Hacker News Reader

conviewon Introducing System One Models and Jev

explanation with example: https://mchromiak.github.io/articles/2026/Sep/17/Jev-Typed-D...

conviewon DinoV2: Meta’s Open Source State-of-the-art computer vision models

Quick overview of DINOv2: https://mchromiak.github.io/articles/2023/Apr/18/DINOv2-Lear...

conviewon DINOv2: State-of-the-art computer vision models with self-supervised learning

https://mchromiak.github.io/articles/2023/Apr/18/DINOv2-Lear...

conviewon Masked Autoencoders Are Scalable Vision Learners – New SSL Algorithm

The return of patch-based self-supervision! No ResNets but from one of the authors of the initial paper. Now with ViT, very simple self-supervised (SSL) pre-training shines again. It outperforms the contrastive learning counterparts and is simpler than BEiT, as its pixel-based (no tokenisation) needed. No need for special augmentation considerations like BYOL. i1k=87.8%

conviewon Decision Transformer; Transformer for RL partially ditching dynamic programming

The "Decision Transformer: Reinforcement Learning via Sequence Modeling" : by Chen L. et al explaining how to use transformer to replace dynamic programming for context length reference.

conviewon MLP-Mixer: How can pure MLP be useful?

An explanatory article on how can MLP is still useful comparing to modern machine learning architectures without convolutions, nor attention.