Data science, career and other topics
15 June 2023
Yann LeCun's I-JEPA learns semantic image representations by predicting masked patch features — no data augmentation needed — training a ViT-Huge on ImageNet in under 72 hours on 16 GPUs.
12 June 2023
My review of the paper BiomedGPT A Unified and Generalist Biomedical Generative Pre-trained Transformer for Vision, Language, and Multimodal Tasks
08 June 2023
My review of the paper StableRep Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners
05 June 2023
My review of the paper The effectiveness of MAE pre-pretraining for billion-scale pretraining
01 June 2023
My review of the paper QLoRA Efficient Finetuning of Quantized LLMs
30 May 2023
My review of the paper Chain of Hindsight Aligns Language Models with Feedback
Type at least 2 characters to search...