Byeongho Heo

bhheo's activity

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

upvoted a collection 2 days ago

Cosmos Tokenizer

Collection

A suite of image and video tokenizers • 10 items • Updated 15 days ago • 17

upvoted 2 papers 21 days ago

Unified Speech-Text Pretraining for Spoken Dialog Modeling

Paper • 2402.05706 • Published Feb 8 • 2

Rethinking Spatial Dimensions of Vision Transformers

Paper • 2103.16302 • Published Mar 30, 2021 • 1

upvoted 2 collections about 1 month ago

RDNet

Collection

DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs [ECCV 2024] • 9 items • Updated Oct 16 • 3

rope-vit

Collection

Rotary Position Embedding for Vision Transformer [ECCV 2024] • 22 items • Updated Oct 16 • 2

upvoted a paper about 1 month ago

DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs

Paper • 2403.19588 • Published Mar 28 • 1

upvoted a paper 4 months ago

Rotary Position Embedding for Vision Transformer

Paper • 2403.13298 • Published Mar 20 • 3