VLAClosed / referencedReadiness 52/100Provisional

InternVLA-A1

Shanghai AI Lab

InternVLA-A1: Unifying Understanding, Generation, and Action for Robotic Manipulation

Code: Available
Weights: Unverified
Checkpoint: Unverified
License: Unverified

Code Model index A–Z

Decision summary

Best for

Model research and source verification

Main blocker

Training data requirements are not structured enough for reliable dataset matching.

Next check

Verify repository and artifact licenses.

Release history

Source-backed release timing for this canonical model record.

Important releases

No source-backed day-level release event is recorded yet. The model remains in the Catalog without an inferred date.

Selection readiness

Evidence dimensions for deciding whether this model is ready to inspect, compare, or adopt. Scores describe catalog evidence, not task performance.

Published evaluation

How scores work

52/100

Provisional

1/6 dimensions scored · 15% confidence

Access and governanceNot scoredconf. 20

Artifact availability52conf. 20

Training and loading reproducibilityNot scoredconf. 15

Training data requirementsNot scoredconf. 15

Evaluation evidenceNot scoredconf. 10

Deployment readinessNot scoredconf. 10

Engineering checks (OBRS) behind this record

Engineering checksBronze

Needs Audit

0/12checks passed

OBRS metadata and reported test evidence. A breakdown behind Selection readiness, not a separate score or an independent OpenBot certification.

Standardization & Loaders2 / 25 pt

Physical & Action Quality2 / 25 pt

Semantic & Annotation4 / 20 pt

Real-World Validation0 / 15 pt

License & Compliance0 / 15 pt

Missing evidence and readiness gaps

A passing real-hardware test report is required.
A passing ingestion/pipeline test report is required.
A passing privacy and provenance review is required.

Why these scores

The strongest decision reasons behind Selection readiness.

Top 3 adoption signals

Artifact availability

Useful

Code availability is declared; repository files and public weights are not verified.

52 · confidence 20

Training and loading reproducibility

Unknown

No verified loading configuration is available.

— · confidence 15

Evaluation evidence

Unknown

No structured evaluation evidence has been verified.

— · confidence 10

Data requirements

Declared loop-data needs, missing evidence, and the next checks that matter.

3 required categories

Observation / ego video

Needs visual observations or other state streams before this model direction is actionable.

required

Language intent / task phase

Needs task intent, instructions, keysteps, or phase labels to connect behavior to goals.

required

Action / robot state

Descriptive model record

required

Future state / dynamics

Needs future-state supervision or rollout structure to validate predictive dynamics.

useful

Critical gaps

Observation / ego video: Needs visual observations or other state streams before this model direction is actionable.
Language intent / task phase: Needs task intent, instructions, keysteps, or phase labels to connect behavior to goals.

Linked datasets

Signal-level links only. Verify runtime interfaces before use.

Browse datasets

No related catalog datasets are linked to this model yet.

More evidenceShow

Additional data signals

Feedback / correction / failure

Needs success, failure, correction, or recovery signals to turn evaluation into better data.

useful

Sim-real / embodiment metadata

Descriptive model record

useful

Additional decision dimensions

Access and governanceUnknown

License or access terms are not verified.

— · c20

Training data requirementsUnknown

Training data requirements are not structured enough for reliable dataset matching.

— · c15

Deployment readinessUnknown

Hardware, latency, dependencies, and checkpoint loading are not pipeline-tested.

— · c10

Artifact facts

discovery.source: secondary_claim; name: worldbench/awesome-embodied-data-pyramid · trust: discovery_only · revision: 0568599d0619f20946e8089f6a941d0d9e30b690; #table-embodied-foundation-models-vla-wam, table 17, row 38
discovery.raw_fields: secondary_claim; Time: 2026.1 · Method: InternVLA-A1 · Institution: Shanghai AI Lab · Project: [![Website](https://img.shields.io/badge/Website-0A7DBD)](https://github.com/InternRobotics/InternVLA-A1) · Model: VLA · Data: ![Real][data-real] ![Ego][data-ego] ![Sim][data-sim]; #table-embodied-foundation-models-vla-wam, table 17, row 38
model.reported_release_time: secondary_claim; 2026.1; #table-embodied-foundation-models-vla-wam, table 17, row 38
model.type: secondary_claim; VLA; #table-embodied-foundation-models-vla-wam, table 17, row 38
model.training_data_layers: secondary_claim; real_robot · ego_exo · simulation; #table-embodied-foundation-models-vla-wam, table 17, row 38
model.institution: secondary_claim; Shanghai AI Lab; #table-embodied-foundation-models-vla-wam, table 17, row 38
catalog.curation: secondary_claim; tier: editorial_focus · collection: WorldBench Awesome Embodied Data Pyramid · policy: human_curated_priority; #table-embodied-foundation-models-vla-wam, table 17, row 38