🔥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

Identifying the true structure of the latent data generating process (causal world model) by learning from passive observation alone is impossible without reasonable priors, which transformers don’t have. This is why LLMs are brittle and can’t reliably do counter factual

You only live once (probably). So go off the beaten path. Take some risks. Don't waste time. Define your own future. There are too many people just gravitating towards what everyone else is doing.

The recording of our talk for the ICLR'24 test-of-time award (with Max Welling) is now available online: iclr.cc/virtual/2024/t… Biggest live audience I've ever spoken to, with >2000 attendees 😅. But it was a lot of fun!

I'll take this chance to promote two of my recent weekend SLURM projects, which are now adopted internally by my lab! 🚀 🦥 lazyslurm - TUI for monitoring and filtering jobs in the SLURM queue. 🐌 SLIME - plugin for automatically sizing GPU jobs to maximise utilisation. 🧵1/5

📢 New publication to be presented at #MICCAI2024! 💪 A semi-supervised causal generative model for learning from a range of partially annotated data settings. 👀 Check out our research: arxiv.org/abs/2403.18717 #causalml #medicalimaging (1/4)

Congratulation to Mélanie Roschewitz for receiving the British Federation of Women Graduates Margaret and Martin Gotheridge Award for disease detection research!🎉 imperial.ac.uk/news/255137/do… #Computing #AI #STEM BFWG

Looking for PhD candidates interested in exploring multi-modal AI for healthcare! If you or someone you know is curious about this opportunity, feel free to reach out. More info about me and the team: cherise215.github.io

📢 New preprint on finding good representations for Visual Question Answering! We focus in particular on object-centric (OC) learning – since its role in downstream tasks is still partially underexplored – and on pretrained foundation models. 📄 arxiv.org/abs/2407.15589 🧵👇

I’m thrilled to announce that my paper has been accepted at #UNSURE2024 at #MICCAI2024! Check out the video below where I give a summary of my findings! Keep an eye out next week for a full-length post where I’ll dive deeper into the work and what’s next!

Grateful for the warm reception at the #CausalAI Conference ! Honoured to share how #CausalSystemDesign draws parallels between Aristotle’s 4 Causes, NASA TRLs & Pearls causal modelling to transform AI. #AIInnovation #AIforBusiness

🎉Thrilled to share our paper "Benchmarking Counterfactual Image Generation" is accepted to NeurIPS Conference 2024!🌟 A big shoutout to my co-first authors Nikos Spyrou, nefeligk and our amazing team: Pedro P. Sanchez, Athanasios (Thanos) Vlontzos, PhD, Yannis Panagakis, Giorgos Papanastasiou & Sotirios (Sotos) Tsaftaris! 🙌

A common question nowadays: Which is better, diffusion or flow matching? 🤔 Our answer: They’re two sides of the same coin. We wrote a blog post to show how diffusion models and Gaussian flow matching are equivalent. That’s great: It means you can use them interchangeably.

Why do NNs often learn similar representations? Existing identifiability results offer theoretical insights, but applying them in practice poses challenges. We’ll present our new work exploring these challenges next week at UniReps #NeurIPS2024 🇨🇦🎉 openreview.net/pdf?id=SQKUZSi… 1/

Everything old is new again. Mamba/ssm folks should really google their "new idea + lstm" please. About a decade ago, people have tried a shitton of things with lstms. Nothing wrong with retrying with modern tools, but ack the past. This is not the first such case I see btw.

If your learning algorithm is based on correlation rather than causation, it will struggle with overfitting. To understand something is to identify its minimal sufficient causal mechanisms. Parsimony isn't just elegance, it's generalization robustness.

We REALLY REALLY need a "Findings" for NeurIPS, ICLR, and ICML. 25,000 submissions at this year's NeurIPS represents extreme excess pressure. It takes valuable time away from legitimate new research. One question is how to administer it. I suggest that Findings go through a

Why work on medical AI? It's one of the most impactful usecases of AI, it's as simple as that. If you want to work on something meaningful instead of using AI to optimize for clicks/revenue/engagement/etc., consider working on medical AI!

I like the resurgence of "old-school" NFs that is happening. Here to distill CNFs for free-energy estimation. RL x.com/GhugareRaj/sta… Diffusion models (NFDM) x.com/GrigoryBartosh… Latent SDEs (SDE Matching) x.com/canaesseth/sta… #SDE #Diffusion #GenAI #ML #FlowMatching

I like em dashes, and I hate that some people now take them as evidence of text being AI generated.