Faster but Different: Diagnosing and Controlling Content Drift in Accelerated Multimodal Diffusion Language Models
Yaoxuan Dou, Yang Shu
cs.CL
Submitted: 2026-07-31
Comments: 9 pages, 4 figures, 6 tables. Preprint
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models
- Accelerating Diffusion LLMs via Adaptive Parallel Decoding
- ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs
- Fast-dLLM++: Fr'{e}chet Profile Decoding for Faster Diffusion LLM Inference
- dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching
- Large Language Diffusion Models
- Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding
- LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning
- Visual-Redundancy-Controlled Parallel Decoding for Diffusion-Based Multimodal Large 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