activity
20242026
most citedUnified Active Retrieval for Retrieval Augmented Generation

2 citations · 3 across the 5 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

BitNest: Bit-Nested Speculative Decoding for Memory-Efficient LLM Inference Acceleration

Chence Yang, Ningxi Cheng, Arash Akbari +9

Speculative decoding accelerates autoregressive generation by using a lightweight draft to propose multiple tokens for parallel verification. However, existing methods often requir…