arXiv AI
Entropy-Aware Token Rejection for Improving Speculative Decoding
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computation and Language
2d ago
Beyond Tokens: Semantic-Aware Speculative Decoding for Efficient Inference by Probing Internal States
Large Language Models suffer from high inference latency, especially when generating long chains of thought. Existing speculative decoding methods draft and verify tokens in parallel but ignore semantic equivalence, causing inefficient rejections. The proposed SemanticSpec framework verifies entire semantic sequences by probing internal hidden states, achieving up to 2.7× speedup on DeepSeekR1-32B and 2.1× on QwQ-32B while outperforming token‑level and sequence‑level baselines in both efficiency and effectiveness.
arXiv AI
Jul 10
A Practical Investigation of Training-free Relaxed Speculative Decoding
arXiv:2607. 08690v1 Announce Type: cross Abstract: Speculative decoding accelerates sampling from an autoregressive LLM by using a faster auxiliary model to draft tokens which are then verified in parallel by the LLM.
arXiv AI
Jun 4
SSSD: Simply-Scalable Speculative Decoding
arXiv:2411. 05894v3 Announce Type: replace-cross Abstract: Speculative Decoding has emerged as a popular technique for accelerating inference in Large Language Models.
arXiv Computation and Language
2d ago
SFAD: Speculative Factuality-Aware Decoding
arXiv:2609.00796v1 Announce Type: new Abstract: As one of the most critical challenges in large language models, contextual faithfulness directly determines their reliability in knowledge-intensive a...
Hugging Face Trending Papers
Jul 9
A Practical Investigation of Training-free Relaxed Speculative Decoding
Speculative decoding accelerates sampling from an autoregressive LLM by using a faster auxiliary model to draft tokens which are then verified in parallel by the LLM. Standard speculative decoding is lossless: its rejection and resampling steps exactly preserve the LLM's sampling distribution.
arXiv Machine Learning
Aug 24
STS: Efficient Sparse Attention with Speculative Token Sparsity
arXiv:2605.15508v3 Announce Type: replace Abstract: The quadratic complexity of attention imposes severe memory and computational bottlenecks on Large Language Model (LLM) inference. This challenge i...