nvidia/QLIP-B-8-256
Updated
•
10
•
1
mexicanamerican PRO
mexicanamerican
AI & ML interests
None yet
Recent Activity
liked
a model
about 9 hours ago
nvidia/QLIP-B-8-256
liked
a Space
about 10 hours ago
Kwai-Kolors/Kolors-Virtual-Try-On
liked
a Space
about 10 hours ago
Nymbo/Serverless-ImgGen-Hub
Organizations
mexicanamerican's activity
liked
a
model
about 9 hours ago
liked
6
Spaces
about 10 hours ago
7.23k
Kolors Virtual Try-On
👕
Virtual try-on for clothes on a person
147
Serverless ImgGen Hub
♨
Highly hackable hub w/ Flux, SD 3.5, LoRAs, no GPUs required
44
Caracal
🔥
A simple app for doing HTR with various models.
1.72k
Voice Clone
🗣
Clone voice to say text
38
ColPali Multi Output
🔍
Generate retrieval queries from a document image
39
FLUX 3D StyleGEN R1
🖼
Fast & High Quality Mode
reacted to
IliaLarchenko's
post with 🔥
about 10 hours ago
Post
959
I am presenting Decoder-Only Transformer (DOT) Policy a simple Behavioral Control policy that outperforms SOTA models on two simple benchmark tasks:
✅ PushT (pushing an object to a goal) – 84% success on keypoints, 74% on images (previous best: 75% / 69%)
✅ ALOHA Insert (precise bimanual insertion) – 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:
🚫 No generative models (Diffusion, VAE, GANs)
🚫 No discretization/tokenization of actions
🚫 No reinforcement learning or multi-stage training
✅ Just learns from human demos, plain and simple
This is still early — 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.
🔗 Open-source code and detailed description: https://github.com/IliaLarchenko/dot_policy
Trained models on Hugging Face:
IliaLarchenko/dot_pusht_keypoints
IliaLarchenko/dot_pusht_images
IliaLarchenko/dot_bimanual_insert
✅ PushT (pushing an object to a goal) – 84% success on keypoints, 74% on images (previous best: 75% / 69%)
✅ ALOHA Insert (precise bimanual insertion) – 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:
🚫 No generative models (Diffusion, VAE, GANs)
🚫 No discretization/tokenization of actions
🚫 No reinforcement learning or multi-stage training
✅ Just learns from human demos, plain and simple
This is still early — 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.
🔗 Open-source code and detailed description: https://github.com/IliaLarchenko/dot_policy
Trained models on Hugging Face:
IliaLarchenko/dot_pusht_keypoints
IliaLarchenko/dot_pusht_images
IliaLarchenko/dot_bimanual_insert
liked
a
model
about 24 hours ago
updated
a
collection
2 days ago
liked
4
Spaces
2 days ago
reacted to
victor's
post with 🔥
2 days ago
Post
3504
Hey everyone, we've given https://hf.co/spaces page a fresh update!
Smart Search: Now just type what you want to do—like "make a viral meme" or "generate music"—and our search gets it.
New Categories: Check out the cool new filter bar with icons to help you pick a category fast.
Redesigned Space Cards: Reworked a bit to really show off the app descriptions, so you know what each Space does at a glance.
Random Prompt: Need ideas? Hit the dice button for a burst of inspiration.
We’d love to hear what you think—drop us some feedback plz!
Smart Search: Now just type what you want to do—like "make a viral meme" or "generate music"—and our search gets it.
New Categories: Check out the cool new filter bar with icons to help you pick a category fast.
Redesigned Space Cards: Reworked a bit to really show off the app descriptions, so you know what each Space does at a glance.
Random Prompt: Need ideas? Hit the dice button for a burst of inspiration.
We’d love to hear what you think—drop us some feedback plz!
- 5 replies
liked
a
Space
2 days ago
liked
2
datasets
2 days ago
liked
a
Space
5 days ago
liked
a
Space
8 days ago