I'm excited to share our latest work “Representation Learning Enables Scalable Multitask Deep Reinforcement Learning”. In this work, we revisit a fundamental question in reinforcement learning: What if representation learning was the key ingredient behind scalable RL? 1/🧵

Show Post

I will be at @icmlconf.bsky.social in Seoul over the next week - first time in South Korea and at ICML so looking forward to an exciting week! I'll be co-presenting our work on PIDMs for offline imitation learning - Poster Session 7 - Hall A #304 - Thu, Jul 9 at 2:30pm - details 👇 See you there!

Show Post

🚀 Imperial NLP is heading to #ACL2026 & #ICML2026 with 23 papers! From reasoning and agents to interpretability, RL, safety, and healthcare models, our students & faculty have been busy. Come find us in San Diego 🌴 and Seoul 🇰🇷 to talk research, swap ideas, and say hi!

Show Post

At #NeurIPS2025 today, @lisaalaz.bsky.social is presenting our joint paper on Reverse Engineering Human Preferences with Reinforcement Learning! Demonstrating undetectable attacks on LLM-as-a-judge benchmarks. Great collaboration with @cohereforai.bsky.social and a well-deserved NeurIPS spotlight!

Show Post

The Myth of "XGBoost is All You Need" – And Why Evidence Says Otherwise Kaggle fairytales 🧚‍♀️ - “XGBoost is all you need” But reality—backed by large-scale benchmarks—tells a completely different story.

Show Post