NIPS
NeurIPS/NIPS conference series on machine learning and related topics
Episodes
-
#5813: How Python Became AI's Default LanguagePython was never designed for science. So how did a general-purpose scripting language end up carrying the entire AI industry? -
#5442: When Do LLMs Suddenly Get Good at Things?New capabilities seem to appear out of nowhere as models scale. Whether that's real — or just how we measure — is still an open fight. -
#5626: What Multimodal Models Actually Learn From VideoLate fusion, early fusion, and vision laziness — what actually happens when models train on video, audio, and text together. -
#5624: One Forward Pass: Building a Bounded ClassifierNo generation, no parsing — just label scores in a single pass. How to build a small encoder classifier that actually works. -
#5443: Heads vs Layers: How Model Merging Actually WorksHeads aren't the Lego bricks of model merging — layers are. Here's what heads really do and how frankenmerges get built.