AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Zero-Shot 3D Question Answering via Hierarchical View-to-Token Transportation

Dongsheng Wang, Dawei Su, Hui Huang

ICML 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Adapting VLMs for zero-shot classification · 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
add geometry-aware design to key-view selection (ablation)KeyVT · ScanQA valCIDEr: 93.8 -> 100.7Improved
add sub-scene partition (ablation)KeyVT · ScanQA valCIDEr: 99.8 -> 100.7Improved
add relevance scoring (ablation)KeyVT · ScanQA valCIDEr: 99.4 -> 100.7Improved
replace AKS with KeyV for view selection (16 frames) (ablation)Qwen2.5-VL-7B · VSI-Bench / ScanQA / SQA3DAcc / CIDEr / EM@1: 36.4 -> 37.7 (VSI), 67.3 -> 70.2 (CIDEr)Improved
add KeyT token compression (16 -> 8 equivalent frames) on top of KeyV (ablation)LLaVA-Video-7B · VSI-Benchaverage accuracy: 33.2 -> 34.6Improved
add KeyT to uniform sampling (ablation)Uniform sampling · ScanQA valCIDEr: 93.4 -> 94.0Improved
add KeyT to AKS (ablation)AKS · ScanQA valCIDEr: 99.0 -> 99.8Improved
inject 10% noise into camera parameters (ablation)KeyVT · ScanQA valCIDEr: 100.7 -> 98.4Hurt
inject 1-5% noise into camera parameters (ablation)KeyVT · ScanQA valCIDEr: 100.7 -> 100.0 (5% noise)No clear effect
use VGGT-estimated cameras instead of true cameras (ablation)KeyVT · ScanQA valCIDEr: 100.7 -> 100.0No clear effect
compress key-view tokens with KeyT instead of DivPrune/FLoC at 50% retain (ablation)Qwen2.5-VL-7B · ScanQA valCIDEr: 67.3 / 68.5 -> 69.6Improved
compress tokens to 50% with KeyT versus full 16 frames (ablation)Qwen2.5-VL-7B · ScanQA valCIDEr: 70.2 -> 69.6Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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