WhiFlash: Accelerating Speculative Decoding with Token-Level Cross-Paradigm Routing

arXiv:2606.07710 · cs.LG, cs.AI · Submitted 2026-06-05 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-06-05

Updated: 2026-09-01

Comments: Accepted at EMNLP 2026

Code: https://github.com/tatsu-lab/stanford_alpaca

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

Terminology

• Speculative Decoding — 20× in this paper · explained in 2 episodes
• Accuracy — 7× in this paper · explained in 1 episode
• KV cache — 7× in this paper · explained in 3 episodes
• Transformer — 5× in this paper · explained in 2 episodes
• Calibration — 4× in this paper · explained in 7 episodes
• Core — 3× in this paper · explained in 2 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Block Diffusion — 2× in this paper · explained in 2 episodes
• Computational overhead — 2× in this paper · explained in 2 episodes
• Verification — 2× in this paper · explained in 2 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Agentic Flow — 1× in this paper · explained in 1 episode
• Agentic Loop — 1× in this paper · explained in 1 episode
• Agentic System — 1× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• Homogeneity — 1× in this paper · explained in 2 episodes
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Test-time Scaling — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• gpt-oss-120b & gpt-oss-20b Model Card
• Program Synthesis with Large Language Models
• Qwen3-Coder-Next Technical Report
• Accelerating Large Language Model Decoding with Speculative Sampling
• DFlash: Block Diffusion for Flash Speculative Decoding
• Evaluating Large Language Models Trained on Code
• Training Verifiers to Solve Math Word Problems
• Olmo 3
• When, What, and How: Rethinking Retrieval-Enhanced Speculative Decoding
• The Llama 3 Herd of Models
• Gaussian Error Linear Units (GELUs)
• Multi-Drafter Speculative Decoding with Alignment Feedback
• Adam: A Method for Stochastic Optimization
• AgentInstruct: Toward Generative Teaching with Agentic Flows
• DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
• Accelerating Speculative Decoding with Block Diffusion Draft Trees
• TALON: Confidence-Aware Speculative Decoding with Adaptive Token Trees
• Qwen3 Technical Report

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks