Qualcomm（高通）

ConFu: Contemplate the Future for Better Speculative Sampling

ConFu：为更好的推测采样展望未来

Zongyue Qin, Raghavv Goel, Mukul Gagrani, Risheek Garrepalli, Mingu Lee, Yizhou Sun

机构 * University of California Los Angeles, United States（美国加州大学洛杉矶分校） ； Qualcomm AI Research, United States（高通人工智能研究） 纠错

AI总结 ConFu提出一种新的推测解码框架，通过引入展望令牌和软提示，使草案模型能利用目标模型的未来信号，提升生成速度和接受率。

Comments v3: Added stress test with long drafts (DL=12, top-k=1) and tail-acceptance (survival) analysis. Earlier versions added Qwen3-4B results and ablations