NeoMME: an efficient Multimodal-native and Multilingual Encoder
• 90
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
NeoMME: A Single-Tower Multimodal-Native Multilingual Foundation Encoder for Efficient Fine-Tuning and Inference
Surfer 2: The Next Generation of Cross-Platform Computer Use Agents
Articles
h-tonywu
updated 8
models about 13 hours ago
Hcompany/NeoMME-800M-Retriever-ST-late
Visual Document Retrieval • 0.8B • Updated • 48 • 4
Hcompany/NeoMME-800M-Retriever-ST-dense
Sentence Similarity • 0.8B • Updated • 92 • 3
Hcompany/NeoMME-800M-Retriever
Visual Document Retrieval • 0.8B • Updated • 276 • 8
Hcompany/NeoMME-800M
Feature Extraction • 0.8B • Updated • 141 • 5
Hcompany/NeoMME-260M-Retriever-ST-late
Visual Document Retrieval • 0.3B • Updated • 132 • 5
Hcompany/NeoMME-260M-Retriever-ST-dense
Sentence Similarity • 0.3B • Updated • 158 • 4
Hcompany/NeoMME-260M-Retriever
Visual Document Retrieval • 0.3B • Updated • 646 • 5
Hcompany/NeoMME-260M
Feature Extraction • 0.3B • Updated • 700 • 12
Article
NeoMME: an efficient Multimodal-native and Multilingual Encoder
Hcompany
• • 90 h-tonywu
published 8
models 8 days ago
Hcompany/NeoMME-800M
Feature Extraction • 0.8B • Updated • 141 • 5
Hcompany/NeoMME-800M-Retriever
Visual Document Retrieval • 0.8B • Updated • 276 • 8
Hcompany/NeoMME-800M-Retriever-ST-late
Visual Document Retrieval • 0.8B • Updated • 48 • 4
Hcompany/NeoMME-800M-Retriever-ST-dense
Sentence Similarity • 0.8B • Updated • 92 • 3
Hcompany/NeoMME-800M-Pretrain-predecay-s450000
Fill-Mask • 0.8B • Updated • 39 • 3
Hcompany/NeoMME-260M-Retriever-ST-late
Visual Document Retrieval • 0.3B • Updated • 132 • 5
Hcompany/NeoMME-260M-Retriever-ST-dense
Sentence Similarity • 0.3B • Updated • 158 • 4
Hcompany/NeoMME-260M-Pretrain-predecay-s450000
Fill-Mask • 0.3B • Updated • 42 • 3
tonywu71
updated a
collection 8 days ago
tonywu71
submitted a
paper to Daily Papers 8 days ago
sergiopaniego
posted an update 8 days ago
Post
2004
Can you do RL over taste?
I've spent some time reproducing, in the open, Surya N's idea of training a model to paint with code. It's a coding model that learns to paint watercolours by writing JS code, trained with GRPO. I used TRL and OpenEnv for this, with the whole pipeline running on Hugging Face.
The interesting part is that the reward has no correct answer, unlike a math problem. In this case it's based on the artistic preferences of the person who builds the dataset.
Everything is published: the environment, the reference pool, the trained adapters, every painting of every run with the code that made it, and a write-up with all the decisions, including the ones that went wrong.
Blog post: https://huggingface.co/blog/train-to-paint-with-code
I've spent some time reproducing, in the open, Surya N's idea of training a model to paint with code. It's a coding model that learns to paint watercolours by writing JS code, trained with GRPO. I used TRL and OpenEnv for this, with the whole pipeline running on Hugging Face.
The interesting part is that the reward has no correct answer, unlike a math problem. In this case it's based on the artistic preferences of the person who builds the dataset.
Everything is published: the environment, the reference pool, the trained adapters, every painting of every run with the code that made it, and a write-up with all the decisions, including the ones that went wrong.
Blog post: https://huggingface.co/blog/train-to-paint-with-code