- all
- popular
- trending
- most recent

Introducing Temporal Kolmogorov-Arnold Networks (TKANs): A Breakthrough in Multi-step Time Series Forecasting
TKANs reshape prediction: faster, sharper, and easier to trust—built on timeless theorems, not just bigger networks.

Understanding the melody of speech
How prosody, the musical quality of speech, conveys emotions and meanings beyond words in everyday conversations.

Sound waves boost optical neural networks
Scientists use sound waves to create a new photonic activation function, advancing energy-efficient AI with optical neural networks.

New memristors mimic brain cells for better computers
Scientists build stable, low-power memristors to help artificial neural networks learn new things without forgetting old ones.

Reinforcement learning pioneers win ACM Turing award
Andrew Barto and Richard Sutton earned the 2024 ACM A.M. Turing Award. This prize honors their work on reinforcement learning.

AI tool helps scientists discover faster
Researchers create an AI that reads studies, analyzes data, and predicts molecule behavior to speed up science.

Elon Musk unveils Grok 3
Performance benchmarks displayed during the event showed Grok 3 outperforming rivals in math, science, and coding tasks.

Latent reasoning: language models that think?
Preliminary research suggests a new path for language models, combining internal reasoning with traditional word generation.

Cheap open AI matches OpenAI and DeepSeek in some tests
AI researchers started with a free Qwen model and used distillation to make a new AI model for less than $50 in cloud computing costs.

Rat vision is still more efficient than machine vision
AI can mimic natural vision but does so differently than biological systems do. Learning from how animals see could help improve AI.