Rob MansonLLMs need their heads read!A ‘Best Paper’ at NeurIPS makes LLMs faster & more stable by adding a gate on each attention head. This turned attention from a…Dec 8, 2025A response icon6
InTowards AIbyHamza BoulahiaHow Do LLMs Actually Work?The intuition, and just enough math.Nov 2, 2025A response icon6Nov 2, 2025A response icon6
InThe Quantastic JournalbyFrancesco De BernardisInterpretability of Graph Neural Networks: An Exploratory Study of Nodes, Features, and AttentionGraph Neural Networks are a relatively recent and powerful modeling tool for graph-structured data. Surprisingly, even simple GNNs can…Jul 12, 2025A response icon3Jul 12, 2025A response icon3
Sourav MukherjeeDeveloping a Game for Cognitive Research- Week 1Are you interested in cognitive neuroscience topics or game development (by a novice) by any chance? This article might be something you…3h ago3h ago
Rob MansonLLMs need their heads read!A ‘Best Paper’ at NeurIPS makes LLMs faster & more stable by adding a gate on each attention head. This turned attention from a…Dec 8, 2025A response icon6
InTowards AIbyHamza BoulahiaHow Do LLMs Actually Work?The intuition, and just enough math.Nov 2, 2025A response icon6
InThe Quantastic JournalbyFrancesco De BernardisInterpretability of Graph Neural Networks: An Exploratory Study of Nodes, Features, and AttentionGraph Neural Networks are a relatively recent and powerful modeling tool for graph-structured data. Surprisingly, even simple GNNs can…Jul 12, 2025A response icon3
Sourav MukherjeeDeveloping a Game for Cognitive Research- Week 1Are you interested in cognitive neuroscience topics or game development (by a novice) by any chance? This article might be something you…3h ago
Sophie ZhaoWhy Deep Learning Loves the Dot Product and Matrix MultiplicationThe dot product is more than a basic linear algebra operation — it is one of the core mathematical tools that powers modern deep learning…Sep 24, 2025A response icon2
Sheelapriya GopalThe Art of Being Here NowHow Daily Consciousness quietly builds the future (even when you’re not trying)12h ago
Alex Xiaoli ShenHands-On Transformer Deep Dive: Part 1 — Masked Attention Explained & ImplementedIn this “Hands-On Transformer Deep Dive” series, we go step-by-step through the algorithms and components of modern Transformers, with…Aug 1, 2025A response icon3
