George SLLM newsClaude just realse open ource LLM and it outperform GPT4. How exciting it is!!! Check the link above to see more details.1 min read·Apr 9, 2024----
George Ssome stuff I am working onhttps://github.com/facebookresearch/segment-anything https://github.com/lucidrains/denoising-diffusion-pytorch/tree/main…1 min read·Mar 15, 2024----
George SWhat is segment anything?!1.segment anything https://github.com/facebookresearch/segment-anything1 min read·Mar 6, 2024----
George SMore Agents Is All You Need[new paper released] How to increase LLM model accuracy, simple as that is to use esemble approach and then do majority voting.1 min read·Feb 11, 2024----
George SAre big model and big data equally important-pa?In general, when training models, more paras and more data brings higher accuracy. there is a phenomenon called emergent abilities of…3 min read·May 12, 2023----
George SDiffusion model ?! Generative AIRegarding generative learning, There are sentences, images, or voices.2 min read·Apr 30, 2023----
George Smindblowing research on generative agents that simulate believable human behaviorIn this paper, researchers successfully made chracters act like humans.1 min read·Apr 17, 2023----
George SDeepmind released overview of transformer architecture and algorithmThis describes what they are, how they are trained and what they are used for. Also key architectural components.1 min read·Apr 17, 2023----
George STake away from Deep Residual learning for Image RecognitionFirst problem is vanishing/exploding gradients. That is with deeper network, it is not change weights efficiently, which makes it hard to…1 min read·Jul 7, 2021----
George STakeaway from AlexNet: ImageNet Classification with Deep Convolutional Neural NetworksRecently had a chance to walk through this very classic paper.1 min read·Jun 30, 2021----