# Oct 19, 2024

- **AI engineers claim new algorithm reduces AI power consumption by 95%**  
  BitEnergy AI's new algorithm, Linear-Complexity Multiplication (L-Mul), replaces complex floating-point multiplication with integer addition, achieving a potential 95% reduction in AI power consumption while maintaining accuracy.

- **Why do random forests work? They are self-regularizing adaptive smoothers**  
  Tree ensembles, viewed as adaptive and self-regularizing smoothers, enhance prediction smoothness beyond individual trees, adjusting their smoothness based on input dissimilarity at test-time, which offers a fresh perspective on their effectiveness.

- **[Project] Tsetlin Machine for Deep Logical Learning and Reasoning With Graphs (finally, after six years!)**  
  The **Graph Tsetlin Machine** is a novel deep learning model that enables **multimodal learning and reasoning** across directed and labeled multigraphs, marking a significant advancement after six years of development.

- **[D] multi-modal neural networks for time series?**  
  **Multi-modal neural networks** can be designed to forecast time series by integrating **auxiliary data** and **property embeddings**, enabling accurate predictions even with non-overlapping time series inputs.

- **TwoMinutePapers - New AI Can Barely Move…And Somehow Learns To Walk!**

- **YannicKilcher - GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models**