Kimi Delta Attention
PulseAugur coverage of Kimi Delta Attention — every cluster mentioning Kimi Delta Attention across labs, papers, and developer communities, ranked by signal.
2 天有情绪数据
-
PapersWithCode 增加多指标排行榜和外部论文支持
Hugging Face 为 PapersWithCode（一个跟踪人工智能最新进展的平台）推出了新功能。更新包括支持排行榜上的多个指标，例如自动语音识别和目标检测。该平台现在还支持 arXiv 以外的外部论文，自动为其添加相关标签和数据，并显示论文的演变过程，以展示后续或先前的研究。
-
NVIDIA 发布 Gated DeltaNet-2 以改进线性注意力
NVIDIA 推出了 Gated DeltaNet-2，这是一种新的线性注意力层，旨在改进循环神经网络中的内存编辑。该模型使用独立的通道门控机制，将擦除旧信息和写入新信息的过程分离开来，解决了先前 delta-rule 架构中的局限性。Gated DeltaNet-2 在 1000 亿 token 和 13 亿参数上进行了训练，在长上下文检索任务上表现优于 Mamba-2 和 KDA 等现有模型。
-
FG^2-GDN enhances long-context understanding with adaptive learning rates
Researchers have introduced FG$^2$-GDN, a novel approach to enhance long-context understanding in neural networks. This method improves upon existing Gated Delta Networks by replacing a scalar learning rate with a chann…
-
Moonshot AI open-sources FlashKDA, boosting Kimi Delta Attention 2.5x on H200 GPUs
Moonshot AI has released FlashKDA, an open-source implementation of Kimi Delta Attention. This new kernel achieves up to 2.5 times faster inference speeds on NVIDIA H200 GPUs. It is built using CUTLASS and optimized for…