Skip to main content
Search

# Late-Interaction Retrieval

2 related articles

Subscribe to updates
  1. arXiv

    Researchers invert multi-vector visual document indices with a conditional flow-matching inverter, recovering 47% of words and 45% of sensitive tokens and ranking the source page first 98.4% of the time

    The work frames inversion of a multi-vector visual document index as conditional document image generation, identifying the encoder, inferring page shape and restoring shuffled order from the stored vectors alone under zero side information, and redrawing the page with a conditional flow-matching inverter; on ViDoRe v3, pages inverted from the raw index recover 47% of words and 45% of sensitive tokens and rank their source page first 98.4% of the time.

    Zhuchenyang Liu（First author）
    Embedding Inversion AttackVisual Document RetrievalFlow MatchingLate-Interaction Retrieval
  2. arXiv

    Sub-2B agents using semantic search for code localization beat grep on SWE-bench Lite and Multi-SWE-bench Flash while cutting CPU latency by 44.1%

    The authors introduce a two-stage training framework around colgrep, a local semantic search tool, combining supervised fine-tuning with turn-level credit based on retrieval outcomes and reinforcement learning on localization quality, and train three 1–1.7B-parameter models for file localization; on SWE-bench Lite and Multi-SWE-bench Flash, colgrep-equipped agents outperform matched grep agents at every training stage, with Qwen3-1.7B reaching 67.29 and 54.00 file F1 after weighted SFT plus RL, while using 29.1% fewer tokens and reducing end-to-end CPU latency by 44.1% and transferring better to seven languages unseen during fine-tuning.

    University of Copenhagen
    Maxence Lasbordes（First author）
    colgrepCode LocalizationAgentic SearchLate-Interaction RetrievalSupervised Fine-tuning

You’re all caught up