SpecFold: Folding Multi-Branch Redundancy for Faster Speculative Decoding in Diffusion Language Models
cs.AI, cs.CL, cs.LG
Submitted: 2026-10-04
Updated: 2026-10-06
Code: https://github.com/chungen04/specfold
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models
- Program Synthesis with Large Language Models
- LLaDA2.0: Scaling Up Diffusion Language Models to 100B
- LLaDA2.1: Speeding Up Text Diffusion via Token Editing
- Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed
- Self Speculative Decoding for Diffusion Large Language Models
- A Comparative analysis of Layer-wise Representational Capacity in AR and Diffusion LLMs
- Hydragen: High-Throughput LLM Inference with Shared Prefixes
- DiffuSpec: Unlocking Diffusion Language Models for Speculative Decoding
- dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching
- dKV-Cache: The Cache for Diffusion Language Models
- Large Language Diffusion Models
- Fast-dLLM v2: Efficient Block-Diffusion LLM
- BlockBatch: Multi-Scale Consensus Decoding for Efficient Diffusion Language Model Inference
- Dream 7B: Diffusion Large Language Models
- LLaDA-MoE: A Sparse MoE Diffusion Language Model
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems