AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

What if? Emulative Simulation with World Models for Situated Reasoning

Ruiping Liu, Yufan Chen, Yuheng Zhang, Junwei Zheng, Kunyu Peng, Chengzhi Wu, Chenguang Huang, Di Wen, Jiaming Zhang, Kailun Yang, Rainer Stiefelhagen

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Spatial reasoning in VLMs · 1 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
fine-tune Wan2.1 on WanderDream (LoRA) instead of prompt-extended Wan2.2world model · Real-world test setFVD: 41.65 -> 27.49Improved
fine-tune Wan2.1 on WanderDream instead of prompt-extended Wan2.2sequential framework · Real-world test setQA accuracy: 38.8 -> 43.0Improved
add MindJourney step-wise imaginationMLLM reasoning · Real-world test setQA accuracy: 38.5 -> 31.9Hurt
fine-tune (LoRA) Wan2.2 instead of prompt extension (ablation)Wan2.2 · WanderDream-Gen (HM3D val)FVD: 17.62 -> 6.19Improved
fine-tune (LoRA) Wan2.2 instead of prompt extension (ablation)Wan2.2 · WanderDream-Gen (ScanNet++ val)FVD: 18.73 -> 9.67Improved
add imagined video frames to start-state reasoning (ablation)Qwen3-VL · WanderDream-QA ScanNet++ start-statecorrectness (%): 32.5 -> 29.7Hurt
add imagined video (CogVideoX1.5 SFT) to end-state reasoning (ablation)Qwen3-VL · WanderDream-QA ScanNet++ end-statecorrectness (%): 45.5 -> 47.5Improved
add imagined video (CogVideoX1.5 SFT) to end-state reasoning (ablation)Qwen3-VL · WanderDream-QA HM3D end-statecorrectness (%): 41.8 -> 44.0Improved
add imagined video (Wan2.1 LoRA) to path reasoning (ablation)Qwen3-VL · WanderDream-QA HM3D pathcorrectness (%): 53.2 -> 53.4No clear effect
add ground-truth intermediate frames to end-state ESR reasoning (ablation)Qwen3-VL · HM3D per-class QAcorrectness (%): 26.0 -> 38.7Improved
add imagination in ScanNet++ path questions where anchor is visible (ablation)Qwen3-VL · ScanNet++ path questionscorrectness (%)No clear effect
use better video generation quality for imaginationsequential framework · WanderDream-QAcorrectness (%)Improved

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