The paper introduces a principled framework for selecting multiple hidden-state layers from large language model decoders to improve speculative decoding. It uses matrix‑entropy to gauge informativeness and centered kernel alignment (CKA) to assess diversity, revealing distinct geometric and informational compartments across layers. The authors propose entropy‑ and CKA‑based selection algorithms, token‑entropy filtering, and demonstrate that these choices outperform traditional fixed‑layer heuristics in EAGLE3‑style decoding.
arXiv:2609.36590v1 Announce Type: cross Abstract: Self-speculative decoding accelerates large language model (LLM) inference by drafting tokens from the target model itself, but faces a sharp tradeof...
The paper introduces T2D, a framework that prunes and adapts a target large language model into a draft model optimized for both inference latency and alignment with the target model’s outputs. By formulating draft model design as an optimization problem, T2D achieves up to 92% pruning while maintaining high speculative decoding performance across multiple target model families and domains. The resulting draft models can also be integrated with other speculative decoding techniques to yield additional gains.
arXiv:2512.23765v2 Announce Type: replace-cross Abstract: Speculative decoding (SD) accelerates large language model (LLM) inference by using a lightweight draft model to propose tokens and a stronge...
arXiv:2606. 02544v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) have recently emerged as a promising alternative to autoregressive (AR) LLMs, offering faster inference through parallel or blockwise decoding.
arXiv:2608.29748v1 Announce Type: new Abstract: Speculative decoding accelerates autoregressive language model inference by having a lightweight draft model propose multiple candidate tokens, which a...
arXiv:2606. 29223v1 Announce Type: new Abstract: Autoregressive LLM decoding evaluates every generated token through the full layer stack, even though many tokens become predictable at intermediate depths.
WaveFront Decoding (WFD) is a training‑free, self‑speculative decoding framework for looped language models that reduces decoding latency by batching draft and verification steps within the same recurrent‑block calls. By exploiting intermediate recurrence outputs as draft predictions and weight sharing to process token states at different depths together, WFD arranges mixed‑depth states into a diagonal wavefront, allowing shallow‑depth drafting while deeper‑depth verification proceeds concurrently. Experiments on six Spec‑Bench task categories show WFD achieving up to 4.81× speedup on Huginn‑3.5B compared to autoregressive decoding, outperforming traditional draft‑then‑verify approaches.
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...
The paper introduces Speculative Probing, a method that repurposes the speculative‑decoding module of large language models for real‑time classification tasks. By appending a trained soft prompt to the target sequence, the approach leverages the already‑cached KV store during inference, adding negligible overhead while achieving higher accuracy than traditional hidden‑state probes. Experiments on four classification tasks across multiple models show that these lightweight probes outperform zero‑shot GPT‑5.4‑mini and rival or surpass specialized 8B safety classifiers without running a full LLM.
SimLens is a training‑free decoder that improves early‑layer predictions in large language models by keeping only the start token and a candidate answer token and performing a lightweight continuation through the remaining layers. It outperforms direct linear readouts, yielding higher accuracy on tasks such as ARC, BoolQ, and HeadQA with LLaMA‑7B and Vicuna‑7B. The method is extended to Linear SimLens for confidence estimation and combined into SimExit, a hybrid early‑exit mechanism that achieves significant speedups while maintaining accuracy.
arXiv:2606. 24957v1 Announce Type: cross Abstract: While speculative decoding improves inference throughput for multi-batch long-context Large Language Models (LLMs), its efficiency is often limited by a verification bottleneck where Key-Value (KV) cache loading dominates latency.
arXiv:2602. 20217v2 Announce Type: replace-cross Abstract: Self-speculative decoding (SSD) accelerates LLM inference by skipping layers to create an efficient draft model, yet existing methods often rely on static heuristics that ignore the dynamic computational overhead of attention in long-context scenarios.