AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Unfold The World: Factorize 4D Properties in Reinforcing Spatial Understanding

Yijun Yang, Shenghe Zheng, Wenbo Li, Jianhui Liu, Haoze Sun, Yanbing Zhang, Jiaxiu Jiang, Lin Song, Haoyang Huang, Nan Duan, Lei Zhu

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Spatial reasoning in VLMs

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 T (temporal cycle consistency) reward (ablation)FactoSR-SFT + GRPO · Camera motion group (Delta_t)accuracy: 45.7 -> 53.6 (+7.9)Improved
add XY (reprojection correspondence) reward (ablation)FactoSR-SFT + GRPO · Correspondence group (Delta_Cor)accuracy: +2.7 (72.6 vs 69.9 SFT)Improved
add Z (depth order) reward (ablation)FactoSR-SFT + GRPO · Depth group (Delta_Depth)accuracy: 86.3 -> 87.6 (+1.3)Improved
RL with vanilla GRPO accuracy reward only (ablation)FactoSR-SFT · 3D/4D average (9 spatial benchmarks)average accuracy: 60.3 -> 60.5 (+0.2)No clear effect
combine XY, Z and T rewards (ablation)FactoSR-SFT + GRPO · 3D/4D average (9 spatial benchmarks)average accuracy: 60.3 -> 62.0 (+1.7)Improved
add vanilla grounding (IoU) reward (ablation)FactoSR-SFT + GRPO · 3D/4D average (9 spatial benchmarks)average accuracy: -0.2 overall, -0.7 Spatial_RelationHurt
use Z reward instead of vanilla grounding reward (ablation)FactoSR-SFT + GRPO · BLINK Relative_Depthaccuracy: +3.2 (vs +0.8 for grounding)Improved
add Z reward (ablation)FactoSR-SFT + GRPO · Correspondence group (Delta_Cor)accuracy: -0.1 (69.8 vs 69.9)No clear effect
combine all rewards vs T reward alone on temporal group (ablation)FactoSR-SFT + GRPO · Camera motion group (Delta_t)accuracy: 53.6 -> 50.9Mixed
add factorized RL stage after SFTFactoSR-8B · VSI-Benchaverage accuracy: 58.5 -> 61.5Improved
add factorized RL stage after SFTFactoSR-8B · All-Angles-Benchaverage accuracy: 51.6 -> 55.4Improved
FactoSR training vs base modelQwen3-VL-8B-Instruct · OCRBenchaccuracy: -2.7Hurt

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