-
SRPO: Self-Referential Policy Optimization for Vision-Language-Action Models
Paper • 2511.15605 • Published • 25 -
VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulators
Paper • 2510.00406 • Published • 69 -
RLDX-1 Technical Report
Paper • 2605.03269 • Published • 127 -
MolmoAct2: Action Reasoning Models for Real-world Deployment
Paper • 2605.02881 • Published • 267
Philipp Neldel
Philmat
AI & ML interests
None yet
Organizations
None yet
VLA
-
SRPO: Self-Referential Policy Optimization for Vision-Language-Action Models
Paper • 2511.15605 • Published • 25 -
VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulators
Paper • 2510.00406 • Published • 69 -
RLDX-1 Technical Report
Paper • 2605.03269 • Published • 127 -
MolmoAct2: Action Reasoning Models for Real-world Deployment
Paper • 2605.02881 • Published • 267
models 26
Philmat/picko-v17_pi0-3
Robotics • 4B • Updated • 6
Philmat/picko-v17_pi0-1
Robotics • 4B • Updated • 6
Philmat/picko-v17_pi0-0
Robotics • 4B • Updated • 6
Philmat/picko-v17-3_smolvla-3
Robotics • 0.5B • Updated • 5
Philmat/picko-v17_smolvla-3
Robotics • 0.5B • Updated • 6
Philmat/picko-v17_smolvla-5
Robotics • 0.5B • Updated • 8
Philmat/picko-v17_smolvla-4
Robotics • 0.5B • Updated • 12
Philmat/picko-v17_smolvla-3_bup
Robotics • 0.5B • Updated • 13
Philmat/picko-v18_smolvla-0
Robotics • 0.5B • Updated • 11
Philmat/picko-v17_smolvla-2
Robotics • 0.5B • Updated • 11
datasets 51
Philmat/picko-v17-merged
SO-100 • Updated • 170 episodes • 53
Philmat/picko-v15
SO-100 • Updated • 10 episodes • 37
Philmat/picko-v14
SO-100 • Updated • 150 episodes • 64
Philmat/picko-v16
SO-100 • Updated • 10 episodes • 43
Philmat/picko-v17
SO-100 • Updated • 170 episodes • 87
Philmat/picko-v18
SO-100 • Updated • 14 episodes • 49
Philmat/picko-v13
SO-100 • Updated • 100 episodes • 67
Philmat/picko-v12
SO-100 • Updated • 50 episodes • 33
Philmat/picko-v11
SO-100 • Updated • 50 episodes • 9
Philmat/picko-v10
SO-100 • Updated • 50 episodes • 60