Ceiling-Clipped Acceptance Histograms Indicate Stranded Speed-up in Block-Diffusion Speculative Decoding

arXiv:2608.30427 · cs.CL, cs.LG · Submitted 2026-08-31 · Read on arXiv

cs.CL, cs.LG

Submitted: 2026-08-31

Updated: 2026-08-31

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 94× in this paper · explained in 2 episodes
• Decode — 17× in this paper · explained in 2 episodes
• Speculative Decoding — 12× in this paper · explained in 2 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Verification — 5× in this paper · explained in 2 episodes
• Block Diffusion — 4× in this paper · explained in 2 episodes
• Distribution Shift — 3× in this paper · explained in 5 episodes
• International Conference on Machine Learning — 3× in this paper
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Verifier — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Decoupling — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Thinking mode — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• Accelerating Large Language Model Decoding with Speculative Sampling
• Gemma 4 Technical Report
• JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting
• Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding
• Bastion: Budget-Aware Speculative Decoding with Tree-structured Block Diffusion Drafting
• Qwen3 Technical Report
• Accelerating Speculative Decoding with Block Diffusion Draft Trees
• Teaching Diffusion to Speculate Left-to-Right
• D-PACE: Dynamic Position-Aware Cross-Entropy for Parallel Speculative Drafting
• DFlare: Scaling Up Draft Capacity for Block Diffusion Speculative Decoding
• Cost-Aware Diffusion Draft Trees for Speculative Decoding

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering