Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

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

External links

GitHubCloudborne ↗

© 2026 Pier.

WatchingResearchWatching0 independent reports0

3DZip: Spatial-Aware Feature Diversity-Guided Token Compression for 3D Question Answering

First seen · 8/2/2026, 04:00 AMLatest activity · 8/2/2026, 04:00 AM

3DZip addresses the thousands of geometry-aware tokens produced by 3D vision-language models. Its three-stage pipeline performs coarse voxelization, selects feature-diverse anchor tokens with a Determinantal Point Process, and merges remaining tokens under spatial constraints. The authors report consistent improvements over existing compression methods on three 3D question-answering benchmarks, while retaining 94.7% of the original performance. The provided abstract does not specify the benchmark names, compression ratios, latency, memory savings, or detailed ablation results.

Event heat · last 24 hours

No heat snapshots are available in the last 24 hours.

No heat snapshots are available in the last 24 hours.

Reporting Timeline

  1. AggregatorHuggingFace Daily Papers8/2, 04:00 AMnot independentRepresentative
    3DZip: Spatial-Aware Feature Diversity-Guided Token Compression for 3D Question Answering