Multimodal Reranking

Follow this topic Ask about this topic

Momentum

2 papers in the last four weeks, down 33% on the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 14

All topics

RankGround: Efficient High-Resolution GUI Grounding via Lightweight Reranker-Guided Crop Selection
Sep 16, 2026Liyang Fan, Xinping Bi, Yitai Li +3Efficient Multimodal Inference Multimodal Reranking
College of Computer Science and Software Engineering Shenzhen University Shenzhen, China · Shenzhen Key Laboratory for High Performance Data Mining Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences Shenzhen, China · Shenzhen University of Advanced Technology Shenzhen, China
Bridging the Semantic-Utility Gap in Multimodal RAG via Generator-in-the-Loop Alignment
Sep 8, 2026Zhan-Lun Chang, Dong-Jun Han, Seyyedali Hosseinalipour +2Multimodal RAG Multimodal Reranking
Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN 47907, USA · Department of Computer Science and Engineering, Yonsei University, Seoul 03722, Republic of Korea · Department of Electrical Engineering, University at Buffalo–SUNY, Buffalo, NY 14260, USA
AutoConcept: Training-Free Concept-Guided Reranking for Metadata-Available Composed Image Retrieval
Sep 1, 2026Tianyu Wang, Tianjiao WuMultimodal Reranking Image Retrieval
School of Computer Science and Technology, Soochow University, Suzhou, China · INSTITUT NATIONAL DES SCIENCES APPLIQUEES DE LYON, Lyon, France
From Saliency to Discriminability: Rank-Preserving Visual Token Pruning for VLM Rerankers
Sep 1, 2026Siyi Liu, Hanjun Yang, Chenchen Zhang +7Efficient VLM Inference Multimodal Reranking
1The Hong Kong University of Science and Technology (Guangzhou) · 2Tencent Yuanbao · 3ARC Lab, Tencent
Heterogeneous Vision-Language Ensemble with Disagreement-Aware Reranking for Text-Based Person Anomaly Retrieval
Aug 13, 2026Huu-An Vu, Cam Tu Tran Thi, Thanh Toan Le Ngo +5Vision-Language Models Multimodal Reranking
Hanoi University of Science and Technology, Hanoi, Vietnam · GenAI4E Lab · University of Information Technology, VNU-HCM, Ho Chi Minh City, Vietnam +4
UniHEAR: Unified Heterogeneous-Source Attentive Retrieval for Knowledge-Based Visual Question Answering
Aug 2, 2026Ganzhong Luo, Yang Ren, Hanyong Wang +2Multimodal IR Multimodal Reranking
School of Aeronautics and Astronautics, Sichuan University
Multimodal LLM-Empowered Re-Ranking for Generalizable Person Re-Identification
Jun 15, 2026Jiachen Li, Xiaojin GongMultimodal Reranking Multimodal Large Language Models
College of Information Science and Electronic Engineering Zhejiang University
PRISMR: Overcoming Parse Collapse in Multimodal Listwise Ranking via Parameterized Representation Internalization
Jun 11, 2026Hao Jiang, Xin Li, Annan Wang +4Multimodal IR Learning to Rank
1Nanyang Technological University · 2Peking University · 3Independent Researcher
Dual-Route Top-K Retrieval with 1v1 VLM Reranking for the CoVR-R
May 31, 2026Yuyang Sun, Yongliang Wu, Xingyu Zhu +8Multimodal Reranking Cross-Modal Retrieval
Southeast University · National University of Singapore · Independent Researcher +2
Reason, Retrieve, Re-rank: A Zero-Shot Reasoning-Aware Framework for Composed Video Retrieval
May 30, 2026Ali AlaviMultimodal Reranking Cross-Modal Retrieval
The Ohio State University
CCS: Clinical Consensus Selection for Radiology Report Generation
May 28, 2026Xi Zhang, Yingshu Li, Zaiqiao Meng +2Radiology Report Generation Radiology VLMs
School of Computing Science, University of Glasgow · School of Electrical and Computer Engineering, University of Sydney · Language Technology Lab, University of Cambridge
OSGNet with MLLM Reranking @ Ego4D Episodic Memory Challenge 2026
May 20, 2026Yisen Feng, Leigang Qu, Haoyu Zhang +5Temporal Video Grounding Multimodal Reranking
Harbin Institute of Technology (Shenzhen) · National University of Singapore · Pengcheng Laboratory +2
Very Efficient Listwise Multimodal Reranking for Long Documents
May 12, 2026Yiqun Sun, Pengfei Wei, Lawrence B. HsiehMultimodal IR Efficient Multimodal Inference
Magellan Technology Research Institute (MTRI), Japan.
MEG-RAG: Quantifying Multi-modal Evidence Grounding for Evidence Selection in RAG
Apr 27, 2026Xihang Wang, Zihan Wang, Chengkai Huang +2Multimodal RAG Multimodal IR
Peking University Beijing, China · University of New South Wales, Macquarie University Sydney, Australia · University of New South Wales, CSIRO’s Data61 Sydney, Australia

Sep 16, 2026, cs.CVJ/K move · Enter open · S save

RankGround: Efficient High-Resolution GUI Grounding via Lightweight Reranker-Guided Crop Selection

Liyang Fan, Xinping Bi, Yitai Li, Shuaimin Li+2

College of Computer Science and Software Engineering Shenzhen University Shenzhen, China · Shenzhen Key Laboratory for High Performance Data Mining Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences Shenzhen, China · Shenzhen University of Advanced Technology Shenzhen, China

Efficient Multimodal Inference Multimodal Reranking GUI Grounding Vision-Language Grounding

Open paper AskPDF arXiv

Graphical User Interface (GUI) grounding is a fundamental perception task for multimodal agents, enabling them to interpret natural language instructions and interact with digital interfaces. Existing methods face a fundamental trade-off between accuracy and efficiency: direct full-image inference often fails to capture small or visually similar UI elements, while multi-crop strategies improve localization at the cost of multiple expensive Vision-Language Model (VLM) calls per query. To address this challenge, we propose RankGround, a two-stage framework that achieves accurate GUI grounding with a single VLM call per query. Central to our approach is GroundRanker, a lightweight multimodal reranker that identifies the most promising crop from a dense candidate set. Because no off-the-shelf ranking dataset is available, we construct ranking supervision data from existing grounding datasets. A strict containment criterion and boundary-aware positive augmentation improve alignment and spatial coverage in cluttered layouts. GroundRanker is then trained with a two-stage curriculum: a pointwise objective first learns coarse containment, and a listwise objective refines subtle semantic and spatial distinctions among visually similar crops. Experimental results show that RankGround consistently outperforms strong baselines while reducing computational cost. It achieves 1.4 times faster inference and improves localization accuracy by 5.5% on average over the second-best method across all backbones and screen scales, establishing a new state of the art in both efficiency and precision for GUI grounding.

Momentum

Related topics

Latest papers 14