davidwdw/fa-historical-generated-audit-tree-136fb4414839
Updated
wang
davidwdw
AI & ML interests
None yet
Recent Activity
new activity about 3 hours ago
The-North-Star-Team/behavior-2026-rollouts:Task26 c49 public 301-320 (Q 0.690625) updated a dataset 2 days ago
davidwdw/t73-eval-c33r-train28-e61524bc6a57 published a dataset 2 days ago
davidwdw/t73-eval-c33r-train28-e61524bc6a57Organizations
davidwdw/fa-eval-task00-recovery-development-20260922-eai-6c3a23f5dcd0
Updated
davidwdw/fa-b1k-task00-recovery-native-smoke-fc49e43e43fb-0f4a2729eaae
Updated
davidwdw/fa-b1k-task00-recovery-inputs-d1639891c14b-859863b00943
Updated
davidwdw/fa-ckpt-t00-mix-prepressfix-52999-8c4462b07bfd
Updated
davidwdw/fa-ckpt-t00-mix-pressfix-audit-20260923t1940-35d2ba1d3bd1
Updated
davidwdw/fa-ckpt-t00-codegen-pressfix-latest-at-seal-5990b9e2eef1
Updated
davidwdw/fa-historical-smoke-h20-metadata-6c90dc944c7d
Updated
davidwdw/fa-historical-alphabet-soup-lora-metadata-9d37b8f9902a
Updated
davidwdw/fa-historical-alphabet-soup-lora-new-metadata-aa2a4545bc8d
Updated
davidwdw/fa-attnfix-balanced-8000-resumable-66ad4bea4f2d
Updated
davidwdw/fa-ckpt-b1k-task00-mix-h50-c50-14999-60a35dc84878
Updated
davidwdw/fa-pi05-attnfix-balanced-5000-fad3174c6b88-4e4e743d3a05
Updated
davidwdw/fa-report-task00-task01-source-gap-70a83f25a26d-12a8d9181435
Updated
davidwdw/fa-code-task00-recovery-f0112812a74f-5f88dee7bae0
Updated
davidwdw/fa-report-recipe-summary-9aa2e7ee8d35-7084e4dffad4
Updated
davidwdw/fa-report-dataset-audit-56f629d22efd-5e0eb3cb915f
Updated
davidwdw/fa-report-action-distribution-0a9ce1a7f9ca-aadf13ca3ae7
Updated
davidwdw/fa-ckpt-b1k-task00-codegen-success-14999-6ea3ad0d61f7
Updated
davidwdw/fa-ckpt-b1k-task00-human-14999-b70ceca3e24b
Updated
davidwdw/fa-task63-candidate18-producer-selected-6291b5d29213
Updated
davidwdw/fa-source-2026-09-22-b1k-task00-pi05-tail-balanced-h20-f8ea5f074569
Updated
davidwdw/fa-source-2026-09-22-b1k-task00-pi05-attention-consistent-73e8360aa59e
Updated
davidwdw/b1k_model
Robotics • Updated
davidwdw/fa-base-pi05-base-a6112dcb8ea7
Updated
davidwdw/rlinf_libero_vla
Reinforcement Learning • Updated