Hasan Arif's picture

1 5 4

Hasan Arif

hasanar1f

·

AI & ML interests

Efficient training and inference

Recent Activity

upvoted a paper about 2 months ago

TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters

upvoted a paper about 2 months ago

NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks

View all activity

Organizations

hasanar1f's activity

upvoted 2 papers about 2 months ago

TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters

Paper • 2410.23168 • Published Oct 30, 2024 • 24

NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks

Paper • 2410.20650 • Published Oct 28, 2024 • 16

upvoted a paper 4 months ago

HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models in Resource-Constrained Environments

Paper • 2408.10945 • Published Aug 20, 2024 • 9

upvoted a collection 10 months ago

LLaVa-NeXT

LLaVa-NeXT (also known as LLaVa-1.6) improves upon the 1.5 series by incorporating higher image resolutions and more reasoning/OCR datasets. • 8 items • Updated Jul 19, 2024 • 27