Adam Hung

Learning from human videos often requires restrictive, carefully choreographed human motions. We propose ✨3PoinTr✨: a scalable way to pretrain from casual human videos. It bridges the embodiment gap by learning 3D scene evolution, enabling learning from natural human motions.

Excited to share SoftAct, a framework for retargeting human manipulation demos to soft robot hands using explicit contact force reasoning! How do you transfer human skill to a hand that looks and moves nothing like yours🐙🖐️? It turns out VR environments can let us capture privileged force interaction demonstrations to help. 🧵1/7

I’m so tired of writing rebuttals to this kind of “lack of novelty” review: “This paper trivially combines A, B, and C, so the algorithmic novelty is limited.” Technically, most (if not all) robotics papers are convex combinations of existing ideas. I still deeply appreciate A+B+C papers—especially when they deliver: - New capabilities: the “trivial combination” unlocks behaviors we simply couldn’t achieve before - Sensible & organic design: A+B+C is clearly the right composition—not some arbitrary A′+B+C′ - Nontrivial interactions: careful analysis of the dynamics, coupling, or failure modes between A, B, C - Rehabilitating old ideas: A was dismissed for years, but paired with modern B/C, it suddenly works—and teaches us why - System-level & "interface" insight: the contribution is not any single piece, but how the pieces talk to each other - Scaling laws or regimes: identifying when/why A+B+C works (and when it doesn’t) - Engineering clarity: making something actually work robustly in the real world is not “trivial” - New problem formulations: sometimes the real novelty is in the reformulation—only under this view does A+B+C make sense. Maybe worth keeping these in mind when reviewing the next A+B+C paper : )

📑Paper: arxiv.org/abs/2603.08485 🌐Website: adamhung60.github.io/3PoinTr/ @CMU_Robotics @SCSatCMU Thank you to collaborators @BDuisterhof and @jeff_ichnowski !! This work was also supported by the NSF GRFP.

By enabling scalable 3D pretraining from casual videos, 3PoinTr takes a step towards future work in making effective use of internet-scale, in-the-wild human interaction data for learning generalist robot policies.

Learning from human videos often requires restrictive, carefully choreographed human motions. We propose ✨3PoinTr✨: a scalable way to pretrain from casual human videos. It bridges the embodiment gap by learning 3D scene evolution, enabling learning from natural human motions.