SpecCTMC: Exact Speculative Simulation of Diffusion Language Model Continuous-Time Markov Chains
cs.CL
Submitted: 2026-11-05
Updated: 2026-11-05
Code: https://github.com/kasakh/specctmc
Terminology
Sources
- Structuring The Future: Diffusion LLM Speculative Decoding via Calibrated Draft Graphs
- Program Synthesis with Large Language Models
- Speculative Sampling for Parametric Temporal Point Processes
- Accelerating Large Language Model Decoding with Speculative Sampling
- Optimal Inference Schedules for Masked Diffusion Models
- SpecFold: Folding Multi-Branch Redundancy for Faster Speculative Decoding in Diffusion Language Models
- Fast-dLLM++: Fr'echet Profile Decoding for Faster Diffusion LLM Inference
- Sharp Convergence Rates for Masked Diffusion Models
- Dependency-Guided Parallel Decoding in Discrete Diffusion Language Models
- Accelerating Speculative Diffusions via Block Verification
- PSD: Pushing the Pareto Frontier of Diffusion LLMs via Parallel Speculative Decoding
- LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning
- Query-Efficient Rejection Sampling for Parallel Masked Diffusion
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