's Avatar

@roxpetcu.bsky.social

Mechanistic Interpretability for Retrieval and Reasoning. PhD student at IRLab Amsterdam 🌧️

207 Followers  |  63 Following  |  2 Posts  |  Joined: 18.11.2024
Posts Following

Posts by (@roxpetcu.bsky.social)

Redirect

📅 𝗜𝗺𝗽𝗼𝗿𝘁𝗮𝗻𝘁 𝗜𝗻𝗳𝗼
- Submission deadline: April 17th, 2026 (23:59 AoE)
- Paper Notification: May 21st, 2026 (23:59 AoE)
- Submission details: scai.info (to be updated)

📚 𝗣𝘂𝗯𝗹𝗶𝗰𝗮𝘁𝗶𝗼𝗻
Papers will be published in the SIGIR 2026 proceedings.

18.02.2026 12:00 — 👍 0    🔁 0    💬 0    📌 0
Redirect

📣𝗦𝗖𝗔𝗜@𝗦𝗜𝗚𝗜𝗥 𝟮𝟬𝟮𝟲: The 10th Workshop on Search-Oriented Conversational AI

🎯𝗪𝗼𝗿𝗸𝘀𝗵𝗼𝗽
Celebrating 10 years of SCAI, we explore advances in conversational AI, focusing on personalized conversational search, including a featured session of the iKAT shared task.

18.02.2026 11:59 — 👍 4    🔁 2    💬 1    📌 0
Post image

Sentences are partially understood before they're fully read. How do LMs incrementally interpret their inputs?

In a new paper, @amuuueller.bsky.social and I use mech interp tools to study how LMs process structurally ambiguous sentences. We show LMs rely on both syntactic & spurious features! 1/10

19.12.2024 13:40 — 👍 71    🔁 15    💬 1    📌 3
PhD Position in Mechanistic Interpretability PhD Position in Mechanistic Interpretability

🚨 PhD position alert! 🚨

I'm hiring a fully funded PhD student to work on mechanistic interpretability at @uva-amsterdam.bsky.social. If you're interested in reverse engineering modern deep learning architectures, please apply: vacatures.uva.nl/UvA/job/PhD-...

02.12.2024 19:36 — 👍 21    🔁 11    💬 0    📌 1
Preview
ESSIR 2024 - Talks Monday - July 1st

Currently writing up a report on the IR summer school that we organized here in Amsterdam. The lectures are publicly available and provide a great introduction to anyone interested in IR. Thought I'd share: 2024.essir.eu/talks

18.11.2024 11:29 — 👍 18    🔁 5    💬 1    📌 0