speculative decoding

AdaSpec: Adaptive Multilingual Speculative Decoding with Self-Synthesized Language-Aware Training and Vocabulary Simplification AAAI 2026 An Empirical Study of Speculative Decoding for Small Language Models EACL 2026 Annealed Relaxation of Speculative Decoding for Faster Autoregressive Image Generation AAAI 2026 Benchmarking the Energy Savings with Speculative Decoding Strategies EACL 2026 Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration OSDI 2026 Calibrated Speculative Decoding: Frequency-Guided Candidate Selection for Efficient Inference ACL 2026 ConfSpec: Efficient Step-Level Speculative Reasoning via Confidence-Gated Verification ACL 2026 Democratizing LLM Efficiency: From Hyperscale Optimizations to Universal Deployability AAAI 2026 DIAA: A Decoding-Efficient Inference Acceleration Approach for On-Device Large Language Models AAAI 2026 DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation ACL 2026 E$^2$-SCI: Elastic Edge-Cloud Speculative Decoding via Credit Inertia CVPR 2026 EDSD: Entropy-Driven Design for Faster Speculative Decoding ACL 2026 FastV-RAG: Towards Fast and Fine-Grained Video QA with Retrieval-Augmented Generation ACL 2026 FlashMesh: Faster and Better Autoregressive Mesh Synthesis via Structured Speculation CVPR 2026 HCSpec: Two-Tier Horizontal Cascade Speculative Decoding for High-Efficiency Large Language Model Inference ACL 2026 HeteroSpec: Leveraging Contextual Heterogeneity for Efficient Speculative Decoding ACL 2026 Inference in the Shadows: Taming Memory Bandwidth Contention in Mobile LLM Inference with Sereno OSDI 2026 Jakiro: Boosting Speculative Decoding via Decoupled MoE ACL 2026 KAD: A Framework for Proxy-based Test-time Alignment with Knapsack Approximation Deferral EACL 2026 LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification ACL 2026 Look Before You Leap: A Lookahead Reasoning Quality Gate for Speculative Decoding EACL 2026 Multi-Scale Local Speculative Decoding for Image Generation CVPR 2026 ParallelVLM: Lossless Video-LLM Acceleration with Visual Alignment Aware Parallel Speculative Decoding CVPR 2026 PIX-TAB: Efficient PIXel-Precise TABle Structure Recognition Approach with Speculative Decoding and Region-Based Image Segmentation CVPR 2026 Scaling LLM Speculative Decoding: Non-Autoregressive Forecasting in Large-Batch Scenarios AAAI 2026