admin
0 Followers · 0 Following
  • Joined on 2026-03-24
Repositories
2
 Projects Packages Public Activity Starred Repositories
admin synced commits to refs/heads/auto/update-uv-lock at admin/lerobot from mirror 2026-05-20 11:10:01 +00:00
8ad6193549 chore(dependencies): update uv.lock
dfdc48a7f1 fix(datasets): bound VideoDecoderCache to prevent OOM on large datasets (#3614)
6a8878a639 fix(datasets): normalize shape=(1,) numeric values before HF encoding (#3344)
d38eb89f71 feat(video re-encoding): Adding utility and dataset edition tool for video re-encoding (#3611)
7ab4936b1b Add extensive language support (#3467)
Compare 6 commits »
admin synced commits to refs/heads/feat/language-annotation-pipeline at admin/lerobot from mirror 2026-05-20 11:10:01 +00:00
a0233f53f4 feat(annotate): default VLM to Qwen3.6-35B-A3B-FP8
admin synced commits to refs/heads/feat/smolvla-on-steerable at admin/lerobot from mirror 2026-05-20 02:59:50 +00:00
75507491bf fix(pi052): VQA <loc> conversion treats coords as 0-1000 normalized
88519cb14c fix(pi052): quantile-normalize actions before FAST tokenizer fit
bc0c993b25 fix(pi052): FAST tokenizer fit read actions from column, not ds[i]
ddf4bc2063 fix(pi052): knowledge insulation crashed on wrong _gated_residual import
b7317b6c29 test(pi052): round-trip coverage for VQA <loc> conversion
Compare 5 commits »
admin synced commits to refs/heads/feat/smolvla-on-steerable at admin/lerobot from mirror 2026-05-19 18:49:54 +00:00
c026aed8f8 feat(pi052): train VQA spatial answers in PaliGemma <loc> format
e425dfd624 fix(processor): fallback to task message when recipe misses
15f79b5e5e fix(pi052): supervise an EOS token at the end of each text target
725ac95b0d feat(runtime): make the interactive runtime drive PI052 too
7b64e5498d revert(annotate): move memory + speech prompts to base PR (#3471)
Compare 6 commits »
admin synced commits to refs/heads/feat/add-topreward-rm at admin/lerobot from mirror 2026-05-19 18:49:54 +00:00
admin synced new reference refs/heads/feat/add-topreward-rm to admin/lerobot from mirror 2026-05-19 18:49:54 +00:00
admin synced commits to refs/heads/feat/language-annotation-pipeline at admin/lerobot from mirror 2026-05-19 18:49:54 +00:00
2ea0da2d9f fix(annotate): tag uploaded dataset revision
134a707c7a feat(annotate): first-person memory narrative + shorter speech prompts
ce47075d6b feat(annotate): deterministic plan, single-frame VQA, dataset tagging
26013da699 feat(annotations): enforce imperative verb-first subtask phrasing
Compare 4 commits »
admin synced and deleted reference refs/heads/feat/language-columns at admin/lerobot from mirror 2026-05-19 18:49:54 +00:00
admin synced and deleted reference refs/heads/feat/video-re-encode at admin/lerobot from mirror 2026-05-19 18:49:54 +00:00
admin synced commits to refs/heads/main at admin/lerobot from mirror 2026-05-19 18:49:53 +00:00
dfdc48a7f1 fix(datasets): bound VideoDecoderCache to prevent OOM on large datasets (#3614)
6a8878a639 fix(datasets): normalize shape=(1,) numeric values before HF encoding (#3344)
d38eb89f71 feat(video re-encoding): Adding utility and dataset edition tool for video re-encoding (#3611)
7ab4936b1b Add extensive language support (#3467)
ca8c60a0ed Set OpenCV fourcc after size and fps (#3620)
Compare 5 commits »
admin synced commits to refs/heads/auto/update-uv-lock at admin/lerobot from mirror 2026-05-19 10:40:07 +00:00
addd0b5385 chore(dependencies): update uv.lock
3c15fd8537 feat(robots): natively integrate Seeed Studio reBot B601-DM arm (#3624)
5ebbdf3d05 Mention the new Lance LeRobotDataset implementation in the docs (#3609)
6e035fb169 Update reward config and model card template (#3625)
Compare 4 commits »
admin synced commits to refs/heads/fix/fix-and-maintain-examples at admin/lerobot from mirror 2026-05-19 10:40:05 +00:00
e927217b80 fix formatting
ad215f6d45 update information on dataset resuming
bfa7fc6762 fix teleop command
Compare 3 commits »
admin synced commits to refs/heads/feat/smolvla-on-steerable at admin/lerobot from mirror 2026-05-19 02:29:47 +00:00
bb31988915 fix(pi052): pass 4d masks to prefix-only forwards
2629175d2d fix(pi05): use fused AdamW by default
2b4c5f49e3 fix(pi05): disable foreach AdamW by default
22c9c4905e fix(pi052): avoid dense CE over padded tokens
Compare 4 commits »
admin synced and deleted reference refs/heads/claude/wizardly-goodall-6ef748 at admin/lerobot from mirror 2026-05-18 18:20:11 +00:00
admin synced and deleted reference refs/heads/fix/reward-config-modelcard-update at admin/lerobot from mirror 2026-05-18 18:20:11 +00:00
admin synced commits to refs/heads/feat/smolvla-on-steerable at admin/lerobot from mirror 2026-05-18 18:20:10 +00:00
7960cc14ec fix(pi052): call policy preprocessing helpers
1750a87104 fix(pi052): handle batched rendered messages
0e2dc1b76f fix(pi052): supervise only FAST action-code tokens
474c5478d9 tune(annotations): VQA emission anchors a single frame (K 3 -> 1)
0f5f0e4091 refactor(recipes): rename recipes, drop pi05_hirobot
Compare 16 commits »
admin synced commits to refs/heads/feat/vla-jepa at admin/lerobot from mirror 2026-05-18 18:20:10 +00:00
ed6978fd18 removing missleading future_action_window_size to just use chunk_size
4e85e23350 allow different state dim and action dim
1642a14ae5 trying out to re-init the action head to avoid pretraining dimension mismatch
e9c171ead0 make default params more aligned with paper and pretrained models
Compare 4 commits »
admin synced commits to refs/heads/feat/language-annotation-pipeline at admin/lerobot from mirror 2026-05-18 18:20:10 +00:00
f72b28738a fix(annotate): default keyframe decode to ffmpeg CLI (thread-safe)
1bd53cc7da fix(annotate): decode keyframes via ffmpeg CLI fallback
7128bb1769 fix(annotate): decode keyframes via PyAV directly
31e0c15e55 fix(annotate): pyav fallback when torchcodec keyframe decode fails
c5676ef1b3 feat(annotate): add dest_repo_id for separate push target
Compare 7 commits »
admin synced new reference refs/heads/feat/depth-frames to admin/lerobot from mirror 2026-05-18 18:20:09 +00:00
admin synced commits to refs/heads/main at admin/lerobot from mirror 2026-05-18 18:20:09 +00:00
3c15fd8537 feat(robots): natively integrate Seeed Studio reBot B601-DM arm (#3624)
5ebbdf3d05 Mention the new Lance LeRobotDataset implementation in the docs (#3609)
6e035fb169 Update reward config and model card template (#3625)
Compare 3 commits »