OpenVLA-OFT+の空間操作と失敗復帰を補う学習データ、および今後公開する追加学習モデル。
YudaiShimanaka
argo11
AI & ML interests
None yet
Organizations
models 24
argo11/openvla-oft-plus-domain-adapted
Robotics • Updated
argo11/parc2026-openvla-oft-plus-base
Robotics • 8B • Updated • 19
argo11/hiro-llm-1
Updated
argo11/hiro-llm-embed768-shakespeare
Updated
argo11/hiro-llm-layers12-smoltalk
Updated
argo11/hiro-llm-layers12-tinystories
Updated
argo11/hiro-llm-layers12-shakespeare
Updated
argo11/hiro-llm-smoltalk
Updated
argo11/hiro-llm-tinystories
Updated
argo11/hiro-llm-shakespeare
Updated
datasets 9
argo11/openvla-oft-plus-robustness-recovery
Viewer • Updated • 3.9k • 85 • 1
argo11/swest28-cross-target-benchmark
Updated • 17
argo11/japanese-math-empirical-difficulty-pilot-50k
Viewer • Updated • 450k • 39
argo11/0399-tv-valid-clean-sft-tokenized-llmjp4-8b
Viewer • Updated • 5.46M • 420
argo11/bio-vla-datasets-local-sync-20260618
Updated • 135
argo11/natori-irodori-tts-dataset
Viewer • Updated • 82k • 216
argo11/app-classification-data
Viewer • Updated • 12.6M • 21
argo11/ipflow-merged
Viewer • Updated • 6.28M • 22
argo11/DNA_DPO_hh-rlhf
Viewer • Updated • 49k • 15