Intent-Triggered Anchoring for Multi-Token Format Units in Parallel Decoding of Diffusion Language Models
cs.CL
Submitted: 2026-10-12
Updated: 2026-10-12
Comments: 17 pages
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Enabling Approximate Joint Sampling in Diffusion LMs
- CheXpert Plus: Augmenting a Large Chest X-ray Dataset with Text Radiology Reports, Patient Demographics and Additional Image Formats
- ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusion
- SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation
- SDAR-VL: Stable and Efficient Block-wise Diffusion for Vision-Language Understanding
- Training Verifiers to Solve Math Word Problems
- LLaDA-MedV: Exploring Large Language Diffusion Models for Biomedical Image Understanding
- MedGemma Technical Report
- Discrete Diffusion Language Models for Interactive Radiology Report Drafting
- Efficient Guided Generation for Large Language Models
- ReXGradient-160K: A Large-Scale Publicly Available Dataset of Chest Radiographs with Free-text Reports
- Lookahead-then-Verify: Reliable Constrained Decoding for Diffusion LLMs under Context-Free Grammars
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