U²-Net: Going Deeper with Nested U-Structure for Salient Object Detection (2020)The idea behind the U-shaped structure is to keep local detail while also capturing the broader context needed for segmentation. What stands out about the proposed RSU-L block is that it works at mu13h ago · 1 min readnickonedrop.hashnode.dev
If AI Is Electricity, What Is the Refrigerator?AI is often compared to electricity. Electricity powered all kinds of new products, from factory machines to refrigerators and washing machines. The idea is that AI—foundation models like Claude and GOct 11 · 2 min readnickonedrop.hashnode.dev
CoCa: Contrastive Captioners Are Image-Text Foundation Models (2022) This is a 2022 paper from Google. For me, the key idea is captured in the following passage and two diagrams. Training combines annotated images with noisy image–text pairs. The class labels in 2AOct 9 · 3 min readnickonedrop.hashnode.dev
Multi-agent cooperation through in-context co-player inference (2026)This paper takes a decentralized multi-agent reinforcement learning approach. What does that mean here? For context, let’s look at another DeepMind paper with overlapping authors: Multi-agent cooperatOct 7 · 3 min readnickonedrop.hashnode.dev
Experiential Reinforcement Learning (2026)The basic reinforcement learning loop is simple: try something, receive a reward, and repeat. Poor behavior is gradually corrected as reward signals accumulate across trials. This paper proposes ExperSep 27 · 3 min readnickonedrop.hashnode.dev
