John Zhou

Can language models learn useful priors without ever seeing language? We pre-pre-train transformers on neural cellular automata — fully synthetic, zero language. This improves language modeling by up to 6%, speeds up convergence by 40%, and strengthens downstream reasoning. Surprisingly, it even beats pre-pre-training on natural text! Blog: hanseungwook.github.io/blog/nca-pre-p… (1/n)

Action chunking is drawing growing interest in RL, yet its theoretical properties are still understudied. We are excited to share some insights on when we should use action chunking in Q-learning + a new algo (DQC) to tackle hard long-horizon tasks!colinqiyangli.github.io/dqc🧵1/N

Very excited to finally share what I’ve been up to @physical_int for the past 6 months: developing advantage-conditioned VLAs! We are finally moving beyond imitating teleop data, and towards improving models with suboptimal deployment data using scalable real-world RL. 👇🧵

Don't miss our Embodied AI group's session this week on November 21st with @sshchang for a presentation on "FLAM: Scaling Latent Action World Models with Factorization." Thanks to @nahidalam and Cole Harrison for organizing this event! ✨ Learn more: cohere.com/events/cohere-…

Offline reinforcement learning is crucial for robotics, but does it scale? We talk to @seohong_park , who discusses how for long-horizon manipulation problems the answer may be no — at least not yet. But there are tricks that you can use to make it work effectively. Watch episode #38 of RoboPapers with @micoolcho and @chris_j_paxton now!

Hierarchical methods for offline goal-conditioned RL (GCRL) can scale to very distant goals that stymie flat (non-hierarchical) policies — but are they really necessary? Paper: arxiv.org/abs/2505.14975 Project page: johnlyzhou.github.io/saw/ Code: github.com/johnlyzhou/saw Thread ↓