An effective and universal harness for embodied manipulation
Xirui Li PRO
AIcell
AI & ML interests
Multi-Modality
Recent Activity
upvoted a paper 2 days ago
Decoding Looped Transformers Better for (Almost) Free upvoted a paper 3 days ago
Sharpening Tax in Post-Training upvoted a paper 3 days ago
4Director: Controlling Video World Models with Rigid 3D GeometryOrganizations
models 6
AIcell/Guava-4B
Image-Text-to-Text • 504k • Updated • 48
AIcell/Frankenstein-RL-Frozen-Late
Image-Text-to-Text • 4B • Updated • 18
AIcell/Frankenstein-RL-Frozen-Mid
Image-Text-to-Text • 4B • Updated • 16
AIcell/Frankenstein-RL-Frozen-Early
Image-Text-to-Text • 4B • Updated • 16
AIcell/Frankenstein-RL
Image-Text-to-Text • 4B • Updated • 21
AIcell/Frankenstein-IN
Image-Text-to-Text • 4B • Updated • 12
datasets 8
AIcell/Guava-4B-SFT-data
Updated • 80
AIcell/SPAgent-NonFrozenLake-2K
Updated • 71
AIcell/paper-laundary-test
Updated • 13
AIcell/Auto-ClawEval
Viewer • Updated • 1.04k • 1.14k • 2
AIcell/Auto-ClawEval-mini
Viewer • Updated • 104 • 275
AIcell/war-test-dataset
Viewer • Updated • 1.88k • 113 • 2
AIcell/moltbook-data
Viewer • Updated • 2.13M • 206 • 6
AIcell/MOSSBench
Viewer • Updated • 544 • 1.47k • 6