Scott Klum's picture

8 9

Scott Klum

sklum

·

AI & ML interests

None yet

Recent Activity

liked a model about 1 month ago

facebook/sam3

liked a model 3 months ago

Qwen/Qwen3-VL-30B-A3B-Instruct

upvoted a collection 4 months ago

View all activity

Organizations

liked a model about 1 month ago

facebook/sam3

Mask Generation • 0.9B • Updated Nov 20 • 1.15M • 1.23k

liked a model 3 months ago

Qwen/Qwen3-VL-30B-A3B-Instruct

Image-Text-to-Text • 31B • Updated Nov 26 • 1.4M • • 477

upvoted 2 collections 4 months ago

Qwen3-Next

4 items • Updated Sep 22 • 169

FastVLM

Efficient Vision Encoding for Vision Language Models • 9 items • Updated Sep 2 • 106

liked a model 5 months ago

microsoft/Florence-2-large

Image-Text-to-Text • 0.8B • Updated Aug 4 • 821k • 1.73k

liked a Space 5 months ago

Qwen Image

Generate detailed images from text prompts

liked a model 9 months ago

vikhyatk/moondream2

Image-Text-to-Text • 2B • Updated Sep 23 • 2.43M • 1.36k

upvoted a paper 10 months ago

Cautious Optimizers: Improving Training with One Line of Code

Paper • 2411.16085 • Published Nov 25, 2024 • 19

upvoted 2 articles 10 months ago

Article

Searching for better (Full) ImageNet ViT Baselines

Aug 26, 2024

•

6

Article

SmolVLM2: Bringing Video Understanding to Every Device

+5

Feb 20

•

320

liked a model 10 months ago

HuggingFaceTB/SmolVLM2-2.2B-Instruct

Image-Text-to-Text • 2B • Updated Apr 8 • 113k • 294

upvoted a collection 10 months ago

SmolVLM2 📺 Smallest video LM ever 🤏🏻

11 items • Updated May 5 • 103

updated a Space over 1 year ago

Detection Metrics

Compute object detection metrics using COCO style

liked a Space over 1 year ago

COCOEvaluate

updated a Space over 1 year ago

My Metric

liked a Space over 1 year ago

Open Object Detection Leaderboard

Request evaluation for a new model

reacted to rwightman's post with 🤗 over 1 year ago

Post

1494

Aiming to keep timm (https://github.com/huggingface/pytorch-image-models) the go-to library for efficient image encoders for your mobile and edge devices, I've started working on an implementation of the new MobileNet-V4 model. Take a look at a short article I wrote about the model: https://huggingface.co/blog/rwightman/mobilenetv4

Paper: MobileNetV4 -- Universal Models for the Mobile Ecosystem (2404.10518)

upvoted an article over 1 year ago

Article

MobileNet-V4 (now in timm)

Jun 17, 2024

•

48

upvoted a collection almost 2 years ago

timm Top-20 Fastest Models

Not the most accurate, but the highest throughput image classification models in timm • 20 items • Updated Sep 19 • 16

liked a Space over 2 years ago

Dpt Depth Estimation + 3D

Image to 3D with DPT + 3D Point Cloud