Vision-Language Alignment

Follow this topic Ask about this topic

Momentum

8 papers in the last four weeks, up 60% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 65

All topics

LEAD: Layer-wise Expert-aligned Decoding for Faithful Radiology Report Generation
Feb 4, 2026Ruixiao Yang, Yuanhe Tian, Di Dong +3Radiology Report Generation Medical Vision-Language Models
Beijing Institute of Technology · Zhongguancun Academy · Zhongguancun Institute of Artificial Intelligence +1
VISPA: Pluralistic Alignment via Automatic Value Selection and Activation
Jan 19, 2026Shenyan Zheng, Jiayou Zhong, Anudeex Shetty +3Pluralistic Alignment Large Language Model Alignment
University of Waterloo · University of Melbourne · Macquarie University +2
PathFLIP: Fine-grained Language-Image Pretraining for Versatile Computational Pathology
Dec 19, 2025Fengchun Liu, Songhan Jiang, Linghan Cai +2Whole-Slide Images Computational Pathology
Harbin Institute of Technology, Shenzhen, School of Computer Science and Technology · National University of Singapore, Department of Electronic and Computer Engineering
Accurate and Scalable Multimodal Pathology Retrieval via Attentive Vision-Language Alignment
Oct 27, 2025Hongyi Wang, Zhengjie Zhu, Junlin Hou +13Whole-Slide Images Digital Pathology
Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong SAR, China · College of Computer Science and Technology, Zhejiang University, Hangzhou, China. · School of Medicine, Wake Forest University, Winston-Salem, NC, USA. +11
ID-Align: RoPE-Conscious Position Remapping for Dynamic High-Resolution Adaptation in Vision-Language Models
May 27, 2025Bozhou Li, Wentao ZhangVision-Language Alignment Rotary Position Embedding
Peking University Beijing, China

Feb 4, 2026, cs.CLJ/K move · Enter open · S save

LEAD: Layer-wise Expert-aligned Decoding for Faithful Radiology Report Generation

Ruixiao Yang, Yuanhe Tian, Di Dong, Xu Yang+2

Beijing Institute of Technology · Zhongguancun Academy · Zhongguancun Institute of Artificial Intelligence+1

Radiology Report Generation Medical Vision-Language Models Vision-Language Alignment Medical Images Report Decoder Layers+2

Open paper AskPDF arXiv

Radiology Report Generation aims to produce accurate and coherent diagnostics from medical images. Although large vision-language models improve report fluency and accuracy, they still suffer from hallucinations by generating plausible pathological descriptions that are not supported by the input images. Existing methods primarily rely on external knowledge guidance to facilitate the alignment between generated text and visual information. However, these approaches often ignore the inherent decoding priors and vision-language alignment biases in pretrained models and lack robustness due to reliance on constructed guidance. In this paper, we propose Layer-wise Expert-aligned Decoding, a method that directly intervenes in the internal decoding process of large vision-language models. A pathology-specific expert module is designed to extract discriminative pathological features, which are then injected into each decoder layer through a gated mechanism. This architecture enables the large language model to progressively incorporate expert features during generation through a learned layer-wise gating function, thereby mitigating decoding biases and steering generation toward factual consistency. Experiments on multiple public datasets demonstrate that the proposed method improves clinical accuracy and factual consistency while maintaining competitive report generation quality.

Momentum

Related topics

Latest papers 65

LEAD: Layer-wise Expert-aligned Decoding for Faithful Radiology Report Generation

VISPA: Pluralistic Alignment via Automatic Value Selection and Activation

PathFLIP: Fine-grained Language-Image Pretraining for Versatile Computational Pathology

Accurate and Scalable Multimodal Pathology Retrieval via Attentive Vision-Language Alignment

ID-Align: RoPE-Conscious Position Remapping for Dynamic High-Resolution Adaptation in Vision-Language Models