Prof. Danushka Bollegala@ICLR-2025 in 🇸🇬 (@bollegala) 's Twitter Profile
Prof. Danushka Bollegala@ICLR-2025 in 🇸🇬

@bollegala

Full Professor (Chair) in NLP at the University of Liverpool, Head of ML. Amazon Scholar. (he/him) Previously University of Tokyo, Microsoft.

ID: 73090248

linkhttp://danushka.net calendar_today10-09-2009 10:44:07

2,2K Tweet

3,3K Followers

797 Following

Prof. Danushka Bollegala@ICLR-2025 in 🇸🇬 (@bollegala) 's Twitter Profile Photo

セッション終了まで後20分ですでに1時間以上並んでる。学生さんには申し訳ないが、発表する姿見れるかな

Masaru Isonuma (@m_isonuma) 's Twitter Profile Photo

This work proposes "reverse dataset distillation," which creates data that induces gradients opposite to those of the original dataset. By training a model on this distilled data, the model unlearns the original dataset without significant performance degradation. #ICLR2025

This work proposes "reverse dataset distillation," which creates data that induces gradients opposite to those of the original dataset. 
By training a model on this distilled data, the model unlearns the original dataset without significant performance degradation. #ICLR2025
Prof. Danushka Bollegala@ICLR-2025 in 🇸🇬 (@bollegala) 's Twitter Profile Photo

ICLRの運営方式はACLなどと違って,Program Chairの上にSenior Program Chairがいて,翌年はその人がGeneral Chairになるという方針のようです.2年続けて大変な時期があるということですかね.

Keenan Crane (@keenanisalive) 's Twitter Profile Photo

Jensen's inequality gives the difference between the average value of a convex function φ, and its value at the center, where both “average” and “center” are defined in terms of some distribution p_X. When the function φ is flat, or the distribution is narrow, they agree.

Masahiro Kaneko (@masahirokaneko_) 's Twitter Profile Photo

Our paper has been accepted to #IJCAI2025🎉 We created EAGLE, a real-world instruction benchmark for evaluating social bias, opinion bias, toxicity, and immorality in LLMs🦅 (w/ Prof. Danushka Bollegala, Tim Baldwin) 📜: arxiv.org/abs/2402.14258 💾: huggingface.co/datasets/Masah…

Our paper has been accepted to #IJCAI2025🎉 We created EAGLE, a real-world instruction benchmark for evaluating social bias, opinion bias, toxicity, and immorality in LLMs🦅 (w/ <a href="/Bollegala/">Prof. Danushka Bollegala</a>, <a href="/eltimster/">Tim Baldwin</a>)
📜: arxiv.org/abs/2402.14258
💾: huggingface.co/datasets/Masah…
Vered Shwartz (@veredshwartz) 's Twitter Profile Photo

*SEM 2025: Direct submissions deadline is now EXTENDED to June 13, 2025! *SEM will be co-located with EMNLP in Suzhou, China. It will be a hybrid event, virtual attendance possible (more info on this will be posted later). Full CFP: starsem2025.github.io/cfp #NLP #NLProc

*SEM 2025: Direct submissions deadline is now EXTENDED to June 13, 2025! *SEM will be co-located with EMNLP in Suzhou, China. It will be a hybrid event, virtual attendance possible (more info on this will be posted later). Full CFP: starsem2025.github.io/cfp #NLP #NLProc