Skip to content
AI News HubLIVE
Original source2 min read

PhysMoE: Fast Spatial Grounding with Single-Token Coordinate Representation in Modality-Decoupled VLMs

Summary

PhysMoE introduces a novel architecture with modality-decoupled Mixture-of-Experts, single-token coordinate encoding, and differentiable SDF supervision, addressing bottlenecks in coordinate prediction for embodied VLMs and achieving 15.7% average gain and 8.31x throughput speedup on 9 grounding benchmarks.

SourcearXiv Computer VisionAuthor: Ruimeng Liu, Denan Liang, Ruofei Bai, Fuming Zhang, Kuan Xu, Shenghai Yuan, Lihua Xie
PhysMoE: Fast Spatial Grounding with Single-Token Coordinate Representation in Modality-Decoupled VLMs
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 8 Nov 2026]

Title:PhysMoE: Fast Spatial Grounding with Single-Token Coordinate Representation in Modality-Decoupled VLMs

View a PDF of the paper titled PhysMoE: Fast Spatial Grounding with Single-Token Coordinate Representation in Modality-Decoupled VLMs, by Ruimeng Liu and 5 other authors

View PDF HTML (experimental)

Abstract:Embodied Vision-Language Models (VLMs) are backbones for robotic planning and manipulation. However, for coordinate prediction in grounding tasks, existing architectures suffer from two distinct bottlenecks: discrete tokenization disrupts spatial continuity with high decoding latency, while standard point regression fails on multi-contact affordances and irregularly shaped targets. To resolve these challenges, we propose PhysMoE, introducing three core contributions: (1) sharing lower layers for multimodal context while routing upper layers to specialized spatial (pixel) and linguistic (text) experts by physical modality, eliminating gradient interference; (2) encoding each coordinate as a single token by reusing the visual encoder's learned positional embeddings, injecting 2D spatial priors to natively align coordinates with visual features and ease training; and (3) differentiable Signed Distance Field (SDF) supervision on pointing, accommodating affordances and irregular geometries without costly mask decoders. Compared to the base model, PhysMoE achieves a 15.7% average gain and an 8.31x throughput speedup across 9 coordinate-based grounding benchmarks (trajectory, affordance, and localization), while preserving multimodal understanding and reasoning across 11 text-based embodied benchmarks.

Subjects:

Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Robotics (cs.RO)

Cite as: arXiv:2611.13000 [cs.CV]

(or arXiv:2611.13000v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2611.13000

arXiv-issued DOI via DataCite

Submission history

From: Ruimeng Liu [view email] [v1] Sun, 8 Nov 2026 16:00:02 UTC (969 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled PhysMoE: Fast Spatial Grounding with Single-Token Coordinate Representation in Modality-Decoupled VLMs, by Ruimeng Liu and 5 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.CV

new | recent | 2026-11

Change to browse by:

cs cs.AI cs.RO

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Modality-decoupled MoE architecture shares lower layers and routes upper layers to spatial or linguistic experts, eliminating gradient interference.
  • Coordinates are encoded as single tokens by reusing the visual encoder's positional embeddings, injecting 2D spatial priors.
  • Differentiable Signed Distance Field (SDF) supervision handles irregular shapes and affordances without costly mask decoders.
  • PhysMoE achieves 15.7% average gain and 8.31x throughput speedup across 9 coordinate-based grounding benchmarks while preserving multimodal understanding.

Highlights and analysis are generated automatically and may contain errors. Check the original source.