Claas Voelcker
@c_voelcker
"All models are wrong, but some are useful" "Do not disfigure the soul" - PhD candidate @UofT, RL researcher unfocused on too many things, he/him, 🏳️🌈
Announcing our EXAIT@ICML workshop paper: CURATE! Have a difficult target task distribution with sparse rewards that you want to train an RL agent to complete? 🤔 We tackle this problem using our curriculum learning algorithm, CURATE. 🎓 Link: openreview.net/forum?id=mAeQu… 1/6
Beyond today's Vector Bytes spotlights, our researchers are presenting additional groundbreaking work at #ICML2025 across three key areas: 🚀 Efficient AI systems - Boyu Wang's FedOne dramatically reduces costly cloud-based LLM queries by activating only one client per…
Shoutout to my current and former students (@c_voelcker @avery__ma @tylerkastnr @rom72aba Yangchen Pan), student collaborators (@AnastasiiaPedan @aahmadian_), and senior collaborators (@robinphysics Mark Rowland @igilitschenski @MuratAErdogdu). I spot two of them in these photos!
Beyond today's Vector Bytes spotlights, our researchers are presenting additional groundbreaking work at #ICML2025 across three key areas: 🚀 Efficient AI systems - Boyu Wang's FedOne dramatically reduces costly cloud-based LLM queries by activating only one client per…
Throwing final things together for Vancouver, polishing a very drafty poster, and finalizing a very promising paper draft (stay tuned 😎). Don't know if I should be super excited or scream 😂 Let me know if you are at @icmlconf and want to grab a coffee and chat about RL!
Come join us for our @icmlconf social! Hang out with us in beautiful Vancouver in just under 2 weeks time!
1/ 💻 Queer in AI is hosting a social at #ICML2025 in Vancouver on 📅 July 16, and you’re invited! Let’s network, enjoy food and drinks, and celebrate our community. Details below…
🚀Our paper on LLM jailbreaking has been accepted as a spotlight poster at ICML2025! 🐼PANDAS: Improving Many-shot Jailbreaking via Positive Affirmation, Negative Demonstration, and Adaptive Sampling Collaboration with Yangchen Pan and Amir massoud Farahmand @sologen. (1/n)
Would you be surprised that many empirical implementations of value-aware model learning (VAML) algos, including MuZero, lead to incorrect model & value functions when training stochastic models 🤕? In our new @icml_conf 2025 paper, we show why this happens and how to fix it 🦾!
In Germany, there is a tradition of creating funny hats for doctoral graduates. 🎓 @c_voelcker brought this tradition to my group and, together with @JainUmangi, spearheaded the construction of a masterpiece for our first PhD graduate, @ashmrz10. 1/2
Today I relearned the most important lesson in RL: The answer is ALWAYS REPS 😂 @Jan_R_Peters First RL lesson I ever learned