Yay!

Fantastic research group meeting today at Johns Hopkins University Bloomberg Center. We then went to see the Cherry Blossoms. We also saw Stumpy!

Process supervision for reasoning is 🔥! While previous approaches often relied on human annotation and struggled to generalize across different reasoning tasks, we're now asking: Can we improve this? Introducing 𝐑𝐀𝐓𝐈𝐎𝐍𝐀𝐋𝐘𝐒𝐓: a new model pre-trained on implicit

🚀 Thrilled to announce SAFR is here! #NAACL2025 Superposition is powerful — but it buries interpretability. We control that! 🧠 Neurons often mix too many features (superposition) — making models a black box. 🎯 SAFR strategically redistributes neurons: · 🧩 Monosemantic for

Excited to present our work at #NAACL2025!

Just Graduated:) Big thanks to all my family and friends who are always there for me!

Thank you so much Mark! Couldn't have done all of this without your help and support! ❤️

There have been various efforts on disentangling "task learning" vs "task recall" in LLMs. We've recently explored a fresh angle by borrowing from cryptography: with substitution ciphers, we transform a given task into an equivalent, but cryptic (no pun intended!!) forms.

I’m at #ICML this week !🍁🍁🍁 Hanjie Chen and I will present the work on Wed 4:30 pm poster session (July 16th), feel free to stand by if you are also interested in steering & controlling! 😃

Our work on readability evaluation for Plain Language Summarization will appear at #EMNLP2025!! Daniel Khashabi 🕊️ Mark Dredze Paper: arxiv.org/pdf/2508.19221 TLDR: Traditional readability metrics correlate poorly with human judgements & LMs consider deeper readability features. 1/6

Our paper is accepted to the main conference of #EMNLP2025! Check the post for more details!