2 papers
cs.LG2026
ExpBoN: Exponential-Noise Best-of- for Efficient Test-Time LLM Alignment
Yanxiao Liu, Sicheng Wan, Deniz Gündüz
Best-of- (BoN) sampling is a simple yet effective inference-time alignment method, but hard maximization provides only coarse control over the trade-off between reward and distr…
cs.CR2026
Watermarkable Multi-Draft Speculative Sampling via Poisson Processes
Yanxiao Liu, Sicheng Wan, Zhan Gao +1
Large language models (LLMs) have achieved state-of-the-art performance across a wide range of tasks, motivating two important aspects of deployment: inference efficiency and outpu…