🚀 Our method, Poutine, was the best-performing entry in the 2025 Waymo Vision-based End-to-End Driving Challenge at #CVPR2025!. Our 3 B-parameter VLM Poutine scored 7.99 RFS on the official test set—comfortably ahead of every other entry (see figure).

RT @apsarathchandar: @jxmnop Origin of most of these innovations is Canada 🇨🇦 though 😜.

Join millions who have switched to Grok.

RT @creus_roger: 🚨 Excited to share our new work: "Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning"! 📈. We pro….

RT @GlenBerseth: How can we make behavioural cloning (BC) achieve better combinatorial generalization on out-of-distribution goals?. We pro….

RT @OWW: Poutine: Vision-Language-Trajectory Pre-Training and Reinforcement Learning Post-Training Enable Robust End-to-End Autonomous Driv….

RT @k_neklyudov: Why do we keep sampling from the same distribution the model was trained on?. We rethink this old paradigm by introducing….

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

This was joint work with my amazing colleagues at @Mila_Quebec: Rodrigue de Schaetzen, @rogg1111 , @chrisjpal , @duckietown_coo . Check out our report here:

Why did Poutine work?. • Plug-and-play VLM – Built on Qwen 2.5 VL 3B. No custom perception backbone or action headers needed. • Simple and effective training recipe – Self-supervised vision-language-trajectory pre-training followed by lightweight RL preference fine-tuning.

This challenge pushed the limits of vision-based end-to-end planning in rare, long-tail scenarios. We show that VLMs can be repurposed into effective planners in the long-tail.

A residency clause made Québec teams ineligible for prizes, so we couldn’t collect the first-prize—but the challenge organizers awarded us a Special Mention instead. Thanks to the @Waymo challenge organizers for the shout-out!.

RT @emilianopp_: Excited that our paper "Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization" was a….

RT @majdi_has: (1/n)🚨You can train a model solving DFT for any geometry almost without training data!🚨. Introducing Self-Refining Training….

RT @nandahkrishna: New preprint! 🧠🤖.How do we build neural decoders that are:.⚡️ fast enough for real-time use.🎯 accurate across diverse ta….

RT @antho_gosselin: 🚗💥Introducing Ctrl-Crash: controllable video generation for autonomous driving! SOTA models struggle to generate physic….

RT @benjamintherien: Is AdamW the best inner optimizer for DiLoCo? Does the inner optimizer affect the compressibility of the DiLoCo delta?….

RT @ShashwatGoel7: Confused about recent LLM RL results where models improve without any ground-truth signal? We were too. Until we looked….

RT @joanrod_ai: Thanks @_akhaliq for sharing our work! Excited to present our next generation of SVG models, now using Reinforcement Learni….

RT @siddarthv66: Is there a universal strategy to turn any generative model—GANs, VAEs, diffusion models, or flows—into a conditional sampl….

RT @xichen_pan: We find training unified multimodal understanding and generation models is so easy, you do not need to tune MLLMs at all. M….