Datapoint

SpaceX IPO a Datapoint to Higher Market Prices, Says Julian Emanuel

Native Hierarchical and Compositional Representations with Subspace Embeddings

arXiv:2508.16687v2 Announce Type: replace Abstract: Traditional embeddings represent datapoints as vectors, which makes similarity easy to compute but limits how well they capture hierarchies and compositionality. We propose a fundamentally different approach: representing concepts as linear subspaces. By spanning multiple dimensions, subspaces can model broader concepts with higher-dimensional regions and nest more specific concepts within them.

FactoryNet: A Large-Scale Dataset toward Industrial Time-Series Foundation Models

arXiv:2605.09081v4 Announce Type: replace Abstract: We introduce the first universal pretraining corpus for industrial time-series data: 51M datapoints across 23k end-to-end task executions (13.3k real, 9.8k synthetic) on six embodiments, unified by a shared schema that enables robust zero-shot cross-embodiment transfer and highly parameter-efficient anomaly detection. We introduce a novel schema: Setpoint, Effort, Feedback, Context (S-E-F-C) underlying the whole pipeline that maps any...

Human-Like Neural Nets by Catapulting

Human-like Neural Nets by Catapulting Speculative proposal to create artificial neural nets with human-like performance by high-learning-rate/regularization training of overparameterized NNs to trigger catapulting/grokking. Over-parameterization as a route to true generalization would resolve many outstanding mysteries of artificial versus natural intelligence. There are many mysteries about deep learning and human intelligence, but we could describe the biggest anomaly this way: why are...

How Optimality Structures Sparse Dictionaries: A Theory for Understanding SAE Representations

Announce Type: cross Abstract: Sparse Autoencoders (SAEs) have found success parsing neural representations into interpretable concepts, providing a basis for understanding and control. However, what exactly SAEs extract, and, correspondingly, the scientific conclusions we can draw from them, are not obvious. Empirically, the proof is in the pudding: SAEs learn interpretable features.

MPs warned about deadly ‘frog poison’ skin cream being sold into Britain

MPs warned about deadly ‘frog poison’ skin cream being sold into Britain Regulators warn of skin products scraped from the skin of a live giant monkey frog and traditionally used in shamanic rituals which has been linked to deaths Experts have warned of “snake oil” cosmetic products being sold into the UK via Amazon. A powerful committee of MPs has investigated the unregulated “wild west” cosmetics industry in the UK including cosmetic products such as a skin cream made from poisonous frogs....