Multi-Scale Local Speculative Decoding for Image Generation
Autoregressive (AR) models have achieved remarkable success in image synthesis, yet their sequential nature imposes significant latency constraints. Speculative Decoding offers a promising avenue for acceleration, but existing approaches are limited by token-level ambiguity and lack of spatial awareness. In this work, we introduce Multi-Scale Local Speculative Decoding (MuLo-SD), a novel framework that combines multi-resolution drafting with spatially informed verification to accelerate AR image generation. Our method leverages a low-resolution drafter paired with an up-sampling step to propose candidate image tokens, which are then verified in parallel by a high-resolution target model. Crucially, we incorporate a local rejection and resampling mechanism, enabling efficient correction of draft errors by focusing on spatial neighborhoods rather than raster-scan resampling after the first rejection. When integrated with parallel decoding resampling, MuLo-SD achieves substantial speedups -- up to $\mathbf{5\times}$ -- outperforming both speculative decoding and parallel decoding baselines in terms of acceleration, while maintaining comparable semantic alignment and perceptual quality. These results are validated using GenEval, DPG-Bench, and FID/HPSv2 on the MS-COCO 5k validation split. Extensive ablations highlight the impact of up-sampling design, probability pooling, and local rejection and resampling with neighborhood expansion. Our approach sets a new state-of-the-art in speculative decoding for image synthesis, bridging the gap between efficiency and fidelity. Project page is available at https://qualcomm-ai-research.github.io/mulo-sd-webpage/ .
Code (0)
등록된 구현이 없습니다.
Tasks
Image GenerationSimilar Papers 제목 키워드 기반
Efficient Speculative Decoding for Llama at Scale: Challenges and Solutions
Speculative decoding is a standard method for accelerating the inference speed of large language models. However, scaling it for production environments poses several engineering challenges, including efficiently impleme…
Annealed Relaxation of Speculative Decoding for Faster Autoregressive Image Generation
Despite significant progress in autoregressive image generation, inference remains slow due to the sequential nature of AR models and the ambiguity of image tokens, even when using speculative decoding. Recent works atte…
Image GenerationAccelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding
RL post-training of frontier language models is increasingly bottlenecked by autoregressive rollout generation, making rollout acceleration a central systems challenge. Many existing efficiency methods improve throughput…
On Speculative Decoding for Multimodal Large Language Models
Inference with Multimodal Large Language Models (MLLMs) is slow due to their large-language-model backbone which suffers from memory bandwidth bottleneck and generates tokens auto-regressively. In this paper, we explore …
Image CaptioningLanguage ModelingLanguage ModellingLarge Language ModelSTree: Speculative Tree Decoding for Hybrid State-Space Models
Speculative decoding is a technique to leverage hardware concurrency to improve the efficiency of large-scale autoregressive (AR) Transformer models by enabling multiple steps of token generation in a single forward pass…
State Space Models