1/ Excited for our oral presentation at #NeurIPS2023 on "Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation"! A theoretical paper about object-centric representation learning (OCRL), disentanglement & extrapolation arxiv.org/abs/2307.02598

Presenting tomorrow at #EMNLP2023: MAGNIFICo: Evaluating the In-Context Learning Ability of Large Language Models to Generalize to Novel Interpretations w/ amazing advisors and collaborators 🇺🇦 Dzmitry Bahdanau, Siva Reddy, and Satwik Bhattamishra

Adversarial Triggers For LLMs Are 𝗡𝗢𝗧 𝗨𝗻𝗶𝘃𝗲𝗿𝘀𝗮𝗹!😲 It is believed that adversarial triggers that jailbreak a model transfer universally to other models. But we show triggers don't reliably transfer, especially to RLHF/DPO models. Paper: arxiv.org/abs/2404.16020

📢 Exciting new work on AI safety! Do adversarial triggers transfer universally across models (as has been claimed)? 𝗡𝗼. Are models aligned by supervised fine-tuning safe against adversarial triggers? 𝗡𝗼. RLHF and DPO are far better!

Presenting tomorrow at #NAACL2024: 𝐶𝑎𝑛 𝐿𝐿𝑀𝑠 𝑖𝑛-𝑐𝑜𝑛𝑡𝑒𝑥𝑡 𝑙𝑒𝑎𝑟𝑛 𝑡𝑜 𝑢𝑠𝑒 𝑛𝑒𝑤 𝑝𝑟𝑜𝑔𝑟𝑎𝑚𝑚𝑖𝑛𝑔 𝑙𝑖𝑏𝑟𝑎𝑟𝑖𝑒𝑠 𝑎𝑛𝑑 𝑙𝑎𝑛𝑔𝑢𝑎𝑔𝑒𝑠? 𝑌𝑒𝑠. 𝐾𝑖𝑛𝑑 𝑜𝑓. Internship Ai2 work with Pradeep Dasigi and my advisors 🇺🇦 Dzmitry Bahdanau and Siva Reddy.

I am thrilled to announce that I will be joining the Gatsby Computational Neuroscience Unit at UCL as a Lecturer (Assistant Professor) in Feb 2025! Looking forward to working with the exceptional talent at Gatsby Computational Neuroscience Unit on cutting-edge problems in deep learning and causality.

🚨NEW PAPER OUT 🚨 Excited to share our latest research initiative on in-context learning and meta-learning through the lens of Information theory !🧠 🔗 arxiv.org/abs/2410.14086 Check out our insights and empirical experiments! 🔍

📣 📣 📣 Our new paper investigates the question of how many images 🖼️ of a concept are required by a diffusion model 🤖 to imitate it. This question is critical for understanding and mitigating the copyright and privacy infringements of these models! arxiv.org/abs/2410.15002

Presenting ✨ 𝐂𝐇𝐀𝐒𝐄: 𝐆𝐞𝐧𝐞𝐫𝐚𝐭𝐢𝐧𝐠 𝐜𝐡𝐚𝐥𝐥𝐞𝐧𝐠𝐢𝐧𝐠 𝐬𝐲𝐧𝐭𝐡𝐞𝐭𝐢𝐜 𝐝𝐚𝐭𝐚 𝐟𝐨𝐫 𝐞𝐯𝐚𝐥𝐮𝐚𝐭𝐢𝐨𝐧 ✨ Work w/ fantastic advisors 🇺🇦 Dzmitry Bahdanau and Siva Reddy Thread 🧵:

𝐓𝐡𝐨𝐮𝐠𝐡𝐭𝐨𝐥𝐨𝐠𝐲 paper is out! 🔥🐋 We study the reasoning chains of DeepSeek-R1 across a variety of tasks and settings and find several surprising and interesting phenomena! Incredible effort by the entire team! 🌐: mcgill-nlp.github.io/thoughtology/

🚨 New Paper! 🚨 Guard models slow, language-specific, and modality-limited? Meet OmniGuard that detects harmful prompts across multiple languages & modalities all using one approach with SOTA performance in all 3 modalities!! while being 120X faster 🚀 arxiv.org/abs/2505.23856