1h ago · 7 min read · Heads-up: The figure captions in this article are clickable. Click on any figure caption to view the associated outputs, visualizations, and intermediate results discussed in that section. Hey guys, i
Join discussion9h ago · 47 min read · Introduction What Is Image Super Resolution Image Super Resolution (SR) is the computational task of reconstructing a high-resolution image from one or more low-resolution observations. The goal is to
Join discussion
15h ago · 56 min read · Introduction What Is Image Inpainting Image inpainting is the computational task of reconstructing missing, corrupted, or deliberately removed regions of a digital image in a way that is visually plau
Join discussion
5d ago · 9 min read · Last time we cut BF16 weights in half by treating the exponent as a 16-entry palette instead of an 8-bit field. SCLP8: 7.9 GB instead of 15.0, perplexity slightly better than the original, token gener
Join discussion
6d ago · 43 min read · GPT-3 was a major breakthrough in natural language processing. With 175 billion parameters, it demonstrated remarkable few-shot learning abilities and showed that scaling large language models could u
Join discussion
May 31 · 20 min read · Image inpainting — the art of filling in missing or damaged regions of an image — has exploded as a research area in 2025–2026. It is no longer just about photo restoration. Today, it powers satellite
Join discussion
May 29 · 11 min read · I built a clean, well-structured deep learning pipeline using MONAI (Medical Open Network for AI) on a public abdominal ultrasound dataset. The pipeline included: proper subject-grouped train/validat
Join discussion
May 27 · 15 min read · Somewhere in the 1950s, a scientist named Frank Rosenblatt had a wild idea: what if a machine could learn to classify things the same way humans do — by adjusting the weight it gives to each piece of
Join discussion
