Ross Wightman's picture

Ross Wightman

rwightman

·

AI & ML interests

Computer vision, transfer learning, semi/self supervised learning, robotics.

Recent Activity

upvoted an article about 5 hours ago

An Analysis of Chinese LLM Censorship and Bias with Qwen 2 Instruct

new activity about 6 hours ago

UCSC-VLAA/openvision-vit-base-patch16-384:Error

updated a model about 7 hours ago

timm/naflexvit_base_patch16_siglip.v2_webli

View all activity

Organizations

upvoted an article about 5 hours ago

Article

An Analysis of Chinese LLM Censorship and Bias with Qwen 2 Instruct

By

•

Jun 11, 2024

• 64

upvoted a collection 4 days ago

MetaCLIP

MetaCLIP & MetaCLIP2 OpenCLIP and timm models. All models are dual timm + OpenCLIP (or just timm for specific vit encoders). • 24 items • Updated 3 days ago • 2

upvoted a collection 11 days ago

Perception Encoder

OpenCLIP (PE Core image + text) and timm PE Core, Spatial, Lang (ViT only) weights. NOTE: These weights do not work with original modeling code. • 19 items • Updated 4 days ago • 5

upvoted 2 collections 12 days ago

Meta CLIP

Scaling CLIP data with transparent training distribution from an end-to-end pipeline. • 7 items • Updated 14 days ago • 4

Perception Encoder

17 items • Updated 24 days ago • 62

upvoted a paper about 1 month ago

RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations

Paper • 2412.19628 • Published Dec 27, 2024 • 2

upvoted 2 collections about 1 month ago

RecNeXt

37 items • Updated 4 days ago • 2

Gemma 3n

4 items • Updated 26 days ago • 201

upvoted 2 collections 3 months ago

MedGemma Release

Collection of Gemma 3 variants for performance on medical text and image comprehension to accelerate building healthcare-based AI applications. • 7 items • Updated 25 days ago • 271

OpenVision

27 items • Updated May 8 • 29

upvoted a paper 5 months ago

SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Paper • 2502.14786 • Published Feb 20 • 146

upvoted a collection 5 months ago

SigLIP 2

OpenCLIP and timm SigLIP 2 models • 45 items • Updated 4 days ago • 23

upvoted an article 5 months ago

Article

SigLIP 2: A better multilingual vision language encoder

By

and 2 others •

Feb 21

• 175

upvoted 2 articles 6 months ago

Article

🚀 Deploying OLMo-7B with Text Generation Inference (TGI) on Hugging Face Spaces

By

•

Feb 2

• 6

Article

Open-R1: a fully open reproduction of DeepSeek-R1

By

and 2 others •

Jan 28

• 876

upvoted 2 articles 7 months ago

Article

MiniMax-01 is Now Open-Source: Scaling Lightning Attention for the AI Agent Era

By

•

Jan 15

• 47

Article

Timm ❤️ Transformers: Use any timm model with transformers

By

and 4 others •

Jan 16

• 50

upvoted 3 papers 8 months ago

Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference

Paper • 2412.13663 • Published Dec 18, 2024 • 153

Phi-4 Technical Report

Paper • 2412.08905 • Published Dec 12, 2024 • 121

PaliGemma 2: A Family of Versatile VLMs for Transfer

Paper • 2412.03555 • Published Dec 4, 2024 • 134