PulseAugur / Brief
EN
LIVE 22:48:35

Brief

last 24h
[2/2] 222 sources

Multi-source AI news clustered, deduplicated, and scored 0–100 across authority, cluster strength, headline signal, and time decay.

  1. TOOL · arXiv cs.AI English(EN) ·

    WriteSAE: Sparse Autoencoders for Recurrent State

    Researchers have developed WriteSAE, a novel sparse autoencoder designed to manipulate the matrix updates within recurrent language model states. This method learns rank-1 matrix atoms that directly replace the model's own matrix updates, showing a significant improvement in final token distribution accuracy. The technique has been successfully applied to models like Gated DeltaNet and Mamba-2, demonstrating its potential for steering model generation and understanding internal state dynamics. AI

    IMPACT Enables direct intervention and steering of recurrent language model states, potentially leading to more controllable and understandable AI generation.

  2. TOOL · arXiv cs.LG English(EN) ·

    Fast and Stable Triangular Inversion for Delta-Rule Linear Transformers

    Researchers have developed a new method for triangular inversion, a crucial operation in linear attention mechanisms used by advanced models like Qwen3.5/3.6 and Kimi Linear. This technique significantly improves the speed and numerical stability of this sub-routine, which is often a performance bottleneck. Experiments show up to a 4.3x speed-up on NPUs compared to existing implementations, leading to overall layer performance gains without sacrificing accuracy. AI

    IMPACT Improves efficiency of linear attention mechanisms, potentially enabling faster and more accurate long-context models.