Exciting news! 🌟 Our highly anticipated workshop on summarization is just a day away! Join us to hear from 5 distinguished keynote speakers and discover cutting-edge insights from our workshop and findings papers. Don’t miss out! #EMNLP #EMNLP2023

Rainy days in Singapore set the stage for a cozy day with coffee and keynote talks on summarization & LLMs at #EMNLP2023. Despite LLM advances, summarization still poses unique challenges. Uncover these at the New Frontier in Summarization workshop on Dec 6th at 8:50 AM #NLProc

NewSumm workshop schedule on Dec. 6th: newsumm.github.io/2023/ We will have 5 amazing keynote speakers gracing our floor: Kathleen McKeown, Jackie Cheung, Rui Zhang (Rui Zhang), Iz Beltagy (Iz Beltagy), and Chenguang Zhu (Chenguang Zhu). #NLProc #EMNLP2023

Dive into #NewSumm on Dec 6th! Explore ~50 posters, keynotes, and lightning talks on summarization. With 480+ registered attendees, discussions and collaborations await. I'll miss #EMNLP2023 in person, catch me at #NeurIPS2023. I have 2~3 PhD positions open! Let's chat!

Please also consider joining the ACL Special Interest Group on Summarization (SIGSUMM) to stay up to date with text summarization research! #EMNLP2023 #NLProc sigsumm.org

On my way to #NeurIPS2023. Excited to chat with old friends and meeting new ones. I am also recruiting 2-3 PhD students for Fall 24, focusing on trustworthy NLP and LLM safety, please shoot me a dm if you’d like to chat in person. More see my website: yuedong.us

Our paper on LLM watermarks for conditional text generation has been accepted to #AAAI2024. We discovered a trade-off between task performance and detection of watermarking LLMs for CTG task, and proposed a semantic watermark for CTG. Paper details: arxiv.org/abs/2307.13808

Attending NeurIPS Workshops? Do not miss the 3rd ENLSP on Efficient LLM and Speech models happening on Saturday Dec. 16th, (Room 206-207 & virtual). #NeurIPS2023 7 Keynote Speakers, A Panel, 10 Spotlight talks & 70+ Posters. Link: neurips2023-enlsp.github.io

#ICLR2024 #Spotlight 🏆 Thrilled to share our paper "Jailbreak in Pieces: Compositional Adversarial Attacks on Multi-Modal Language Models" accepted for publication at ICLR 2026 2024 for #Spotlight 🎖 presentation! (top 5% submissions)!

We reveal #LLMs safety alignment varies by NLP tasks: weak in summarization, risking in-context attacks. Safety-sensitive documents #ChatGPT refuse to translate can be translated if we ask for a summary first #NLProc Demo: fyyfu.github.io/SafetyAlignNLP/ Paper: arxiv.org/abs/2312.06924

Sharing my vision for SIGDAT: 1️⃣ Advocate Open Science Research 2️⃣ Ensure consistent review practices & Allow finding papers be presented at EMNLP. 3️⃣ Commit to aggressive fundraising for ECRs & champion an evidence-based approach to inclusion.

I am honored to be nominated by SIGDAT (the org that oversees EMNLP) to run for VP-elect with other awesome candidates who share the goal of improving our community. Please check your email to vote by 3/24.🗳️ See details: bit.ly/3ItRc0S

🤖 We will be giving a 3-hour tutorial at ACL 2026 on Sunday, August 11th. The focus is on the "Vulnerabilities of LLMs/VLMs to Adversarial Attacks" and in general, "AI Safety"! 😈 So if you want to get a thorough understanding of the field, make sure you don't miss it! 😀

📕You can also check out our survey paper in case you are interested. paper: lnkd.in/grffp66V Regrettably, I can't be there in person, but I'd like to extend my thanks to my advisors, Yue Dong @ NeurIPS 2023 and Nael Abu-Ghazaleh , who will be presenting the tutorial. 🙏 #ACL2024 #Tutorial

🚀 Thrilled to share that our paper “Can Textual Unlearning Solve Cross-Modality Safety Alignment?” Was accepted to #EMNLP2024 Findings! 👨🏻‍🎓Link: arxiv.org/pdf/2406.02575 #Cross_Modality_Safety_Alignment #Textual_Unlearning #SFT #MultiModal #LLMs #AI_Safety #EMNLP2024

📣 As #EMNLP2025 begins, join the 5th New Frontiers in Summarization Workshop (NewSumm 2025) this Saturday, Nov 8! 🔗 newsumm.github.io/2025/ Explore grounded, multimodal, and long-form summarization with reliable evaluation and efficient LLMs. #NLProc #NLP #LLMs #Summarization

[2/2] 🎤 We’re excited to host an amazing lineup of keynote speakers for #NewSumm2025 at #EMNLP2025! Mohit Bansal (UNC) Mohit Bansal Greg Durrett (NYU) Greg Durrett Arman Cohan (Yale) Arman Cohan Alexander R. Fabbri (Scale AI) Jey Han Lau (Univ. of Melbourne) #NLProc

🔥 Proactive Co-Creator is officially LIVE in Google AI Studio! Stop guessing prompts. Start collaborating. Use it now to remix ideas and generate images, stories, and video with an AI that proactively helps you create. 🔗 Try it here: aistudio.google.com/apps/bundled/p… 📍 At #NeurIPS2025?