Pith. sign in

REVIEW 3 cited by

Learning the RoPEs: Better 2D and 3D Position Encodings with STRING

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2502.02562 v1 pith:TJSS3BR2 submitted 2025-02-04 cs.LG cs.AIcs.CVcs.ROstat.ML

Learning the RoPEs: Better 2D and 3D Position Encodings with STRING

Connor Schenck , Isaac Reid , Mithun George Jacob , Alex Bewley , Joshua Ainslie , David Rendleman , Deepali Jain , Mohit Sharma
show 14 more authors
Avinava Dubey Ayzaan Wahid Sumeet Singh Ren\'e Wagner Tianli Ding Chuyuan Fu Arunkumar Byravan Jake Varley Alexey Gritsenko Matthias Minderer Dmitry Kalashnikov Jonathan Tompson Vikas Sindhwani Krzysztof Choromanski
This is my paper
classification cs.LG cs.AIcs.CVcs.ROstat.ML
keywords stringencodingspositionroboticstokenalgorithmanalysisarbitrary
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We introduce STRING: Separable Translationally Invariant Position Encodings. STRING extends Rotary Position Encodings, a recently proposed and widely used algorithm in large language models, via a unifying theoretical framework. Importantly, STRING still provides exact translation invariance, including token coordinates of arbitrary dimensionality, whilst maintaining a low computational footprint. These properties are especially important in robotics, where efficient 3D token representation is key. We integrate STRING into Vision Transformers with RGB(-D) inputs (color plus optional depth), showing substantial gains, e.g. in open-vocabulary object detection and for robotics controllers. We complement our experiments with a rigorous mathematical analysis, proving the universality of our methods.

discussion (0)

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

Forward citations

Cited by 3 Pith papers

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

  1. Group Representational Position Encoding

    cs.LG 2025-12 unverdicted novelty 7.0

    GRAPE unifies RoPE and ALiBi as special cases of group actions on positions, providing a principled design space for positional encodings via SO(d) rotations and GL unipotent transformations.

  2. Elastic Attention Cores for Scalable Vision Transformers

    cs.CV 2026-05 unverdicted novelty 6.0

    VECA learns effective visual representations using core-periphery attention where patches interact exclusively via a resolution-invariant set of learned core embeddings, achieving linear O(N) complexity while maintain...

  3. CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining

    cs.RO 2026-01 unverdicted novelty 6.0

    CLAMP pretrains 3D multi-view encoders with contrastive learning on point clouds and actions, then initializes diffusion policies for more sample-efficient fine-tuning on robotic tasks.