SAGE: Accelerating Vision-Language Models via Entropy-Guided Adaptive Speculative Decoding
School of Computer Science（计算机科学学院）；Artificial Intelligence, Wuhan University of Technology, Hubei 430070, China（人工智能，武汉科技大学，湖北430070，中国）；School of Computer Science, Wuhan University, Hubei 430072, China（计算机科学学院，武汉大学，湖北430072，中国）
Speculative decoding has emerged as a promising approach to accelerate inference in vision-language models (VLMs) by enabling parallel verification of multiple draft tokens. However, existing methods rely on static tree structures that remain fixed throughout the decoding process, failing to adapt to the varying prediction difficulty across generation steps. This leads to suboptimal acceptance lengths and limited speedup. In this paper, we propose SAGE, a novel framework that dynamically adjusts the speculation tree structure based on real-time prediction uncertainty. Our key insight is that output entropy serves as a natural confidence indicator with strong temporal correlation across decoding steps. SAGE constructs deeper-narrower trees for high-confidence predictions to maximize speculation depth, and shallower-wider trees for uncertain predictions to diversify exploration. SAGE improves acceptance lengths and achieves faster acceleration compared to static tree baselines. Experiments on multiple benchmarks demonstrate the effectiveness of SAGE: without any loss in output quality, it delivers up to $3.36\times$ decoding speedup for LLaVA-OneVision-72B and $3.18\times$ for Qwen2.5-VL-72B.
College of Software Engineering, Southeast University（东南大学软件工程学院）；School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）；School of Cyber Science and Engineering, Southeast University（东南大学网络空间安全学院）；School of Computing and Information Systems, Singapore Management University（新加坡管理大学计算机与信息系统学院）
Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding
The University of Hong Kong（香港大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；CUHK（香港中文大学）；Tsinghua University（清华大学）；Shanghai Jiao Tong University（上海交通大学）；Infinigence AI（智源人工智能）
HIPPO: Accelerating Video Large Language Models Inference via Holistic-aware Parallel Speculative Decoding
University of Science and Technology of China（中国科学技术大学）；Shanghai AI Laboratory（上海人工智能实验室）；Department of Electronic Engineering, Tsinghua University（清华大学电子工程系）
SpeCa: Accelerating Diffusion Transformers with Speculative Feature Caching
Shanghai Jiao Tong University（上海交通大学）；Shandong University（山东大学）；University of Electronic Science and Technology of China（电子科学与技术大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））；Tsinghua University（清华大学）；National University of Singapore（新加坡国立大学）
Continuous Speculative Decoding for Autoregressive Image Generation
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；MAIS, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所多模态人工智能系统实验室）；JD.COM Inc（京东集团股份有限公司）；China Tower Corporation Limited（中国铁塔股份有限公司）
XSpecMesh: Quality-Preserving Auto-Regressive Mesh Generation Acceleration via Multi-Head Speculative Decoding
Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University（教育部多媒体可信感知与高效计算重点实验室，厦门大学）；Shandong Inspur Database Technology Co.,Ltd（山东浪潮数据库技术有限公司）
