arXiv Machine Learning June 11, 2026 By Yulin Yuan, Hongshuo Zhao, Xiangming Meng

Visual-Redundancy-Controlled Parallel Decoding for Diffusion-Based Multimodal Large Language Models

Read the original on arXiv Machine Learning →

arXiv:2605. 25820v2 Announce Type: replace Abstract: Diffusion-based multimodal large language models (dMLLMs) decode by iteratively predicting tokens at multiple masked positions in parallel.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Computation and Language

Aug 28

Visual Information-Guided Parallel Decoding for Diffusion Multimodal Large Language Models

Visual Information-Guided Parallel Decoding for Diffusion Multimodal Large Language Models introduces the VIG‑Sampler, a method that prioritizes tokens for decoding based on their attention to image tokens and penalizes redundancy in image‑attention distributions. The approach aims to improve the quality of multimodal generation by selecting more informative tokens during diffusion decoding. Experiments on seven captioning and VQA benchmarks with three open‑source dMLLMs show that VIG‑Sampler outperforms the Info‑Gain Sampler by an average of 19.3 CIDEr points and achieves better COCO Caption results using only half as many decoding steps.

By Insu Lee, Wooje Park, Wonseok Shin, Jinwoo Son, Byonghyo Shim

llms diffusion multimodal benchmarks

arXiv Computer Vision

Sep 22

Layer-Aware Position Embeddings for Visual Token Pruning in Multimodal Large Language Models

arXiv:2609.23715v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) incur substantial computational overhead due to the reliance on hundreds of visual tokens to represent images....

By Yahong Wang, Zhangkai Ni, Juncheng Wu, Yuyin Zhou, Ying Wen, Lianghua He

llms rag efficiency multimodal benchmarks

arXiv AI

Jul 28

MM-ShiftKV: Decode-Aware Prefill-Stage KV Selection for Multimodal Large Language Models

arXiv:2607. 22586v1 Announce Type: new Abstract: Key-Value (KV) caching is essential for efficient inference in multimodal large language models (MLLMs), yet its memory footprint grows linearly with context length and becomes a major bottleneck due to the large number of visual tokens.

By Jinsong Shu, Chenyang Wu, Zhongle Xie, Baokun Wang, Lidan Shou

llms efficiency multimodal benchmarks

arXiv AI

Jun 19

PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models

arXiv:2606. 19534v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have achieved remarkable progress in visual understanding tasks.

By Yueyi Sun, Yuhao Wang, Jason Li, Ye Tian, Tao Zhang, Jacky Mai, Yihan Wang, Haochen Wang, Jinbin Bai, Ling Yang, Yunhai Tong

llms diffusion multimodal benchmarks

arXiv Computer Vision

3d ago

DecoMoE: Decoupling Visual Propagation and Expert Computation for Efficient Multimodal MoE Inference

arXiv:2609.38823v1 Announce Type: new Abstract: Multimodal mixture-of-experts (MoE) models combine sparse expert activation with visual-language capabilities, yet their inference remains costly becau...

By Xudong Tan, Peng Ye, Ming Xie, Chenyu Huang, Yaoxin Yang, Jiayuan Fan, Tao Chen

multimodal benchmarks

arXiv AI

Sep 10

STAR-Pro: Stage-Wise Token Adaptive Reduction with Progressive Refinement for Efficient Large Vision-Language Models

arXiv:2609.05916v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) achieve strong multimodal understanding, but the hundreds to thousands of visual tokens they process impose subs...

By Yichen Guo, Tinghao Wang, Qizhe Zhang, Lingbei Meng, Yuan Zhang, Jiajun Cao, Hao Jiang, Chenwei Wu, Jixian Wu, Sixiang Chen, Tao Luo, Hongyang Cheng, Kai Tang, Chenxi Li, Renyuan Li, Xiande Huang, Wenya Wang, Shanghang Zhang

llms efficiency multimodal benchmarks

One email a morning, machine-written

Related stories

Visual Information-Guided Parallel Decoding for Diffusion Multimodal Large Language Models

Layer-Aware Position Embeddings for Visual Token Pruning in Multimodal Large Language Models

MM-ShiftKV: Decode-Aware Prefill-Stage KV Selection for Multimodal Large Language Models

PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models

DecoMoE: Decoupling Visual Propagation and Expert Computation for Efficient Multimodal MoE Inference

STAR-Pro: Stage-Wise Token Adaptive Reduction with Progressive Refinement for Efficient Large Vision-Language Models