Showing cs.LGShow all
3 papers · 1 filter
cs.LG2025
Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing
Xu Wang, Chenkai Xu, Yijie Jin +3
Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to autoregressive (AR) LLMs for text generation, with the potential to decode multiple tokens in a s…
cs.LG2025
Scaling Speculative Decoding with Lookahead Reasoning
Yichao Fu, Rui Ge, Zelei Shao +2
Reasoning models excel by generating long chain-of-thoughts, but decoding the resulting thousands of tokens is slow. Token-level speculative decoding (SD) helps, but its benefit is…
cs.LG2025
MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection
Bokai Lin, Zihao Zeng, Zipeng Xiao +5
KV cache has become a de facto technique for the inference of large language models (LLMs), where tensors of shape (layer number, head number, sequence length, feature dimension) a…