rotem israeli's picture

rotem israeli

irotem98

·

https://rotem154154.github.io

rotem154154

AI & ML interests

None yet

Organizations

None yet

irotem98's activity

upvoted 2 papers 8 days ago

GPT or BERT: why not both?

Paper • 2410.24159 • Published 12 days ago • 12

Randomized Autoregressive Visual Generation

Paper • 2411.00776 • Published 11 days ago • 17

upvoted an article 11 days ago

Article

Trick or ResNet Treat

By

•

12 days ago

• 3

upvoted a paper 11 days ago

Unpacking SDXL Turbo: Interpreting Text-to-Image Models with Sparse Autoencoders

Paper • 2410.22366 • Published 15 days ago • 73

upvoted a collection 12 days ago

SmolLM2

State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M • 8 items • Updated 9 days ago • 163

upvoted 2 papers 15 days ago

GPT-4o System Card

Paper • 2410.21276 • Published 18 days ago • 77

A Survey of Small Language Models

Paper • 2410.20011 • Published 18 days ago • 36

upvoted a collection 16 days ago

timm tiny test models

A collection of very small (~300-500k parameter) models at 160x160 resolution, for testing purposes. Trained on ImageNet-1k. • 13 items • Updated Oct 2 • 3

upvoted 5 papers 20 days ago

Scalable Ranked Preference Optimization for Text-to-Image Generation

Paper • 2410.18013 • Published 20 days ago • 14

Lightweight Neural App Control

Paper • 2410.17883 • Published 21 days ago • 9

Scaling Diffusion Language Models via Adaptation from Autoregressive Models

Paper • 2410.17891 • Published 21 days ago • 15

MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models

Paper • 2410.17637 • Published 21 days ago • 34

WorldSimBench: Towards Video Generation Models as World Simulators

Paper • 2410.18072 • Published 20 days ago • 16

upvoted 2 papers 21 days ago

PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction

Paper • 2410.17247 • Published 21 days ago • 43

Kolmogorov-Arnold Convolutions: Design Principles and Empirical Studies

Paper • 2407.01092 • Published Jul 1 • 1

upvoted 4 collections 21 days ago

VILA-U-7B

VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation • 2 items • Updated 22 days ago • 5

DC-AE-Diffusion

Efficient Diffusion Models with Deep Compression Autoencoder • 7 items • Updated 1 day ago • 6

EfficientViT

1 item • Updated 29 days ago • 3

DC-AE

Deep Compression Autoencoder • 7 items • Updated 22 days ago • 11

upvoted a paper 30 days ago

From Generalist to Specialist: Adapting Vision Language Models via Task-Specific Visual Instruction Tuning

Paper • 2410.06456 • Published Oct 9 • 35