ColNanoVDR: Document-Free Query Distillation for Multi-Vector Visual Document Retrieval via Optimal Transport
cs.IR, cs.CL, cs.CV
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/Ryenhails/NanoVDR
Terminology
Sources
- Wasserstein Contrastive Representation Distillation
- JaColBERTv2.5: Optimising Multi-Vector Retrievers to Create State-of-the-Art Japanese Retrievers with Constrained Resources
- Reducing the Footprint of Multi-Vector Retrieval with Minimal Performance Impact via Token Pooling
- Multi-Level Optimal Transport for Universal Cross-Tokenizer Knowledge Distillation on Language Models
- MUVERA: Multi-Vector Retrieval via Fixed Dimensional Encodings
- Exploring Dual Encoder Architectures for Question Answering
- A Unified Framework for Implicit Sinkhorn Differentiation
- ColPali: Efficient Document Retrieval with Vision Language Models
- Introducing Neural Bag of Whole-Words with ColBERTer: Contextualized Late Interactions using Enhanced Reduction
- ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT
- EmbedDistill: A Geometric Knowledge Distillation for Information Retrieval
- Distilling Dense Representations for Ranking using Tightly-Coupled Teachers
- Structural Anchor Pruning: Training-Free Multi-Vector Compression for Visual Document Retrieval
- NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval
- ViDoRe V3: A Comprehensive Evaluation of Retrieval Augmented Generation in Complex Real-World Scenarios
- Differential Properties of Sinkhorn Approximation for Learning with Wasserstein Distance
- Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings
- ViDoRe Benchmark V2: Raising the Bar for Visual Retrieval
- LightCLIP: Learning Multi-Level Interaction for Lightweight Vision-Language Models
- Computational Optimal Transport
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
- RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendation
- Right Family, Wrong Skill: Evaluating Risk Exposure in Agent Skill Retrieval
- UltRAG: a Universal Simple Scalable Recipe for Knowledge Graph RAG