Skip to main content
Search

# Visual Document Retrieval

3 related articles

Subscribe to updates
  1. arXiv

    Retrieval stops chasing one gold chunk: Perplexity's new embedders rank answers and their supporting evidence together

    Perplexity released the pplx-embed-v2-context family, which distills graded chunk-level relevance from a query-aware context compression model instead of gold-chunk labels, so training targets no longer depend on how a document is chunked. The 9B model beats the strongest baseline, voyage-context-4, by 14.4 points at Answer@10 on context-bench and leads on Q2D-Chunk and ConTEB; the 0.6B model shares the 9B embedding space, so a small model can query an index built with the large one.

    Sedigheh Eslami（First author）
    pplx-embed-v2-contextChunk-level relevance distillationContextual EmbeddingsQ2D-ChunkVisual Document Retrieval
  2. 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
  3. arXiv

    ColNanoVDR distills multi-vector visual document retrieval queries into a 149M text-only student, keeping about 95% of NDCG@5 and encoding queries 26x faster on one CPU thread

    The work introduces ColNanoVDR, which uses OTW, an entropic optimal-transport objective with learned token weights, to distill the query encoder of multi-vector visual document retrieval teachers into 149M text-only students without encoding or reading any page during training, retaining about 95% of the teachers' NDCG@5 on ViDoRe v1-v3, encoding queries up to 26x faster on a single CPU thread, and matching score distillation under identical training while reading 12.6x less cached teacher data.

    Aalto University
    Zhuchenyang Liu（First author）
    ColNanoVDROTW (Optimal Transport with Learned Weights)Query-Side DistillationVisual Document RetrievalOptimal Transport

You’re all caught up