Meet BFM-Zero: A Promptable Humanoid Behavioral Foundation Model w/ Unsupervised RL👉 🧩ONE latent space for ALL tasks ⚡Zero-shot goal reaching, tracking, and reward optimization (any reward at test time), from ONE policy 🤖Natural recovery & transition

How it works 👉 🧠 Unsupervised RL — no specific rewards in training 🔁 Forward–Backward Representation — builds a dynamics-aware space 🎯 Zero-shot Inference — reach goals, track motions, or optimize any reward function at test time without retraining

Goal Reaching: z = B(s_g) (🤔B can be viewed as "inverse dynamics" that maps from a desired state to a needed latent skill) See how natural it can be 👇:

Reward Optimization: z = \sum_i B(s_i)r(s_i) We do not have any labeled rewards in training ! In the test time, users can prompt in ANY type of reward w.r.t. the robot states, and the policy zero-shot output the optimized skills without retraining.

Motion Tracking: z = \sum_n \lambda_n B(s_{t+n}) (this can be viewed as a "moving horizon" (or MPC) version of goal tracking) Diverse motion tracking + natural & smooth recovery even under unexpected falls🫣

🌿 Smooth & well-regulated space enables: 1️⃣ Natural recovery under disturbance (it even runs a few steps🦿to regain balance when pushed🫱!) 2️⃣ Search-based few-shot adaptation 3️⃣ Meaningful latent-space interpolation See more details in our website~

Deeply grateful to @zhengyiluo — a dream collaboration😍; to the Motivo [link: team at @AIatMeta for making this possible; to @TongheZhang01 @JimmyDai218776 @ElijahGalahad for the countless late nights; and to @GuanyaShi @teopir for the invaluable advice.

Great work, Yitang 👍

this is extremely cool work! and really nicely presented demos

BFM-Zero deploys sim-to-real robustness perfectly for advanced manufacturing. UAE’s Jafza should test this-zero-shot adaptability is a game-changer. I'd love to see German engineers pilot it in their robotics hubs.

@LeCARLab Can we put it in ?

hi Yitang Li

This is cool