Hugging Face's logo
PommesPeter's picture
9 16 37

PommesPeter

PommesPeter
HAUZachery's profile picture 21world's profile picture MoonRide's profile picture
Ā·

AI & ML interests

MM-LLM

Recent Activity

updated a model about 5 hours ago
PommesPeter/dp_ckpts
reacted to IliaLarchenko's post with šŸ‘ 2 days ago
I am presenting Decoder-Only Transformer (DOT) Policy a simple Behavioral Control policy that outperforms SOTA models on two simple benchmark tasks: āœ… PushT (pushing an object to a goal) ā€“ 84% success on keypoints, 74% on images (previous best: 75% / 69%) āœ… ALOHA Insert (precise bimanual insertion) ā€“ 30% success (previous best: ~21%) The best part? DOT is much smaller (sometimes 100 times less parameters) than previous SOTA models, trains faster, and avoids complexity: šŸš« No generative models (Diffusion, VAE, GANs) šŸš« No discretization/tokenization of actions šŸš« No reinforcement learning or multi-stage training āœ… Just learns from human demos, plain and simple This is still early ā€” more complex real-life tasks need testing, and no guarantees it will actually work well there, but I think it's interesting to share. Sometimes, simpler approaches can be just as effective (or even better) than complex ones. šŸ”— Open-source code and detailed description: https://github.com/IliaLarchenko/dot_policy Trained models on Hugging Face: https://huggingface.co/IliaLarchenko/dot_pusht_keypoints https://huggingface.co/IliaLarchenko/dot_pusht_images https://huggingface.co/IliaLarchenko/dot_bimanual_insert
reacted to IliaLarchenko's post with šŸ”„ 2 days ago
I am presenting Decoder-Only Transformer (DOT) Policy a simple Behavioral Control policy that outperforms SOTA models on two simple benchmark tasks: āœ… PushT (pushing an object to a goal) ā€“ 84% success on keypoints, 74% on images (previous best: 75% / 69%) āœ… ALOHA Insert (precise bimanual insertion) ā€“ 30% success (previous best: ~21%) The best part? DOT is much smaller (sometimes 100 times less parameters) than previous SOTA models, trains faster, and avoids complexity: šŸš« No generative models (Diffusion, VAE, GANs) šŸš« No discretization/tokenization of actions šŸš« No reinforcement learning or multi-stage training āœ… Just learns from human demos, plain and simple This is still early ā€” more complex real-life tasks need testing, and no guarantees it will actually work well there, but I think it's interesting to share. Sometimes, simpler approaches can be just as effective (or even better) than complex ones. šŸ”— Open-source code and detailed description: https://github.com/IliaLarchenko/dot_policy Trained models on Hugging Face: https://huggingface.co/IliaLarchenko/dot_pusht_keypoints https://huggingface.co/IliaLarchenko/dot_pusht_images https://huggingface.co/IliaLarchenko/dot_bimanual_insert
View all activity

Organizations

ZeroGPU Explorers's profile picture VL-Group's profile picture MagicBot's profile picture