🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Can AI predict future heart failure risk using low-cost ECGs for global health? 🫀💡 The challenge is: public datasets like UK Biobank have very few recorded HF events, making it hard for AI to learn meaningful patterns. How do we overcome this? 🤔 check out our paper and code!

Swing by our #AAAI2025 poster #826 today at noon to know more about video understanding and computationally efficient video clip localization in scenarios where detecting temporal boundaries is extremely challenging.

2018: Saliency maps give plausible interpretations of random weights, triggering skepticism and catalyzing the mechinterp cultural movement, which now advocates for SAEs. 2025: SAEs give plausible interpretations of random weights, triggering skepticism and ...

I'm really excited that the research funding programme I've been developing is expanding and becoming much bigger! Please share with people you think this might be relevant to

Train your vision SAE on Monday, then again on Tuesday, and you'll find only about 30% of the learned concepts match. ⚓ We propose Archetypal SAE which anchors concepts in the real data’s convex hull, delivering stable and consistent dictionaries. arxiv.org/pdf/2502.12892…

Highly recommend applying! Clare was one of the first people I collaborated with when I’d just started research, and I’ve learnt so much from her. She’s incredibly smart and genuinely kind.

⚠️Beware: Your AI assistant could be hijacked just by encountering a malicious image online! Our latest research exposes critical security risks in AI assistants. An attacker can hijack them by simply posting an image on social media and waiting for it to be captured. [1/6] 🧵

Huawei Research Center Zürich is looking for a Research Scientist intern to work with me on advancing foundation models for computer vision, focusing on enhancing computational photography features in mobile phones. Details below ˙✧˖°📸⋆｡˚

Excited to have Anthropic and Google DeepMind join OpenAI in co-sponsoring our AI Security Institute Agent Red-Teaming Challenge! New wave of challenges out tomorrow 1 pm EDT. Give it a try!

Excited to share that our paper "Bridging the human–AI knowledge gap through concept discovery and transfer in AlphaZero" is now out in PNAS! With Nenad Tomasev, Tom McGrath, Demis Hassabis, Ulrich Paquet, Been Kim 🎉 📄 doi.org/10.1073/pnas.2…

We have a senior postdoc position available with OATML_Oxford (closing 19/05) to lead work on LLM based causal reasoning with GSK. Please share with anyone you think this might be relevant to! my.corehr.com/pls/uoxrecruit…

Our work finding universal concepts in vision models is accepted at #ICML2025!!! My first major conference paper with my wonderful collaborators and friends Matthew Kowal Julian Thomas Fel Kosta Derpanis Working with y'all is the best 🥹 Preprint ⬇️

Our work ConceptAttention was accepted to ICML 2025 as a Spotlight Poster ("top" 2.6% of submissions)! ConceptAttention creates rich saliency maps of text concepts present in generated images and videos. It requires no additional training, only repurposing existing parameters.

If you submitted to ICML and TMLR as an author, where did you get higher review quality (grounded, fair, and helped improve your paper)? 𝐏𝐥𝐞𝐚𝐬𝐞 𝐝𝐞𝐜𝐨𝐮𝐩𝐥𝐞 𝐭𝐡𝐞 𝐮𝐥𝐭𝐢𝐦𝐚𝐭𝐞 𝐟𝐚𝐢𝐭𝐡 𝐨𝐟 𝐩𝐚𝐩𝐞𝐫 𝐟𝐫𝐨𝐦 𝐲𝐨𝐮𝐫 𝐣𝐮𝐝𝐠𝐞𝐦𝐞𝐧𝐭 𝐨𝐟 𝐪𝐮𝐚𝐥𝐢𝐭𝐲.

I hope no one's got a deadline...