Tessera
Folgen

Tom Schaul

@schaul.bsky.social

RL researcher at DeepMind https://schaul.site44.com/ 🇱🇺

35 Posts3335 Follower307 Folgt
Katrina Manson@katrinamanson.bsky.social · 3mo ago

Exclusive: More than 580 Google workers including hundreds of AI researchers urge CEO Sundar Pichai to refuse classified military AI work, after senior Pentagon official tells me he is already in talks with Google. Our story on Bloomberg now, from me and Julia Love

Reinforcement Learning Conference@rl-conference.bsky.social · 5mo ago

Only ~7 days to go until the full paper deadline (Mar 5, AOE)! Wishing everyone a strong close to the submission cycle.

Reinforcement Learning Conference@rl-conference.bsky.social · 6mo ago

Quick reminder for everyone grinding on their RLC 2026 papers, only ~3 weeks to go! The submission site opens in just a few days (Feb 17). Deadlines: ⏳ March 1 (AoE): Abstract Submission ⏳ March 5 (AoE): Full Paper Submission Good luck with the final changes!

Tom Schaul@schaul.bsky.social · 9mo ago

Could we meta-learn which data to train on? Yes! Does this make LLM training more efficient? Yes! Would you like to know exactly how? arxiv.org/pdf/2505.17895 (come see us at NeurIPS too!)

arxiv.org

Luisa Zintgraf@luisazintgraf.bsky.social · 9mo ago

Excited to share our new paper, "DataRater: Meta-Learned Dataset Curation"! We explore a fundamental question: How can we *automatically* learn which data is most valuable for training foundation models? Paper: arxiv.org/pdf/2505.17895 to appear at @neuripsconf.bsky.social Thread 👇

Tom Schaul@schaul.bsky.social · last yr.

When faced with a challenge (like debugging) it helps to think back to examples of how you've overcome challenges in the past. Same for LLMs! The method we introduce in this paper is efficient because examples are chosen for their complementarity, leading to much steeper inference-time scaling! 🧪

Aditi Mavalankar@aditimavalankar.bsky.social · last yr.

Excited to share our recent work, AuPair, an inference-time technique that builds on the premise of in-context learning to improve LLM coding performance! arxiv.org/abs/2502.18487 🧵

Tom Schaul@schaul.bsky.social · 2y ago

Could language games (and playing many of them) be the renewable energy that Ilya was hinting at yesterday? They do address two core challenges of self-improvement -- let's discuss! My talk is today at 11:40am, West Meeting Room 220-222, #NeurIPS2024 language-gamification.github.io/schedule/

Tom Schaul@schaul.bsky.social · 2y ago

Are there limits to what you can learn in a closed system? Do we need human feedback in training? Is scale all we need? Should we play language games? What even is "recursive self-improvement"? Thoughts about this and more here: arxiv.org/abs/2411.16905

Tom Schaul@schaul.bsky.social · 2y ago

This year's (first-ever) RL conference was a breath of fresh air! And now that it's established, the next edition is likely to be even better: Consider sending your best and most original RL work there, and then join us in Edmonton next summer!

Reinforcement Learning Conference@rl-conference.bsky.social · 2y ago

The call for papers for RLC is now up! Abstract deadline of 2/14, submission deadline of 2/21! Please help us spread the word. rl-conference.cc/callforpaper...

Tom Schaul@schaul.bsky.social · 2y ago

Are there limits to what you can learn in a closed system? Do we need human feedback in training? Is scale all we need? Should we play language games? What even is "recursive self-improvement"? Thoughts about this and more here: arxiv.org/abs/2411.16905

Boundless Socratic Learning with Language Games

An agent trained within a closed system can master any desired capability, as long as the following three conditions hold: (a) it receives sufficiently informative and aligned feedback, (b) its covera...

arxiv.org