Aray Karjauv·1d agoWhat LRP Is and Why It Fails Quietly When Interpreting Vision ModelsHow LRP helps debug vision models by routing relevance back to the pixels, where modern layers break the flow without warning, and the new…
Aray Karjauv·4d agoWhat Does a Vision Model See Without Labels?How activation maps and relevance propagation can shed light on deep models without any labels.A response icon2A response icon2
Aray Karjauv·Apr 20, 2023Tour of the LLM Zoo: Exploring the Cutting-Edge Large Language ModelsLlama, Vicuna, Koala, Alpaca, Dolly - this blog post reviews the most promising LLMs and recent releases to help you stay up-to-date.
Aray Karjauv·Apr 13, 2023Simulating human-like social behavior with ChatGPTA short review of “Generative Agents: Interactive Simulacra of Human Behavior”
Aray Karjauv·Mar 29, 2023Multi-Language Speech Recognition and Speaker DiarizationLearn how to transcribe any video in minutes using speech recognition that works in 99 languages, identifies speakers, and translates the…
Aray Karjauv·Dec 11, 2022StyleGAN as a latent feature extractorSelf-supervised representation learning using StyleGAN2
InCodeXbyAray Karjauv·Oct 18, 2020Python on a Webpage? EasyHave you ever wanted to add the Python scientific stack to your webpage? Good news! All you need is Pyodide.A response icon1A response icon1