure 3 for Learning from Natural Language Feedback
Figure 4 for Learning from Natural Language Feedback
* The First Workshop on Learning with Natural Language Supervision at ACL 2022 
   Access Paper or Ask Questions

On the Effect of Pretraining Corpora on In-context Learning by a Large-scale Language Model



Seongjin Shin , Sang-Woo Lee , Hwijeen Ahn , Sungdong Kim , HyoungSeok Kim , Boseop Kim , Kyunghyun Cho , Gichang Lee , Woomyoung Park , Jung-Woo Ha , Nako Sung

Figure 1 for On the Effect of Pretraining Corpora on In-context Learning by a Large-scale Language Model
Figure 2 for On the Effect of Pretraining Corpora on In-context Learning by a Large-scale Language Model
Figure 3 for On the Effect of Pretraining Corpora on In-context Learning by a Large-scale Language Model
Figure 4 for On the Effect of Pretraining Corpora on In-context Learning by a Large-scale Language Model
* Accepted to NAACL2022 as a long paper 
   Access Paper or Ask Questions

Separating the World and Ego Models for Self-Driving



Vlad Sobal , Alfredo Canziani , Nicolas Carion , Kyunghyun Cho , Yann LeCun

Figure 1 for Separating the World and Ego Models for Self-Driving
Figure 2 for Separating the World and Ego Models for Self-Driving
Figure 3 for Separating the World and Ego Models for Self-Driving
Figure 4 for Separating the World and Ego Models for Self-Driving
* 8 pages main content, 14 with references and appendix. 5 figures in total. Submitted and accepted to ICLR 2022 workshop on Generalizable Policy Learning in the Physical World (https://ai-workshops.github.io/generalizable-policy-learning-in-the-physical-world/) 
   Access Paper or Ask Questions

Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks



Nan Wu , Stanisław Jastrzębski , Kyunghyun Cho , Krzysztof J. Geras

Figure 1 for Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks
Figure 2 for Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks
Figure 3 for Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks
Figure 4 for Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks

   Access Paper or Ask Questions

Generative multitask learning mitigates target-causing confounding



Taro Makino , Krzysztof Geras , Kyunghyun Cho

Figure 1 for Generative multitask learning mitigates target-causing confounding
Figure 2 for Generative multitask learning mitigates target-causing confounding
Figure 3 for Generative multitask learning mitigates target-causing confounding
Figure 4 for Generative multitask learning mitigates target-causing confounding

   Access Paper or Ask Questions
1
2
3
4
5
6
7
>>