AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

ViewFusion: Structured Spatial Thinking Chains for Multi-View Reasoning

Xingjian Tao, Yiwei Wang, Yujun Cai, Yifan Song, Jing Tang

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Spatial reasoning in VLMs · 2 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
train ViewFusion (SFT+RL) on Qwen3-VL-4B-InstructQwen3-VL-4B-Instruct · MMSI-Benchaccuracy (%): 30.1 -> 35.4Improved
train ViewFusion on Qwen3-VL-4B-InstructQwen3-VL-4B-Instruct · MindCubeaccuracy (%): 37.0 -> 77.0Improved
train ViewFusion on Qwen3-VL-4B-InstructQwen3-VL-4B-Instruct · ViewSpatial-Benchaccuracy (%): 42.5 -> 45.4Improved
use ViewFusion instead of a thinking-mode modelQwen3-VL-4B-Thinking · MMSI-Benchaccuracy (%): 29.0 -> 35.4Improved
use structured two-stage output instead of free-form reasoning under RL (ablation)ViewFusion · MMSI-Benchaccuracy (%): 33.4 -> 35.4Improved
add GRPO after SFT (ablation)ViewFusion · MMSI-Benchaccuracy (%): 32.4 -> 35.4Improved
add format reward (ablation)ViewFusion · MMSI-Benchaccuracy (%): 35.0 -> 35.4No clear effect
add GRPO after SFT (ablation)ViewFusion · MindCubeaccuracy (%): 68.5 -> 77.0Improved
add GRPO after SFT (ablation)ViewFusion · ViewSpatial-Benchaccuracy (%): 45.1 -> 45.4No clear effect
use ViewFusionQwen3-VL-4B-Instruct · MMSI-Bench Obj.-Reg.accuracy (%): 29.4 -> 21.2Hurt
use ViewFusionQwen3-VL-4B-Instruct · MMSI-Bench Cam.-Cam.accuracy (%): 30.1 -> 46.2Improved

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