Test-Time Speculation
cs.CL, cs.LG
Submitted: 2026-05-10
Updated: 2026-11-16
Code: https://github.com/z-lab/dflash
Terminology
Sources
- PARD: Accelerating LLM Inference with Low-Cost PARallel Draft Model Adaptation
- LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs
- 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
- The Llama 3 Herd of Models
- Mamba: Linear-Time Sequence Modeling with Selective State Spaces
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Measuring Mathematical Problem Solving With the MATH Dataset
- CodeSearchNet Challenge: Evaluating the State of Semantic Code Search
- LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
- EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test
- Online Speculative Decoding
- GPQA: A Graduate-Level Google-Proof Q&A Benchmark
- Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
- SpecPV: Improving Self-Speculative Decoding for Long-Context Generation via Partial Verification
- Efficient Speculative Decoding for Llama at Scale: Challenges and Solutions
- Qwen3 Technical Report
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data