Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

  • Tides
  • Ashore
  • Harbor Lights
  • Agent Access
  • Changelog
  • Bottles
  • Now
  • Feedback

External links

GitHubCloudborne ↗

© 2026 Pier.

WatchingResearchWatching0 independent reports0

Generative Late-Interaction Embeddings for Visual Document Retrieval

First seen · 9/10/2026, 04:00 AMLatest activity · 9/10/2026, 04:00 AM

Late-interaction search provides state-of-the-art accuracy for visual document retrieval at the cost of storing around 1,000 embeddings per page. Examining this representation, the authors show that page vectors lie on the unit sphere within a low-dimensional manifold of just five to six intrinsic dimensions. Leveraging this geometry, Generative Late-Interaction Embeddings (GLIE) indexes pages using only a few basis vectors and reconstructs the full embedding set on demand via a compact 415K-parameter decoder. On ViDoRe v1, indexing just four vectors per page preserves nearly 80% of uncompressed retrieval performance.

Event heat · last 24 hours

There are 7 persisted snapshots in the last 24 hours. Peak heat was 0 at 9/12, 20:00; latest heat is 0.

There are 7 persisted snapshots in the last 24 hours. Peak heat was 0 at 9/12, 20:00; latest heat is 0.10.509/12, 20:00, event heat 09/12, 23:00, event heat 09/13, 02:00, event heat 09/13, 05:00, event heat 09/13, 08:00, event heat 09/13, 11:00, event heat 09/13, 14:00, event heat 024 hours agoNow
  1. 9/12, 20:00, event heat 0
  2. 9/12, 23:00, event heat 0
  3. 9/13, 02:00, event heat 0
  4. 9/13, 05:00, event heat 0
  5. 9/13, 08:00, event heat 0
  6. 9/13, 11:00, event heat 0
  7. 9/13, 14:00, event heat 0

Reporting Timeline

  1. AggregatorHuggingFace Daily Papers9/10, 04:00 AMnot independentRepresentative
    Generative Late-Interaction Embeddings for Visual Document Retrieval