Can Large Language Models help with Scientific Hypothesis Generation? Find out what Aidong Zhang, prof UVA Engineering has to say Virginia Tech Computer Science The Sanghani Center at Virginia Tech-sponsored Distinguished Lecture, Tues, Nov 12, 2-3:15 p.m. Attend in 310 Kelly Hall, Blacksburg or Room 3-024, VTRC-A, Arlington.

Join us for the Undergraduate and High School Symposium at BigData'24 on 12/15 in DC! Enjoy a full day of exciting activities, including a keynote by Dr. Héctor Muñoz-Avila (NSF PD), 18 oral presentations, 12 poster sessions, and 7 best paper/runner-up awards! IEEE Big Data

We are excited to present our AI4Science tutorial again at #AAAI2025! Looking forward to seeing everyone in Philadelphia! AAAI aaai.org/conference/aaa…

Our tutorial, "𝐀𝐈 𝐟𝐨𝐫 𝐒𝐜𝐢𝐞𝐧𝐜𝐞 𝐰𝐢𝐭𝐡 𝐋𝐋𝐌𝐬", at 𝐀𝐀𝐀𝐈25! AAAI 📅 𝐃𝐚𝐭𝐞 & 𝐓𝐢𝐦𝐞: Feb 26, 2025 | 8:30 AM – 12:30 PM EST 📍 𝐋𝐨𝐜𝐚𝐭𝐢𝐨𝐧: Philadelphia Convention Center, Room 119A 🔗 𝐓𝐮𝐭𝐨𝐫𝐢𝐚𝐥 𝐖𝐞𝐛𝐬𝐢𝐭𝐞: xuanwang91.github.io

I am honored to give a talk at UIUC iSchool this Friday to share our recent work on multi-agent language model systems. Thanks to Yun Huang, PhD for the kind invitation! 🌽😊 University of Illinois iSchool at Illinois DM me if you are interested in joining us (in person or via Zoom)!

🙏Thank you Prof. Xuan Wang Xuan Wang for visiting us! We look forward to having fun and engaging discussions. 👏👏👏

Congratulations to Priya, co-advised with Xuan Wang Xuan Wang, on a successful defense of her MS thesis on improving multi-agent LLM deliberation for real-world tasks. Thanks to Pinar Yanardag 🚀 CVPR2025 for serving on her committee! Next stop? No stop — she’s continuing right into her PhD

I’ve seen many questions about how to choose ARR tracks for submissions aim at the new tracks at #emnlp2025. We actually wrote a blogpost along with the 2nd CFP exactly to address this: 2025.emnlp.org/track-changes/ Please help us share it widely! Good luck with your emnlp submissions!

Congratulations to my student Sindhura on her first ISMB main conference paper! 🎉 #ISMB2025 #Bioinformatics #FoundationModels

If LLMs tend to agree with humans (sycophancy) during conversations, what happens when they interact in a multi-agent system? How does it influence multi-agent LLM effectiveness & efficiency? Our ACL'25 paper tackles this question. Congrats to my PhD student Priya! 👏

LLMs, although successful in many NLP tasks, still struggle with zero-shot IE for structured data. Can multiple LLM agents help, or do they add new challenges? Our ACL’25 paper explores these questions. Full post on LinkedIn: linkedin.com/posts/meng-lu-…

🚀 We are excited to announce 𝐑𝐀𝐢𝐌 𝟐𝟎𝟐𝟓: 𝐓𝐡𝐞 𝐅𝐢𝐫𝐬𝐭 𝐈𝐧𝐭𝐞𝐫𝐧𝐚𝐭𝐢𝐨𝐧𝐚𝐥 𝐖𝐨𝐫𝐤𝐬𝐡𝐨𝐩 𝐨𝐧 𝐑𝐞𝐬𝐢𝐥𝐢𝐞𝐧𝐭 𝐀𝐫𝐭𝐢𝐟𝐢𝐜𝐢𝐚𝐥 𝐈𝐧𝐭𝐞𝐥𝐥𝐢𝐠𝐞𝐧𝐜𝐞 𝐟𝐨𝐫 𝐌𝐚𝐧𝐮𝐟𝐚𝐜𝐭𝐮𝐫𝐢𝐧𝐠 (𝐈𝐂𝐃𝐌'𝟐𝟓)! More details: linkedin.com/posts/xwang2_r…

We are excited to announce 𝐁𝐞𝐲𝐨𝐧𝐝 𝐂𝐡𝐚𝐭: 𝐕𝐢𝐬𝐮𝐚𝐥 𝐋𝐚𝐧𝐠𝐮𝐚𝐠𝐞𝐬 𝐟𝐨𝐫 𝐄𝐦𝐛𝐨𝐝𝐢𝐞𝐝 𝐇𝐮𝐦𝐚𝐧–𝐋𝐋𝐌 𝐈𝐧𝐭𝐞𝐫𝐚𝐜𝐭𝐢𝐨𝐧 𝐢𝐧 𝐒𝐞𝐧𝐬𝐞𝐦𝐚𝐤𝐢𝐧𝐠 – 𝐀𝐧 𝐈𝐄𝐄𝐄 𝐕𝐋/𝐇𝐂𝐂 𝟐𝟎𝟐𝟓 𝐖𝐨𝐫𝐤𝐬𝐡𝐨𝐩! More details: linkedin.com/posts/xwang2_2…

🚀 We are excited to announce a new tool: 𝗟𝗟𝗠𝗧𝗵𝗶𝗻𝗸𝗕𝗲𝗻𝗰𝗵 — a rigorous and customizable framework to stress-test fundamental mathematical reasoning and overthinking tendencies in language models. Thanks to my MS student, Gaurav Srivastava, for leading this effort!