Divya Appapogu retweeted
馃摙 Excited to share our #EMNLP2026 Main paper, co-led by @yukyunglee_ and me! 馃帀
AI-generated text shows a consistent stylometric footprint across models and domains, while AI-edited text shows a different pattern.
馃敆Paper: arxiv.org/pdf/2608.27855
Divya Appapogu retweeted
馃毃 NEMI decisions are out!
Be sure to check your spam folder for the decision email, as a few have ended up there.
Looking forward to seeing you at NEMI! 馃帀
Silico has been great for poking around model internals.
Divya Appapogu retweeted
The NEMI workshop registration deadline is today, July 27th! Last chance to sign up to meet New England鈥檚 mech interp community, including Rhett the Terrier, who鈥檚 using J-Space to learn what LLMs think when he begs them for treats. Link in thread 馃憞
Divya Appapogu retweeted
The NEMI crew are entering the boat parade at Sail Boston while we wait for the mech interp abstracts to sail in on August 1
Divya Appapogu retweeted
Excited to share that our paper, Automatic RL Env generation was accepted to #COLM2026!
This is my first publication, which makes it especially meaningful! See you at San Francisco!
Huge thanks to @sethkarten!
Divya Appapogu retweeted
馃馃 The 2026 New England Mechanistic Interpretability (NEMI) Workshop will be Aug. 14 at Boston University!
Help spread the word and join the New England mech interp community! Registration and submission info in thread:馃憞
Divya Appapogu retweeted
How do language models track entities across state changes? When tracking objects in different boxes, do they cumulatively build up a global state of what鈥檚 in every box? How do they add objects or remove objects (i.e. Entity Unbinding)? Find out in our ICML paper! 馃У
Divya Appapogu retweeted
Singular vectors of the attention QK matrix align with features!
This has been found empirically in other works, like Talking Heads from @jack_merullo_. We show theoretically and empirically how and why.
New @icmlconf 2026 paper with Carson Loughridge and @mcrovella.















