Showing cs.AIShow all
3 papers · 1 filter
cs.AI2026
XPress: Parallel Refinement for Diffusion Drafters in Speculative Decoding
Zheng Wang, Davis Wertheimer, Yu Chin Fabian Lim +4
Block-diffusion drafters like dFlash generate an entire block of draft tokens in a single forward pass, drastically reducing the overhead of multiple-token drafting in speculative…
cs.AI2026
Quantization Inflates Reasoning: Token Inflation as a Hidden Cost of Low-Bit Reasoning Models
Xinyu Lian, Walid Krichene, Beichen Huang +4
Quantization is widely used to reduce the inference cost of large language models, but its effect on reasoning models is not fully captured by final-answer accuracy or per-token la…
cs.AI2026
PRESTO: Prefix-Aligned Tree Drafting for Diffusion Speculative Decoding
Zheng Wang, Zhifan Ye, Qi Cheng +8
Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to autoregressive (AR) LLMs, generating tokens in parallel. This makes them effective draft models f…