Showing cs.LGShow all
3 papers · 1 filter
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…
cs.LG2026
HyperDFlash: Hyper-Connection-Aligned Block Speculative Decoding with Gated Residual Reduction
Luxi Lin, Shuang Peng, Rui Ma +7
We present HyperDFlash, a block-parallel speculative decoding framework tailored to DeepSeek-V4's Hyper-Connections (HC). Despite the strong performance of DeepSeek-V4's native Mul…
cs.LG2026
Efficiently Aligning Draft Models via Parameter- and Data-Efficient Adaptation
Luxi Lin, Zhihang Lin, Zhanpeng Zeng +5
Speculative decoding accelerates LLM inference but suffers from performance degradation when target models are fine-tuned for specific domains. A naive solution is to retrain draft…