Why we can often prune very large neural networks after training?
Excited to share an early version of my new paper "It's not a Lottery, it's a Race: Understanding How Gradient Descent Adapts the Network's Capacity to the Task". https://t.co/KZ6EdCcsUI
🔥 We're looking for a brilliant AI Research Engineer - it's honestly an amazing opportunity to build LLMs from scratch and entirely in the open. 💖 We're also looking for 2 PhD students and 2 Postdocs on the same project!
🚀Apply now!
https://t.co/cmvs4fxmr7
❣️Please share ❣️
Achieving your goals is impossible without being part of a great team! It feels amazing to be in front of thousands of researchers at @NeurIPSConf, knowing there are outstanding people who have your back.
🥳With 13 contributions, our members will again be very busy in Vancouver! #NeurIPS2024
We're hiring!🚀Looking for a PhD, an engineering position, or do you want to be an assistant professor? https://t.co/PH3o9A6YzZ or come talk to us @pechenizkiy@joavanschoren
🚀 Ready to push the boundaries of #AI & #ML? We're hiring 7(!) brilliant PhDs, PostDocs, and Engineers to work on cutting-edge #LLMs#AutoML#ContinualLearning @TUeindhoven
🌟 Think big and shape the future of AI!
🧑💻 Apply now! https://t.co/cmvs4fwOBz
❣️Please share❣️
🧵 1/6
PhD position RL.
Are you eager to work on #AI safety, unleashing the potential of #RL?
I'm #hiring a PhD student to work on #RL while exploring relevant areas of #ML to tackle challenges in partial observability and safety. @Data_AI_TUe @TUeindhoven
https://t.co/Wd5jNickPQ
The #SciLake 3rd Project Plenary kicks off this morning at @TUeindhoven , hosted by the @Data_AI_TUe cluster and @SciLake_project . Looking forward to a productive and stimulating meeting together!
🥳Wieger Punter, Odysseas Papapetrou and Minos Garofalakis received the best paper award at VLDB this year!
Check out OmniSketch, the first efficient sketch for multidimensional streaming analytics with arbitrary predicate combinations https://t.co/THFAHC41Gv.
Jiarong is currently presenting his (spotlight! 🎉) work called MALIBO at #ICML2024, with co-authors Stefan Falkner, Felix Berkenkamp, and @joavanschoren.
🥳Our group members are presenting 13 papers at ICML, see https://t.co/BnJko2uioH
Recently, I have been getting more interested in #GenerativeAISystems (#GenAISys). I am convinced that a systems-based perspective on #GenAI is crucial to design more reliable, robust, and responsive #GenAI.
You can read my perspective here: https://t.co/cDHZarP6OB
💡Which information about the dataset does a simple CNN, trained with GD, store in its parameters? Only the most important frequencies, through a winner-takes-all process!
Judging from my body language, I was trying hard to get the message across 😅 https://t.co/Bt4Jjikfzr
PhD position alert! We (Wil Michiels from the security group and I) are looking for a PhD candidate, working on trustworthy and secure AI with a focus on OOD detection at TU Eindhoven (Netherlands). You can apply here:
https://t.co/k9RgAnxCdm