ydy0615
0 Followers · 0 Following
  • Joined on 2025-12-26
Repositories
5
 Projects Packages Public Activity Starred Repositories
ydy0615 synced commits to main at ydy0615/lerobot-clone from mirror 2026-05-30 02:11:25 +00:00
b8ad81bf39 feat(rewards): add ROBOMETER reward model (#3627)
ydy0615 synced and deleted reference refs/tags/feat/add-robometer-rm at ydy0615/lerobot-clone from mirror 2026-05-30 02:11:25 +00:00
ydy0615 synced commits to feat/vla-jepa at ydy0615/lerobot-clone from mirror 2026-05-29 18:01:25 +00:00
ac9128b319 fixing simlink
61d82a5773 adding configuration gripper index and threshold
d8ed30d58c removing swish in favor of silu
79f6756505 cleanup
7a98c56ce4 removing useless pre-processor
Compare 7 commits »
ydy0615 synced commits to feat/add-robometer-rm at ydy0615/lerobot-clone from mirror 2026-05-29 18:01:25 +00:00
9036186a25 feat(rewards/robometer): add image key argument to compute Robometer progress
7be8aecc19 doc(rewards/robometer): update citation and original github link
28693f9089 Merge branch 'main' into feat/add-robometer-rm
24017e960c Add MolmoAct2 policy (#3604)
e86f5af5bf feat(rewards): add TOPReward reward model (#3629)
Compare 20 commits »
ydy0615 synced commits to feat/vla-jepa at ydy0615/lerobot-clone from mirror 2026-05-28 17:31:29 +00:00
c2b29c8ae0 removing conversion script
58eac863aa fixing misconception about multiview / singleview handling
952e5146dc smol fix to avoid having default CPU device when training
37fda2a6fc adding instructions for different embodiement + fixing some tests
df7d5132d1 fix qwen norm layer output libero eval is now as expected
Compare 39 commits »
ydy0615 synced new reference fix/topreward-docs-symlink to ydy0615/lerobot-clone from mirror 2026-05-28 01:11:25 +00:00
ydy0615 synced commits to fix/topreward-docs-symlink at ydy0615/lerobot-clone from mirror 2026-05-28 01:11:25 +00:00
ydy0615 synced commits to main at ydy0615/lerobot-clone from mirror 2026-05-27 17:01:27 +00:00
24017e960c Add MolmoAct2 policy (#3604)
e86f5af5bf feat(rewards): add TOPReward reward model (#3629)
Compare 2 commits »
ydy0615 synced commits to feat/vla-jepa at ydy0615/lerobot-clone from mirror 2026-05-27 17:01:27 +00:00
ea738a20c0 fixing misconception about multiview / singleview handling
ydy0615 synced commits to feat/smolvla-on-steerable at ydy0615/lerobot-clone from mirror 2026-05-27 17:01:27 +00:00
1f1541243a pi052: make `lerobot-eval` work on saved checkpoints
ydy0615 synced and deleted reference refs/tags/feat/add-topreward-rm at ydy0615/lerobot-clone from mirror 2026-05-27 17:01:27 +00:00
ydy0615 synced commits to auto/update-uv-lock at ydy0615/lerobot-clone from mirror 2026-05-27 08:51:25 +00:00
6b647fee2c chore(dependencies): update uv.lock
5c98e80430 fix(gr00t): fix Eagle25VL model and processor crash in transformers>=5.4.0, <5.6.0 (#3652)
f65f3f7a4a Fix policy.path in YAML configs (PR #3145 followup) (#3597)
Compare 3 commits »
ydy0615 synced commits to main at ydy0615/lerobot-clone from mirror 2026-05-26 16:31:27 +00:00
5c98e80430 fix(gr00t): fix Eagle25VL model and processor crash in transformers>=5.4.0, <5.6.0 (#3652)
f65f3f7a4a Fix policy.path in YAML configs (PR #3145 followup) (#3597)
Compare 2 commits »
ydy0615 synced commits to feat/vla-jepa at ydy0615/lerobot-clone from mirror 2026-05-26 16:31:27 +00:00
5e2c4c22c8 Merge branch 'main' into feat/vla-jepa
1a536d1f71 smol fix to avoid having default CPU device when training
5c98e80430 fix(gr00t): fix Eagle25VL model and processor crash in transformers>=5.4.0, <5.6.0 (#3652)
f65f3f7a4a Fix policy.path in YAML configs (PR #3145 followup) (#3597)
d09410882d adding instructions for different embodiement + fixing some tests
Compare 10 commits »
ydy0615 synced commits to feat/smolvla-on-steerable at ydy0615/lerobot-clone from mirror 2026-05-26 16:31:27 +00:00
d70c810416 pi052: drop `use_hf_kernels` flag — always patch Liger kernels
4c3ddb1ff5 pi052: wire Liger fused linear CE + DDP-safe FAST tokenizer fit
8615f3f613 annotate(vqa): tighten bbox + keypoint quality bar
Compare 3 commits »
ydy0615 synced new reference docs/complete-docs-redesign to ydy0615/lerobot-clone from mirror 2026-05-26 16:31:27 +00:00
ydy0615 synced commits to docs/complete-docs-redesign at ydy0615/lerobot-clone from mirror 2026-05-26 16:31:27 +00:00
ydy0615 synced new reference chore/add-dependabot-github-actions to ydy0615/lerobot-clone from mirror 2026-05-26 16:31:27 +00:00
ydy0615 synced commits to chore/add-dependabot-github-actions at ydy0615/lerobot-clone from mirror 2026-05-26 16:31:27 +00:00
ydy0615 synced commits to feat/smolvla-on-steerable at ydy0615/lerobot-clone from mirror 2026-05-26 08:21:24 +00:00
2686450d68 annotate(plan): force composite-action subtasks; tune run_hf_job for robocasa_smoke