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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

A critical appraisal of equity in conversational AI: Evidence from auditing GPT-3's dialogues with different publics on climate change and Black Lives Matter


Sep 27, 2022
Kaiping Chen, Anqi Shao, Jirayu Burapacheep, Yixuan Li


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learning


Sep 21, 2022
Haobo Wang, Mingxuan Xia, Yixuan Li, Yuren Mao, Lei Feng, Gang Chen, Junbo Zhao

* Accepted to NeurIPS 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Out-of-distribution Detection via Frequency-regularized Generative Models


Aug 18, 2022
Mu Cai, Yixuan Li

* Paper accepted as a spotlight in WACV2023 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Open-world Contrastive Learning


Aug 04, 2022
Yiyou Sun, Yixuan Li

* 22 pages, 6 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Task Agnostic and Post-hoc Unseen Distribution Detection


Jul 26, 2022
Radhika Dua, Seongjun Yang, Yixuan Li, Edward Choi


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

POEM: Out-of-Distribution Detection with Posterior Sampling


Jun 28, 2022
Yifei Ming, Ying Fan, Yixuan Li

* Thirty-ninth International Conference on Machine Learning (2022) 
* ICML 2022 (Long Talk); First two authors contributed equally 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

What are People Talking about in #BackLivesMatter and #StopAsianHate? Exploring and Categorizing Twitter Topics Emerging in Online Social Movements through the Latent Dirichlet Allocation Model


May 29, 2022
Xin Tong, Yixuan Li, Jiayi Li, Rongqi Bei, Luyao Zhang

* Accepted at AAAI and ACM Conference on AI, Ethics, and Society, August 1 to 3, 2022, Oxford, United Kingdom 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Mitigating Neural Network Overconfidence with Logit Normalization


May 19, 2022
Hongxin Wei, Renchunzi Xie, Hao Cheng, Lei Feng, Bo An, Yixuan Li

* Accepted by ICML 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Out-of-distribution Detection with Deep Nearest Neighbors


Apr 13, 2022
Yiyou Sun, Yifei Ming, Xiaojin Zhu, Yixuan Li

* 16 pages, 5 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Are Vision Transformers Robust to Spurious Correlations?


Mar 17, 2022
Soumya Suvra Ghosal, Yifei Ming, Yixuan Li


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
4
5
>>