Recurrence Meets Transformers for Universal Multimodal Retrieval
cs.CV, cs.AI, cs.CL, cs.MM
Submitted: 2025-09-10
Updated: 2026-08-27
Comments: TPAMI 2026
Code: https://github.com/aimagelab/ReT-2
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Unsupervised Dense Information Retrieval with Contrastive Learning
- SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
- Qwen2.5-VL Technical Report
- EVA-CLIP: Improved Training Techniques for CLIP at Scale
- The Llama 3 Herd of Models
- Joint Fusion and Encoding: Advancing Multimodal Retrieval from the Ground Up
- LLaMA: Open and Efficient Foundation Language Models
- R-Transformer: Recurrent Neural Network Enhanced Transformer
- Layer Normalization
- RoRA-VLM: Robust Retrieval-Augmented Vision Language Models
- Towards General Continuous Memory for Vision-Language Models
- mR squared AG: Multimodal Retrieval-Reflection-Augmented Generation for Knowledge-Based VQA
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models