[Paper Review] Stable Diffusion & SDXL
September 15, 2024
SDXL extends Stable Diffusion with a larger U-Net backbone, multi-scale generation, and flexible text conditioning, enabling high-resolution, semantically ri...
Blog
2024
![[Paper Review] Stable Diffusion & SDXL](https://jun-brro.kr/images/thumbnails/sdxl.png)
[Paper Review] UMT (Unified Multimodal Transformers)
September 09, 2024
UMT is a unified framework for video highlight detection and moment retrieval that flexibly integrates visual, audio, and optional text modalities to identif...
![[Paper Review] UMT (Unified Multimodal Transformers)](https://jun-brro.kr/images/thumbnails/umt.png)
[Paper Review] Segment Anything Model 2 (SAM2)
August 16, 2024
SAM2 generalizes promptable visual segmentation to video by integrating spatio-temporal memory, interactive prompting, and a data engine for fine-grained, ef...
![[Paper Review] Segment Anything Model 2 (SAM2)](https://jun-brro.kr/images/thumbnails/sam2.png)
[Paper Review] SlowFast Networks for Video Recognition
July 23, 2024
The SlowFast network employs dual pathways, with the Slow Pathway capturing high-resolution spatial details and the Fast Pathway capturing rapid temporal cha...
![[Paper Review] SlowFast Networks for Video Recognition](https://jun-brro.kr/images/thumbnails/slowfast.png)
[Paper Review] End-to-End Object Detection with Transformers (DETR)
July 23, 2024
DETR revolutionizes object detection by integrating the Transformer architecture’s global attention mechanism with CNN-extracted image features, utilizing a ...
![[Paper Review] End-to-End Object Detection with Transformers (DETR)](https://jun-brro.kr/images/thumbnails/detr.png)
[Paper Review] VAE (Variational AutoEncoder)
July 13, 2024
Variational Autoencoders (VAEs) employ a probabilistic approach to latent variable modeling, optimizing a variational lower bound to perform efficient approx...
![[Paper Review] VAE (Variational AutoEncoder)](https://jun-brro.kr/images/thumbnails/vae.png)
[Paper Review] Transformers
July 10, 2024
Transformers is a deep learning architecture that enhances natural language processing by using self-attention mechanisms to capture long-range dependencies ...
![[Paper Review] Transformers](https://jun-brro.kr/images/thumbnails/transformers.png)
[Paper Review] VAE (Variational AutoEncoder)
July 10, 2024
DDIM (Denoising Diffusion Implicit Models) is a generative model for efficient image generation through a refined diffusion denoising process.
![[Paper Review] VAE (Variational AutoEncoder)](https://jun-brro.kr/images/thumbnails/ddim.png)
[Paper Review] BERT
July 10, 2024
BERT (Bidirectional Encoder Representations from Transformers) is a deep learning model that improves natural language understanding by pre-training on vast ...
![[Paper Review] BERT](https://jun-brro.kr/images/thumbnails/bert.png)