Review
Aug 2026
Is Multimodal Speculative Decoding Ready for Diffusion-Based Parallel Drafting? A Survey and Empirical Diagnosis
A unified taxonomy that isolates drafter-side parallelism from orthogonal design choices such as tree construction and verification strategies is introduced, and a comprehensive empirical comparison of existing methods under varying degrees of parallelism across standardized multimodal benchmarks, including OCR, VQA, visual reasoning, and image captioning is provided.
Yantao Li, Huanlin Gao, Fang Zhao et al.
· 0 citations