Inverting Multi-Vector Visual Document Indices
cs.IR, cs.CL, cs.CV
Submitted: 2026-10-07
Updated: 2026-10-07
Sources
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- TextDiffuser: Diffusion Models as Text Painters
- Reducing the Footprint of Multi-Vector Retrieval with Minimal Performance Impact via Token Pooling
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Inverting Visual Representations with Convolutional Networks
- Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
- ColPali: Efficient Document Retrieval with Vision Language Models
- Transform Before You Query: A Privacy-Preserving Approach for Vector Retrieval with Embedding Space Alignment
- Classifier-Free Diffusion Guidance
- ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT
- Zero2Text: Zero-Training Cross-Domain Inversion Attacks on Textual Embeddings
- PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR System
- Flow Matching for Generative Modeling
- Understanding Deep Image Representations by Inverting Them
- Text Embeddings Reveal (Almost) As Much As Text
- Language Model Inversion
- Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation
- Survey of Vector Database Management Systems
- PLAID: An Efficient Engine for Late Interaction Retrieval
Related papers
- The Price of Isolation: Estimating the Ecosystem Cost of Symmetric Two-Sided A/B Testing
- SCAR: Semantic Continuity-Aware Retrieval for Efficient Context Expansion in RAG
- MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora
- How Do LLM-Generated Texts Impact Term-Based Retrieval Models?
- MemSyco-Bench: Benchmarking Sycophancy in Agent Memory
- Training with Missed Targets in Generative Recommendation: Separating Supervision from Probability Competition