Pith. sign in

REVIEW 5 cited by

MetaMorph: Learning Universal Controllers with Transformers

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2203.11931 v1 pith:CMLMHQLG submitted 2022-03-22 cs.LG cs.NEcs.RO

MetaMorph: Learning Universal Controllers with Transformers

classification cs.LG cs.NEcs.RO
keywords robotmorphologieslargemetamorphtaskcontrollerdemonstratedesign
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Multiple domains like vision, natural language, and audio are witnessing tremendous progress by leveraging Transformers for large scale pre-training followed by task specific fine tuning. In contrast, in robotics we primarily train a single robot for a single task. However, modular robot systems now allow for the flexible combination of general-purpose building blocks into task optimized morphologies. However, given the exponentially large number of possible robot morphologies, training a controller for each new design is impractical. In this work, we propose MetaMorph, a Transformer based approach to learn a universal controller over a modular robot design space. MetaMorph is based on the insight that robot morphology is just another modality on which we can condition the output of a Transformer. Through extensive experiments we demonstrate that large scale pre-training on a variety of robot morphologies results in policies with combinatorial generalization capabilities, including zero shot generalization to unseen robot morphologies. We further demonstrate that our pre-trained policy can be used for sample-efficient transfer to completely new robot morphologies and tasks.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Knowledge Reutilization in Meta-Reinforcement Learning

    cs.AI 2026-06 unverdicted novelty 6.0

    A meta-RL framework learns task-level knowledge on dynamics-simplified agents, organizes modes with Bayesian non-parametrics, and transfers via interfaces to heterogeneous agents, reporting 94.75-99.79% tracking error...

  2. EmbodiSteer: Steering Embodiment-Agnostic Visuomotor Policies with Joint-Space Guidance for Zero-Shot Cross-Embodiment Deployment

    cs.RO 2026-06 unverdicted novelty 6.0

    EmbodiSteer steers embodiment-agnostic Cartesian diffusion policies into joint space with Jacobian-based collision guidance after each denoising step for zero-shot cross-embodiment deployment.

  3. Any2Any: Efficient Cross-Embodiment Transfer for Humanoid Whole-Body Tracking

    cs.RO 2026-05 unverdicted novelty 6.0

    Any2Any transfers pretrained humanoid whole-body tracking policies to new embodiments with 1% of original training cost via kinematic alignment and parameter-efficient fine-tuning.

  4. Any2Any: Efficient Cross-Embodiment Transfer for Humanoid Whole-Body Tracking

    cs.RO 2026-05 unverdicted novelty 5.0

    Any2Any transfers humanoid whole-body tracking models across embodiments via kinematic alignment followed by targeted PEFT, matching full-training performance with 1% of the data and compute on tested platforms.

  5. OmniGen2: Towards Instruction-Aligned Multimodal Generation

    cs.CV 2025-06 unverdicted novelty 5.0

    OmniGen2 introduces a unified generative model with two distinct decoding pathways and a decoupled image tokenizer that achieves competitive results on text-to-image and editing benchmarks plus state-of-the-art consis...