Amir Elahi

amir-elahi

4 3

·

amir-elahi

AI & ML interests

Data extraction, Transformers, Diffusion models, VAE

Recent Activity

upvoted a paper 9 days ago

Blind-Spots-Bench: Evaluating Blind Spots in Multimodal Models

upvoted a paper 9 days ago

PixSDS: Why Latent SDS Makes Noisy Pixels

liked a model 9 days ago

Qwen/Qwen3.8-27B

View all activity

Organizations

upvoted 2 papers 9 days ago

Blind-Spots-Bench: Evaluating Blind Spots in Multimodal Models

Paper • 2607.08317 • Published Jul 9 • 37

PixSDS: Why Latent SDS Makes Noisy Pixels

Paper • 2608.12997 • Published 16 days ago • 11

liked a model 9 days ago

Qwen/Qwen3.8-27B

Image-Text-to-Text • 28B • Updated 14 days ago • 3.46M • • 13.1k

liked a model 11 months ago

shixuanleong/visualheist-large

Image-Text-to-Text • 0.8B • Updated Mar 5, 2025 • 12 • 1

upvoted a collection about 1 year ago

Qwen3

84 items • Updated Dec 31, 2025 • 1.85k

upvoted a paper about 2 years ago

Are large language models superhuman chemists?

Paper • 2404.01475 • Published Apr 1, 2024 • 19

updated a collection about 2 years ago

Forecasting

This is a collection for pre-trained forecasting models • 5 items • Updated Jun 6, 2024

updated a collection over 2 years ago

Forecasting

This is a collection for pre-trained forecasting models • 5 items • Updated Jun 6, 2024

liked a model over 2 years ago

google/timesfm-1.0-200m

Time Series Forecasting • Updated May 17, 2024 • 573 • 832

updated a collection over 2 years ago

Text-to-images-general

1 item • Updated Apr 30, 2024