Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Draft in Parallel, Condition Through Depth: Adjacent Causal Injection for Speculative Decoding
Haohui Zhang, Keyu Chen, Haocheng Sun +4
Parallel speculative drafting generates multiple candidates in one backbone pass, but independent token selection can produce inconsistent continuations that shorten the accepted p…
cs.LG2026
Training-Free Hashing-Based Attention via Binary Principal Components
Daohai Yu, Zhanpeng Zeng, Keyu Chen +6
Long-context large language models (LLMs) are increasingly deployed in real-world applications, yet self-attention remains a major efficiency bottleneck -- especially during decodi…