FastGuide: Accelerating Reward Guidance for Diffusion Large Language Models
cs.CL, cs.LG
Submitted: 2026-09-28
Updated: 2026-09-28
Terminology
Sources
- Structuring The Future: Diffusion LLM Speculative Decoding via Calibrated Draft Graphs
- Accelerated Sampling from Masked Diffusion Models via Entropy Bounded Unmasking
- Adaptive Guidance: Training-free Acceleration of Conditional Diffusion Models
- SimSD: Simple Speculative Decoding in Diffusion Language Models
- A Survey on Diffusion Models for Inverse Problems
- Compress Guidance in Conditional Diffusion Sampling
- Self Speculative Decoding for Diffusion Large Language Models
- S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation
- Wide-In, Narrow-Out: Revokable Decoding for Efficient and Effective DLLMs
- Mercury: Ultra-Fast Language Models Based on Diffusion
- DAPD: Dependency-Aware Parallel Decoding via Attention for Diffusion LLMs
- Beyond Next-Token Prediction: A Performance Characterization of Diffusion versus Autoregressive Language Models
- KLASS: KL-Guided Fast Inference in Masked Diffusion Models
- Lookahead Sample Reward Guidance for Test-Time Scaling of Diffusion Models
- DyLLM: Efficient Diffusion LLM Inference via Saliency-based Token Selection and Partial Attention
- Cascade Reward Sampling for Efficient Decoding-Time Alignment
- Reward-Guided Speculative Decoding for Efficient LLM Reasoning
- dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching
- FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality
- dKV-Cache: The Cache for Diffusion Language Models
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering