qubvel-hf (Pavel Iakubovskii)

upvoted a paper 13 days ago

Associative Recurrent Memory Transformer

Paper • 2407.04841 • Published 17 days ago • 30

upvoted an article 28 days ago

Article

Fine-tuning Florence-2 - Microsoft's Cutting-edge Vision Language Models

28 days ago

• 142

upvoted 2 collections about 1 month ago

Depth Anything v2 Release

Collection

A comprehensive collection on DAv2 • 5 items • Updated Jun 18 • 9

MobileNetV4 pretrained weights

Collection

Weights for MobileNet-V4 pretrained in timm • 13 items • Updated 28 days ago • 10

upvoted a paper about 1 month ago

Depth Anything V2

Paper • 2406.09414 • Published Jun 13 • 88

upvoted an article about 1 month ago

Article

Uncensor any LLM with abliteration

By

•

Jun 13

• 238

upvoted an article about 2 months ago

Article

Sales Forecasting with Image Regression

By

•

May 24

• 5

upvoted 2 papers about 2 months ago

Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations

Paper • 2405.18392 • Published May 28 • 12

An Introduction to Vision-Language Modeling

Paper • 2405.17247 • Published May 27 • 78

upvoted 4 articles about 2 months ago

Article

AI has a problem with objectifying women

By

•

May 24

• 54

Article

Multimodal Augmentation for Documents: Recovering “Comprehension” in “Reading and Comprehension” task

By

•

May 16

• 15

Article

MobileNet-V4 (now in timm)

By

•

Jun 17

• 30

Article

Unlocking Longer Generation with Key-Value Cache Quantization

May 16

• 22

upvoted an article 2 months ago

Article

A Dive into Pretraining Strategies for Vision-Language Models

Feb 3, 2023

• 30

upvoted a collection 2 months ago

PaliGemma Release

Collection

Pretrained and mix checkpoints for PaliGemma • 16 items • Updated 25 days ago • 124

upvoted an article 3 months ago

Article

Welcome Llama 3 - Meta's new open LLM

Apr 18

• 261

Pavel Iakubovskii

AI & ML interests

Organizations

qubvel-hf's activity

Associative Recurrent Memory Transformer

Fine-tuning Florence-2 - Microsoft's Cutting-edge Vision Language Models

Depth Anything v2 Release

MobileNetV4 pretrained weights

Depth Anything V2

Uncensor any LLM with abliteration

Sales Forecasting with Image Regression

Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations

An Introduction to Vision-Language Modeling

AI has a problem with objectifying women

Multimodal Augmentation for Documents: Recovering “Comprehension” in “Reading and Comprehension” task

MobileNet-V4 (now in timm)

Unlocking Longer Generation with Key-Value Cache Quantization

A Dive into Pretraining Strategies for Vision-Language Models

PaliGemma Release

Welcome Llama 3 - Meta's new open LLM