Wonjae Kim

dandelin's activity

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

authored a paper 24 days ago

Extract Free Dense Misalignment from CLIP

Paper • 2412.18404 • Published Dec 24, 2024

authored 13 papers about 1 month ago

Discrete Infomax Codes for Supervised Representation Learning

Paper • 1905.11656 • Published May 28, 2019

Diversified Mutual Learning for Deep Metric Learning

Paper • 2009.04170 • Published Sep 9, 2020

Group Generalized Mean Pooling for Vision Transformer

Paper • 2212.04114 • Published Dec 8, 2022

STELLA: Continual Audio-Video Pre-training with Spatio-Temporal Localized Alignment

Paper • 2310.08204 • Published Oct 12, 2023

Language-only Efficient Training of Zero-shot Composed Image Retrieval

Paper • 2312.01998 • Published Dec 4, 2023

An Extendable, Efficient and Effective Transformer-based Object Detector

Paper • 2204.07962 • Published Apr 17, 2022

HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts

Paper • 2404.17507 • Published Apr 26, 2024

Probabilistic Language-Image Pre-Training

Paper • 2410.18857 • Published Oct 24, 2024

What Do Self-Supervised Vision Transformers Learn?

Paper • 2305.00729 • Published May 1, 2023

Pivotal Role of Language Modeling in Recommender Systems: Enriching Task-specific and Task-agnostic Representation Learning

Paper • 2212.03760 • Published Dec 7, 2022

Learning Dynamics of Attention: Human Prior for Interpretable Machine Reasoning

Paper • 1905.11666 • Published May 28, 2019

Computational Approaches for App-to-App Retrieval and Design Consistency Check

Paper • 2309.10328 • Published Sep 19, 2023

Reducing Task Discrepancy of Text Encoders for Zero-Shot Composed Image Retrieval

Paper • 2406.09188 • Published Jun 13, 2024

updated 2 models about 1 year ago

dandelin/hype-sampler-abl

Updated Nov 8, 2023 • 2

dandelin/hype-sampler

Updated Nov 7, 2023 • 1

authored 4 papers over 1 year ago

ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision

Paper • 2102.03334 • Published Feb 5, 2021

SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage

Paper • 2303.11114 • Published Mar 20, 2023

CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion

Paper • 2303.11916 • Published Mar 21, 2023

ViDT: An Efficient and Effective Fully Transformer-based Object Detector

Paper • 2110.03921 • Published Oct 8, 2021 • 1