Decision summary
Whole-body action generation
Hardware, latency, dependencies, and checkpoint loading are not pipeline-tested.
Verify weight files, sizes, format, and loading instructions.
Evidence profile
A visual read of adoption evidence. Scores describe catalog evidence readiness, not task performance.
Published evaluation
4/6
dimensions scored
Unknown evidence remains visible and is never treated as a zero.
Why these scores
The strongest decision reasons behind the evidence profile.
Artifact availability
UsefulArtifact availability is declared by the published record; exact files and loadability still require metadata verification.
Training and loading reproducibility
UnknownNo verified loading configuration is available.
Evaluation evidence
UsefulThe source declares evaluation tasks or results.
Data requirements
Declared loop-data needs, missing evidence, and the next checks that matter.
Observation / ego video
observation
Language intent / task phase
language intent · task phase
Action / robot state
actions · robot state
Future state / dynamics
future state
Critical gaps
Core categories are represented. Interface alignment and data quality still require verification.
Evaluation focus
- Structured official evaluation result
Linked datasets
Signal-level links only. Verify runtime interfaces before use.
More evidenceShowHide
Additional data signals
Feedback / correction / failure
Structured official evaluation result
Sim-real / embodiment metadata
robot state
Additional decision dimensions
Access and license are declared by the source.
75 · c85Required signal categories are structured; exact tensor and action interfaces still need verification.
76 · c70Hardware, latency, dependencies, and checkpoint loading are not pipeline-tested.
— · c10Artifact facts
- release_year
- official_claim
- 2026
- curated official source year
- model.required_signals
- official_claim
- observation · future state · language intent · actions · robot state · task phase
- Official model documentation and curated signal mapping
- repository.code
- metadata_verified
- repository: Robbyant/lingbot-vla-v2 · default branch: main · archived: false · code file count: 265 · sample files: deploy/__init__.py · deploy/image_tools.py · deploy/lingbot_vla_v2_policy.py · deploy/msgpack_numpy.py · deploy/utils.py · deploy/websocket_client_policy.py · deploy/websocket_policy_server.py · experiment/__init__.py · lingbotvla/__init__.py · lingbotvla/checkpoint/__init__.py · lingbotvla/checkpoint/checkpointer.py · lingbotvla/checkpoint/format_utils.py · lingbotvla/data/__init__.py · lingbotvla/data/batching_strategy.py · lingbotvla/data/chat_template.py · lingbotvla/data/constants.py · lingbotvla/data/data_collator.py · lingbotvla/data/data_loader.py · lingbotvla/data/data_transform.py · lingbotvla/data/dataset.py
- GitHub repository metadata and recursive tree
- model.hub
- official_claim
- declared
- curated model hub link
- model.training_data
- official_claim
- total hours: 60000 · robot trajectory hours: 50000 · egocentric human video hours: 10000 · robot configurations: 20
- README, Overview
- model.action_schema
- official_claim
- dimensions: 55 · components: arm joints · end-effector pose · grippers · hand joints · waist · head · mobile base
- README, Unified Action Representation
- model.runtime_requirements
- official_claim
- gpu: NVIDIA GeForce RTX 4090D · latency ms: 130 · denoising steps: 10
- README, Real-Robot Deployment
- model.evaluation_results
- official_claim
- model revision: LingBot-VLA 2.0 · benchmark: GM-100 · embodiment: AgileX Cobot Magic · metric: progress_score · value: 66.2 · model revision: LingBot-VLA 2.0 · benchmark: GM-100 · embodiment: AgileX Cobot Magic · metric: success_rate_percent · value: 34.4 · model revision: LingBot-VLA 2.0 · benchmark: GM-100 · embodiment: Galaxea R1Pro · metric: progress_score · value: 34.6 · model revision: LingBot-VLA 2.0 · benchmark: GM-100 · embodiment: Galaxea R1Pro · metric: success_rate_percent · value: 15.6
- README, Performance, GM-100 Bimanual Manipulation
- license.code
- metadata_verified
- Apache-2.0
- GitHub repository SPDX license metadata
- license
- metadata_verified
- Apache-2.0
- GitHub repository SPDX license metadata
- release_timing
- metadata_verified
- 2026-07-07T15:33:12.000Z
- arXiv 2607.06403 published
- discovery.source
- secondary_claim
- name: worldbench/awesome-embodied-data-pyramid · trust: discovery_only · revision: 0568599d0619f20946e8089f6a941d0d9e30b690
- #table-embodied-foundation-models-vla-wam, table 17, row 69
- discovery.raw_fields
- secondary_claim
- Time: 2026.7 · Method: LingbotVLA 2.0 · Institution: Ant Group · Project: [](https://technology.robbyant.com/lingbot-vla-v2) · Model: VLA · Data: ![Real][data-real] ![Ego][data-ego]
- #table-embodied-foundation-models-vla-wam, table 17, row 69
- model.reported_release_time
- secondary_claim
- 2026.7
- #table-embodied-foundation-models-vla-wam, table 17, row 69
- model.type
- secondary_claim
- VLA
- #table-embodied-foundation-models-vla-wam, table 17, row 69
- model.training_data_layers
- secondary_claim
- real_robot · ego_exo
- #table-embodied-foundation-models-vla-wam, table 17, row 69
- model.institution
- secondary_claim
- Ant Group
- #table-embodied-foundation-models-vla-wam, table 17, row 69
- 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 69
Additional references
OpenBot notes
- Track as a release in the LingBot-VLA series rather than an unrelated model.