23 days ago
-
Publish global128 ant gr00t profile checkpoint and evaluations
-
Publish global128 walker2d gr00t profile checkpoint and evaluations
24 days ago
-
Publish global128 ant openvla profile checkpoint and evaluations
-
Publish global128 hopper gr00t profile checkpoint and evaluations
-
Publish global128 walker2d openvla profile checkpoint and evaluations
-
Publish global128 hopper openvla profile checkpoint and evaluations
-
Remove superseded Ant Hopper Walker2d checkpoints for global128 retraining
-
Publish corrected issued-action hopper gr00t profile model
-
Publish corrected issued-action walker2d gr00t profile model
-
Bind ant Pi0.5 legacy state and actions to the current inference code
-
Bind walker2d Pi0.5 legacy state and actions to the current inference code
-
Bind hopper Pi0.5 legacy state and actions to the current inference code
-
Publish corrected issued-action ant pi05 profile model
-
Publish corrected issued-action walker2d pi05 profile model
-
Publish corrected issued-action hopper pi05 profile model
26 days ago
-
Retire benchmark-datasets root archive and update current artifact references
Codex
27 days ago
-
Repair preserved evaluation references and label unpublished training sources
Codex
-
Repair preserved evaluation references and label unpublished training sources
Codex
-
Prune retired task and training artifacts; retain evaluated checkpoints and repair release references
Codex
-
Publish formal task-transfer and joint-training archive catalogue
-
Consolidate task-transfer assets 1-14
-
Import factor-sweep assets 401-527
-
Import factor-sweep assets 1-400
-
Import factor-sweep assets 1-400
-
Add task-level fine-tuning-scope catalogue and preserve historical comparison limits
-
Complete fine-tuning-scope asset ownership transfer before removing old repositories
-
Add concise experiment navigation and task-level reproducibility manifests
-
Add concise experiment navigation and task-level reproducibility manifests
-
Store identical historical inference checkpoints once and retain per-run metadata
-
Add concise experiment navigation and task-level reproducibility manifests
-
Consolidate paper experiment assets by task and run (1-2)
-
Consolidate paper experiment assets by task and run (451-556)
-
Consolidate paper experiment assets by task and run (301-450)
-
Consolidate paper experiment assets by task and run (151-300)
-
Consolidate paper experiment assets by task and run (1-150)
-
Archive four mean-trained QwenOFT profile-simulation evaluations, 100 episodes each
-
Record manifest-derived robot type in mean-profile portable inference configs
-
Publish completed intercept QwenOFT H1 mean-profile 5000-update run
-
Publish completed ant QwenOFT H1 mean-profile 5000-update run
-
Publish completed deadly_corridor QwenOFT H1 mean-profile 5000-update run
-
Publish completed Intercept H1 RTX3090 mean-profile teacher
-
Publish completed deadly_corridor RTX3090 mean-profile teacher
-
Publish completed ant RTX3090 mean-profile teacher
-
Publish completed Flappy QwenOFT H1 mean-profile 5000-update Blackwell run
-
Add Flappy fixed-mean RTX3090 teacher; evaluation pending
-
Remove Extreme Parkour and HAIC model bundles
-
Import Standard-Pipeline walker2d selected inference bundles
-
Import Standard-Pipeline inverted-pendulum selected inference bundles
-
Import Standard-Pipeline humanoid selected inference bundles
-
Import Standard-Pipeline hopper selected inference bundles
