One of the most striking, non-text AI plots I've seen since ChatGPT launched. Scaling keeps working, this time for Waymo's tooling.

Poutine: Vision-Language-Trajectory Pre-Training and Reinforcement Learning Post-Training Enable Robust End-to-End Autonomous Driving. arxiv.org/abs/2506.11234

How can we make behavioural cloning (BC) achieve better combinatorial generalization on out-of-distribution goals? We propose BYOL-γ: an auxiliary self-predictive loss to improve generalization for goal-conditioned BC. 🧵1/6

Why do we keep sampling from the same distribution the model was trained on? We rethink this old paradigm by introducing Feynman-Kac Correctors (FKCs) – a flexible framework for controlling the distribution of samples at inference time in diffusion models! Without re-training

🚨 Excited to share our new work: "Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning"! 📈 We propose gradient interventions that enable stable, scalable learning, achieving significant performance gains across agents and environments! Details below 👇

dr. jack morris Origin of most of these innovations is Canada 🇨🇦 though 😜

🚨Announcing the World Modeling Workshop 2026 🚨 📅 When: Feb 4–6, 2026 📍Where: Mila (Montréal) + Online (free) 💡 What: Keynotes, Methods Deep Dive, and Tutorials 🌐 world-model-mila.github.io ✉️ [email protected] 🧵 Details below:

NO verifiers. NO Tools. Qwen3-4B-Instruct can match DeepSeek-R1 and o3-mini (high) with ONLY test-time scaling. Presenting Recursive Self-Aggregation (RSA) — the strongest test-time scaling method I know of! Then we use aggregation-aware RL to push further!! 📈📈 🧵below!

“GRPO” is just rebranded REINFORCE. Everything “unique” about GRPO like the advantage normalization and (biased) KL regularization are pretty much useless. Kill GRPO. It’s always been REINFORCE.

Waymos are 80% less likely to get into a serious crash than human drivers. An 80% reduction in car crash deaths in the US would mean more lives saved than if you eliminated all homicides. Great piece by Kelsey Piper theargumentmag.com/p/please-let-t…

Waymo is coming to London next year. waymo.com/blog/2025/10/h…

I respect that ICLR 2026 had to respond to the OR leak, but I disagree with resetting scores. Many students worked hard on rebuttals and improved their papers in good faith. I hope the organizers reconsider and revert the reset. If you agree, feel free to retweet.

Today, we are launching GAIA-3 🚀 Our most advanced world model for autonomous driving yet. ⚠️Consider safety-critical scenarios like this. GAIA-3 can evaluate system performance at a scale and richness that real-world testing cannot match. Major advance for safety,

I have a guest essay in The New York Times today about autonomous vehicle safety. I wrote it because I’m tired of seeing children die. Done right, we can eliminate car crashes as a leading cause of death in the United States Waymo recently released data covering nearly 100 million

🚨 New paper! “Understanding Adam Requires Better Rotation-Dependent Assumptions.” Come check out our poster at NeurIPS Conference, or DM me if you would like to chat! 📅 Wednesday, December 3 🕐 4:30 PM PST 📍Exhibit Hall C,D,E #908