Jennifer Neville (@profjenneville) 's Twitter Profile
Jennifer Neville

@profjenneville

Professor, Computer Science & Statistics, Purdue University, Research interests: machine learning, data mining, network science, artificial intelligence.

ID: 101561169

linkhttps://jenneville.github.io calendar_today03-01-2010 20:09:55

367 Tweet

2,2K Followers

448 Following

Bruno Ribeiro (@brunofmr) 's Twitter Profile Photo

Research news: Want to boost the expresiness of your favorite GNN architecture? Collective learning can help: a hybrid GNN representation with Hang & Jennifer Neville arxiv.org/abs/2003.12169 GCNs (@thomaskipf, Max Welling ) benefit the most (up to +15% in accuracy)!

Jennifer Neville (@profjenneville) 's Twitter Profile Photo

Congratulations to Dr. Changping (Jason) Meng for his successful PhD defense today on “Scalable Representation Learning with Invariances” (coadvised with Bruno Ribeiro). Hope Purdue will have a graduation in the summer so we can celebrate with him in person!

Dr. Giselle Zeno (@giselle_zeno) 's Twitter Profile Photo

Online presentation for our paper, with Timothy La Fond and Jennifer Neville, "Dynamic Network Modeling from Motif-Activity" is now available: youtu.be/snuAUPgIRas #MAISoN2020 #TheWebConf The Web Conference

Jennifer Neville (@profjenneville) 's Twitter Profile Photo

This didn’t make me feel as hopeful as I think it was supposed to, but happy to learn about Lynn Conway and add her to my list of female role models in CS. forbes.com/sites/jeremyal…

Jennifer Neville (@profjenneville) 's Twitter Profile Photo

👏Congratulations to Dr. Mahak Goindani for her successful PhD defense today on “Social Reinforcement Learning”! I can't believe she's already the third student from my lab to do a virtual defense during this pandemic and she won't be the last.

WiML (@wimlworkshop) 's Twitter Profile Photo

We are looking forward to welcoming you to the 15th Women in Machine Learning (#WiM2020) Virtual Workshop on Wednesday, December 9th. The full *program book*, including details of all the sessions, can be found here: bit.ly/2KA7MS9 #WiML NeurIPS Conference #NeurIPS2020

We are looking forward to welcoming you to the 15th Women in Machine Learning (#WiM2020) Virtual Workshop on Wednesday, December 9th. 

 The full *program book*, including details of all the sessions, can be found here: bit.ly/2KA7MS9

#WiML <a href="/NeurIPSConf/">NeurIPS Conference</a> #NeurIPS2020
Jennifer Neville (@profjenneville) 's Twitter Profile Photo

Wish I could hear discussions with Google mentors at WiML mentoring round tables later today, particularly table 14 with Jeff Dean #ISupportTimnit

Jennifer Neville (@profjenneville) 's Twitter Profile Photo

Excited to announce that I will be joining Microsoft Research in Redmond in June. Looking for an intern for this summer, if you are interested in graph learning with neural networks apply at link below and let me know. Microsoft Research careers.microsoft.com/us/en/job/9349…

Dr. Giselle Zeno (@giselle_zeno) 's Twitter Profile Photo

Just presented my paper "DYMOND: DYnamic MOtif-NoDes Network Generative Model" at The Web Conference, co-authored with Timothy La Fond and Jennifer Neville. Recording here: youtu.be/sp2sv4zl3CI #TheWebConf #WWW21

Philippe Laban (@philippelaban) 's Twitter Profile Photo

🆕paper: LLMs Get Lost in Multi-Turn Conversation In real life, people don’t speak in perfect prompts. So we simulate multi-turn conversations — less lab-like, more like real use. We find that LLMs get lost in conversation. 👀What does that mean? 🧵1/N 📄arxiv.org/abs/2505.06120

🆕paper: LLMs Get Lost in Multi-Turn Conversation

In real life, people don’t speak in perfect prompts.
So we simulate multi-turn conversations — less lab-like, more like real use.

We find that LLMs get lost in conversation.
👀What does that mean? 🧵1/N
📄arxiv.org/abs/2505.06120
Kiran Tomlinson (@kiran_tomlinson) 's Twitter Profile Photo

New paper from my group at Microsoft Research! 📄arxiv.org/abs/2507.07935 Promises about how AI will change work are cheap. What does the actual data say? We measured which work activities people use AI for, how successful they are, and which jobs do those tasks. 🧵1/8

Towards Data Science (@tdatascience) 's Twitter Profile Photo

Your 1M+ context window LLM might be less powerful than you think. Tobias Schnabel's new article reveals working memory as a critical bottleneck for LLMs. towardsdatascience.com/your-1m-contex…

Kiran Tomlinson (@kiran_tomlinson) 's Twitter Profile Photo

🤔 Why do LLMs fail on some tasks and not others? Our paper (arxiv.org/abs/2505.08140) gives a theoretically grounded explanation: some reasoning problems need more information-tracking than LLMs can handle. The details get ✨lost in transmission✨ between attention heads. 🧵 1/8

🤔 Why do LLMs fail on some tasks and not others?
Our paper (arxiv.org/abs/2505.08140) gives a theoretically grounded explanation: some reasoning problems need more information-tracking than LLMs can handle.
The details get ✨lost in transmission✨ between attention heads. 🧵 1/8
Jie He (@jiehenlp) 's Twitter Profile Photo

I couldn’t make it to #ACL2025, but excited to share our paper GenTool from Microsoft Research and The University of Edinburgh! aclanthology.org/2025.findings-… We introduce GenTool: a training framework that simulates zero-to-one and weak-to-strong tool transitions to boost tool generalization in LLMs.

Jennifer Neville (@profjenneville) 's Twitter Profile Photo

For those AI researchers who have recently (re)entered the job market, just a reminder that our team— AI Interaction and Learning at Microsoft Research Redmond—is currently hiring multiple ML/AI researchers. jobs.careers.microsoft.com/global/en/job/… jobs.careers.microsoft.com/global/en/job/…