Showing cs.CLShow all
2 papers · 1 filter
cs.CL2025
TokenTiming: A Dynamic Alignment Method for Universal Speculative Decoding Model Pairs
Sibo Xiao, Jinyuan Fu, Zhongle Xie +1
Accelerating the inference of large language models (LLMs) has been a critical challenge in generative AI. Speculative decoding (SD) substantially improves LLM inference efficiency…
cs.CL2025
Long Context Scaling: Divide and Conquer via Multi-Agent Question-driven Collaboration
Sibo Xiao, Zixin Lin, Wenyang Gao +2
Processing long contexts has become a critical capability for modern large language models (LLMs). Existing works leverage agent-based divide-and-conquer methods for processing lon…