AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

From Views to Worlds: Active Exploration over 3D Worlds for Vision-Language Models

Qijian Tian, Jiayu Ying, Ke Fan, Lizhuang Ma, Xin Tan

NeurIPS 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 summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes active exploration over 3D worlds so vision-language models can acquire spatial evidence beyond currently visible views for 3D spatial reasoning.

Problem

Passive view-centric perception limits VLMs' 3D spatial reasoning, which often requires actively acquiring evidence beyond visible views (camera poses, cross-view relations).

Approach

Shifts VLMs from passive view-centric perception to active exploration over 3D worlds, letting the model acquire additional spatial evidence such as camera poses and cross-view relationships to infer 3D relations not explicit in the input views.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add visual and linguistic world interfaces with active exploration (training-free)Qwen3-VL-8B · MindCube-Tinyoverall accuracy: 30.6 -> 50.2Improved
use V2W active exploration instead of chain-of-thought promptingQwen3-VL-235B · MindCube-Tinyoverall accuracy: 45.4 -> 59.6Improved
add chain-of-thought promptingQwen2.5-VL-7B · MindCube-Tinyoverall accuracy: 34.5 -> 29.1Hurt
add both interfaces in training-free V2W (ablation)Qwen2.5-VL-7B · MindCube-Tiny RotationRotation accuracy: 35.0 -> 35.0No clear effect
add the linguistic interface to the visual interface (ablation)V2W training-free · MindCube-Tinyoverall accuracy: 38.5 -> 43.8Improved
add the full world interface after SFT-then-RL (ablation)V2W · MindCube-Tinyoverall accuracy: 74.8 -> 90.8Improved
use RL instead of SFT for exploration policy (ablation)V2W with full interface · MindCube-Tinyoverall accuracy: 71.3 -> 83.9Improved
add RL after SFT (ablation)V2W with full interface · MindCube-Tinyoverall accuracy: 71.3 -> 90.8Improved
add step-wise reward in RL (ablation)V2W SFT-then-RL · MindCube-Tinyoverall accuracy: 89.0 -> 90.8Improved
swap Depth Anything 3 for VGGT in the 3D world construction (ablation)V2W training-free · MindCube-Tinyoverall accuracy: 43.8 -> 42.6 (Qwen2.5-VL-7B); 50.2 -> 50.0 (Qwen3-VL-8B)No clear effect
use V2W with larger Qwen3-VL series vs Qwen2.5-VL-7BV2W training-free · MindCube-Tinyoverall accuracy gain: +9.3 (Qwen2.5-VL-7B) vs +19.6 (Qwen3-VL-8B)Improved
add V2W to GPT-4.1-mini over pySpatialGPT-4.1-mini · MindCube-Tinyoverall accuracy: 58.2 -> 61.7Improved

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