2 papers
cs.AI2026
FlowBlock: Wavefront-Parallel Decoding for Self-Correcting Diffusion Language Models
Bing Tian, Haikun Liu, Xiaocheng Zhong +5
Block-wise diffusion large language models (dLLMs) decode sequentially at the block level, enabling effective KV-cache reuse across blocks but making inter-block decoding strictly…
cs.IR2024
FusionANNS: An Efficient CPU/GPU Cooperative Processing Architecture for Billion-scale Approximate Nearest Neighbor Search
Bing Tian, Haikun Liu, Yuhang Tang +6
Approximate nearest neighbor search (ANNS) has emerged as a crucial component of database and AI infrastructure. Ever-increasing vector datasets pose significant challenges in term…