← Search

Yanran Wu

2 accepted papers

2025

Reward-Shifted Speculative Sampling Is An Efficient Test-Time Weak-to-Strong Aligner

EMNLP 2025

Aligning large language models (LLMs) with human preferences has become a critical step in their development. Recent research has increasingly focused on test-time alignment, where additional compute is allocated during inference to enhance LLM safety and reasoning capabilities. However, these test-

2025

Unveiling Environmental Impacts of Large Language Model Serving: A Functional Unit View

ACL 2025long

Large language models (LLMs) offer powerful capabilities but come with significant environmental impact, particularly in carbon emissions. Existing studies benchmark carbon emissions but lack a standardized basis for comparison across different model configurations. To address this, we introduce the…