Preprint

To Explore The Strange New World Beyond Data Distribution: System Behavior, Causality Tax, and Non-causal Base Model

We show that the causality of language models may not be necessary nor optimal when system behavior is incorporated as a first-principle Bayesian feature. We propose the SBD …

xianzhi-zeng
•

LiteTopK: Exploiting the Curse of Dimensionality for a Fused Indexer-TopK Kernel in Long-Context Sparse Attention

Indexer-TopK, the operation to compute the scores and select the top-k candidates, is widely used by sparse attention kernels in large language models and vector retrieval in …

ziqi-yin
•