Xin Wen's picture

4 11 6

Xin Wen

xwen99

·

https://wen-xin.info

AI & ML interests

self-supervised learning, object discovery

Recent Activity

liked a Space 17 days ago

HuggingFaceM4/FineVision

upvoted a paper about 2 months ago

The Automated LLM Speedrunning Benchmark: Reproducing NanoGPT Improvements

upvoted a paper 2 months ago

Vision-Language-Vision Auto-Encoder: Scalable Knowledge Distillation from Diffusion Models

View all activity

Organizations

liked a Space 17 days ago

FineVision: Open Data is All You Need

A new open-source dataset for training VLMs

liked a Space over 2 years ago

BLIP2

image captioning, VQA

liked 3 models over 2 years ago

Salesforce/blip2-flan-t5-xxl

Image-Text-to-Text • 12B • Updated Feb 3 • 5.42k • 93

google/flan-t5-xl

3B • Updated Nov 28, 2023 • 352k • 519

facebook/opt-iml-1.3b

Text Generation • Updated Jan 26, 2023 • 1.23k • 29

liked a Space over 2 years ago

BLIP2

Generate captions and chat about images