Simple Linear Corrections for Compression in Late Interaction
cs.IR, cs.CL, cs.LG
Submitted: 2026-10-09
Updated: 2026-10-09
Sources
- On Strengths and Limitations of Single-Vector Embeddings
- On the Theoretical Limitations of Embedding-Based Retrieval
- Multi-Vector Embeddings are Provably More Expressive than Single Vector Embeddings
- Nemotron ColEmbed V2: Top-Performing Late Interaction Embedding Models for Visual Document Retrieval
- M3DR: Towards Universal Multilingual Multimodal Document Retrieval
- PLAID: An Efficient Engine for Late Interaction Retrieval
- MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction
- Multi-Vector Index Compression in Any Modality
- A Study on Token Pruning for ColBERT
- Reducing the Footprint of Multi-Vector Retrieval with Minimal Performance Impact via Token Pooling
- DocPruner: A Storage-Efficient Framework for Multi-Vector Visual Document Retrieval via Adaptive Patch-Level Embedding Pruning
- Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework
- Visual Late Chunking: An Empirical Study of Contextual Chunking for Efficient Visual Document Retrieval
- A Brief Comparison of Training-Free Multi-Vector Sequence Compression Methods
- EigenLI: Spectral Approximations to Late Interaction
- Quantifying and Expanding the Theoretical Capacity of Late-Interaction Retrieval Models
- Near-Optimal Dimension Lower Bounds for Single-Vector Embeddings of Maximum Inner Product Similarity
- Learn to Pool: Lightweight Fine-Tuning for Flexible Multi-Vector Compression
- Static Pruning in Dense Retrieval using Matrix Decomposition
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