Tag: sota
15 posts
Paper Review: DINOv3
Meta's self-supervised vision model trained on 17 billion images, introducing Gram anchoring to prevent feature degra...
Paper Review: FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization
My review of the paper FastViT A Fast Hybrid Vision Transformer using Structural Reparameterization
Paper Review: Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning
My review of the paper Scaling Autoregressive Multi-Modal Models Pretraining and Instruction Tuning
Paper Review: Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles
My review of the paper Hiera A Hierarchical Vision Transformer without the Bells-and-Whistles
Paper Review: Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture
Yann LeCun's I-JEPA learns semantic image representations by predicting masked patch features — no data augmentation ...
Paper Review: ImageBind: One Embedding Space To Bind Them All
My review of the paper ImageBind One Embedding Space To Bind Them All
Paper Review: DINOv2: Learning Robust Visual Features without Supervision
How Meta built all-purpose visual features by scaling self-supervised pretraining to a curated 142M-image dataset, pr...
Paper Review: PaLM-E: An Embodied Multimodal Language Model
My review of the paper PaLM-E An Embodied Multimodal Language Model
Paper Review: In-Context Instruction Learning
My review of the paper In-Context Instruction Learning
Paper Review: LLaMA: Open and Efficient Foundation Language Models
My review of the paper LLaMA Open and Efficient Foundation Language Models
Paper Review: Scaling Vision Transformers to 22 Billion Parameters
My review of the paper Scaling Vision Transformers to 22 Billion Parameters
Paper Review: EfficientNetV2: Smaller Models and Faster Training
My review of the paper EfficientNetV2 Smaller Models and Faster Training.
Paper Review: Revisiting ResNets: Improved Training and Scaling Strategies
My review of the paper Revisiting ResNets, Improved Training and Scaling Strategies.
Paper Review: JigsawGAN: Self-supervised Learning for Solving Jigsaw Puzzles with Generative Adversarial Networks
My review of the paper JigsawGAN Self-supervised Learning for Solving Jigsaw Puzzles with Generative Adversarial Netw...
Paper Review: Language-agnostic BERT Sentence Embedding
My review of the paper Language-agnostic BERT Sentence Embedding.