Ross Wightman

rwightman's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a collection 7 months ago

MobileCLIP2

Collection

MobileCLIP2: Mobile-friendly image-text models with SOTA zero-shot capabilities trained on DFNDR-2B • 30 items • Updated Apr 23 • 62

upvoted a paper 8 months ago

Diffusion Transformers with Representation Autoencoders

Paper • 2510.11690 • Published Oct 13, 2025 • 171

upvoted a collection 8 months ago

timm DINOv3

Collection

Meta AI's DINOv3 weights in timm. ViTs with `qkvb` have a zero QV bias present, otherwise bias is disabled. QKV bias are all 0 in original weights. • 18 items • Updated Sep 19, 2025 • 36

upvoted a collection 10 months ago

gpt-oss

Collection

Open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. • 2 items • Updated Aug 7, 2025 • 437

upvoted an article 10 months ago

view article

Article

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

• 

leonardlin

•

Jun 11, 2024

• 69

upvoted 4 collections 10 months ago

MetaCLIP

Collection

MetaCLIP & MetaCLIP2 OpenCLIP and timm models. All models are dual timm + OpenCLIP (or just timm for specific vit encoders). • 24 items • Updated Sep 19, 2025 • 3

Perception Encoder

Collection

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 Sep 19, 2025 • 7

Meta CLIP 1

Collection

Scaling CLIP data with transparent training distribution from an end-to-end pipeline. • 7 items • Updated Nov 24, 2025 • 23

Perception Encoder

Collection

16 items • Updated Mar 2 • 82

upvoted a paper 11 months ago

RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations

Paper • 2412.19628 • Published Dec 27, 2024 • 2

upvoted 2 collections 11 months ago

RecNeXt

Collection

37 items • Updated Aug 1, 2025 • 2

Gemma 3n

Collection

4 items • Updated Mar 12 • 269

upvoted 2 collections about 1 year ago

MedGemma Release

Collection

Collection of Gemma 3 variants for performance on medical text and image comprehension to accelerate building healthcare-based AI applications. • 9 items • Updated Mar 12 • 493

OpenVision

Collection

27 items • Updated Aug 15, 2025 • 33

upvoted a paper over 1 year ago

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

Paper • 2502.14786 • Published Feb 20, 2025 • 165

upvoted a collection over 1 year ago

SigLIP 2

Collection

OpenCLIP and timm SigLIP 2 models • 49 items • Updated 9 days ago • 27

upvoted 4 articles over 1 year ago

view article

Article

SigLIP 2: A better multilingual vision language encoder

• 
• 
• +1

ariG23498, merve, qubvel-hf

•

Feb 21, 2025

• 214

view article

Article

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

• 

ariG23498

•

Feb 2, 2025

• 6

view article

Article

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

• 
• 
• +1

eliebak, lvwerra, lewtun

•

Jan 28, 2025

• 889

view article

Article

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

• 

MiniMax-AI

•

Jan 15, 2025

• 48