Reliable Parallel Decoding in Masked Diffusion Language Models
cs.CL, cs.AI
Submitted: 2026-09-29
Updated: 2026-09-29
Terminology
Sources
- Program Synthesis with Large Language Models
- Eliciting Latent Predictions from Transformers with the Tuned Lens
- Evaluating Large Language Models Trained on Code
- From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step
- DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models
- Measuring Mathematical Problem Solving With the MATH Dataset
- DAPD: Dependency-Aware Parallel Decoding via Attention for Diffusion LLMs
- Stability-Weighted Decoding for Diffusion Language Models
- LoPA: Scaling dLLM Inference via Lookahead Parallel Decoding
- Dream 7B: Diffusion Large Language Models
- Ripple-Pivot Search: Active Parallel Decoding for Diffusion Large Language Models
- Answer First, Reason Later: When Commitment Order Costs Accuracy in 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