AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Qwen-3D: A Generalist 3D Vision-Language Model for Spatial Understanding

Lucy Lin, Ayush Jain, Yifan Liu, Katerina Fragkiadaki

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Spatial reasoning in VLMs · 3 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
feed full text and visual tokens to mask decoder instead of a <REF> token (ablation)Qwen-3D · ScanRefer Acc@50 (3B ablation)Top-1 Acc: 39.7 -> 53.5Improved
use full attention mask instead of causal mask (ablation)Qwen-3D · ScanRefer Acc@50 (3B ablation)Top-1 Acc: 36.4 -> 53.5Improved
fine-tune the VLM backbone instead of freezing (ablation)Qwen-3D · ScanRefer Acc@50 (3B ablation)Top-1 Acc: 37.0 -> 53.5Improved
use aligned 3D RoPE instead of naive 3D MRoPE (ablation)Qwen-3D · ScanRefer Acc@50 (3B ablation)Top-1 Acc: 49.9 -> 53.5Improved
use aligned 3D RoPE instead of 2D RoPE (ablation)Qwen-3D · ScanRefer Acc@50 (3B ablation)Top-1 Acc: 53.2 -> 53.5No clear effect
joint 2D-3D training retains 2D capabilityQwen-3D 3B · RefCOCO / RealWorldQAaccuracy: RefCOCO 89.1 -> 88.1; RefCOCO+ 82.4 -> 82.7; RealWorldQA 62.6 -> 60.4Mixed
use Qwen-3D mask decoder instead of Grounded-3D-LLMQwen-3D 3B · ScanNet200 instance segmentationmAP: 12.1 -> 25.3Improved
Qwen-3D vs specialist UniVLG out-of-domainQwen-3D 3B · Locate3D ScanNet++Acc@25: 32.3 -> 55.7Improved
Qwen-3D vs UniVLG on outdoor vehicle splitQwen-3D 3B · 3EED VehicleA@0.25: 28.6 -> 22.9Hurt
use voxel pooling instead of token merging (ablation)Qwen-3D · ScanNet dense scenesmemoryImproved
Qwen-3D 3B vs 7BQwen-3D · ScanRefer Acc@25accuracy: 62.2 -> 62.8No clear effect

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