R
ROBBYANT / robbyant/lingbot-touch-small

LingBot-Touch-Small

Robbyant JEPA encoder for magnetic, piezoresistive and visuotactile signals. It turns normalized measurements into representations that other models can use to interpret contact during manipulation.

01 / SUMMARY

The essential

ORIENTATIONTactile perception encoder

Primary use stated or inferred cautiously from official documentation.

CONTEXTFive-finger sequences

Maximum input capacity when published by the source.

EXITVectors with spatiotemporal addresses

Documented maximum generation limit.

ACCESSHugging Face · downloadable checkpoint

Verified availability channels.

MODEL TYPERobotics

Primary functional family and verified specialties.

LICENSEApache 2.0

Declared terms for API access, model weights, or self-hosting.

02 / TECHNICAL SHEET

Limits and integration

API IDrobbyant/lingbot-touch-small
Model typeRobotics
Access modelOpen weights
LicenseApache 2.0
DeploymentSelf-hosted
Release09 NOV 2026
Knowledge cutoffNot published
EntranceNormalized tactile signals
ExitTactile representations
Context windowFive-finger sequences
maximum outputVectors with spatiotemporal addresses
ReasoningNot published
Published tools
Structured OutingsNot published
Batch processingNot published
Prompt cacheNot published
Fine-tuningNot published
Verified platformsHugging Face · ModelScope · PyTorch
BEST SUITED FOR

Extract tactile features using the 21.76-million-parameter HaT-Small encoder. The bundle includes frozen weights and their inference configuration.

WORTH MONITORING

Visuotactile input uses scalar measurements derived from the sensor. The bundle accepts no raw RGB images and contains no robot control policy. Integration requires adapting each sensor’s geometry and ranges.

03 / CAPABILITIES

What it can do

01

Orientation

Extract tactile features using the 21.76-million-parameter HaT-Small encoder. The bundle includes frozen weights and their inference configuration.

02

Context

Five-finger sequences · Vectors with spatiotemporal addresses

03

Tools and integration

Not published

04

Access

Hugging Face · downloadable checkpoint

Input modalities
Normalized tactile signals
04 / PRICES

Documented cost

ConceptWorthUnit/condition
Standard inputNo published official API rateStandard API rate
Cached inputNot publishedReading reused prefixes
Cache write or storageNot publishedThe condition varies by provider
Standard outputSelf-hosted infrastructure costMay include reasoning tokens
Batch inputNot publishedAsynchronous processing
Batch outputNot publishedAsynchronous processing

Weights are distributed under Apache 2.0. The developer publishes inference code separately and does not announce a commercial API for these checkpoints.

i Prices change and may depend on level, region or context length. Check the source before making a decision.

05 / EVALUATIONS

How to read the results

“

The project reports experiments across 26 physical and 12 simulated manipulation tasks. Results for policies that use tactile features do not represent the success rate of the encoder alone.

i Integrated policy results in the technical report.

Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.

06 / VERSIONS

Chronology

LingBot-Touch-Small

Encoder weights and inference configuration.

07 / SOURCES

Traceability