AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

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

Changwoo Baek, Kyeongbo Kong

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Spatial reasoning in VLMs · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use feature-space distance instead of spatial distance in DPP anchor selection (ablation)3DZip · SQA3D test (64 tokens)EM: 50.1 -> 52.8Improved
use feature-space distance instead of spatial distance in DPP anchor selection (ablation)3DZip · SQA3D test (32 tokens)EM: 49.0 -> 51.1Improved
add coarse voxelization before anchor selection (ablation)3DZip · SQA3D test (64 tokens)EM: 51.8 -> 52.8Improved
increase voxel size from 0.2m to 0.3m (ablation)3DZip · SQA3D test (64 tokens)EM: 52.8 -> 52.1Hurt
add spatially-constrained token merging (ablation)3DZip · SQA3D test (64 tokens)EM: 52.5 -> 52.8Improved
add spatial constraint to token merging (ablation)3DZip · SQA3D test (64 tokens)EM: 52.3 -> 52.8Improved
use DPP instead of farthest point sampling for anchor selection (ablation)3DZip · SQA3D test (64 tokens)EM: 52.2 -> 52.8Improved
use DPP instead of MMDP for anchor selection (ablation)3DZip · SQA3D test (64 tokens)EM: 52.5 -> 52.8Improved
use cosine similarity instead of L1 distance in feature space (ablation)3DZip · SQA3D test (64 tokens)EM: 52.5 -> 52.8Improved
increase merging threshold tau_g from 1 to 5 (ablation)3DZip · SQA3D test (64 tokens)EM: 52.5 -> 52.8Improved
add DPP anchor selection on top of voxel-mean aggregation (ablation)Voxel-mean · SQA3D test (64 tokens)EM: 49.8 -> 52.5Improved
add DPP anchor selection on top of ConceptFusion aggregation (ablation)ConceptFusion · SQA3D test (64 tokens)EM: 50.3 -> 52.7Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy