AI Paper Atlas

Research map / Video / Video generation

GameVerse: A Minute-Scale Gameplay Dataset for Long-Horizon Interactive World Modeling

Kang He, Wenshuo Peng, Chuanhao Li, Zihui Gao, Xiaojie Xu, Zhengyuan Lin, Yuzhe Ding, Donghong Ji, Kaipeng Zhang, Yongtao Ge

NeurIPS 2026 · Video › Video generation · approach: World-model video generation · 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.

Introduces GameVerse, a minute-scale game video dataset designed to support long-horizon, camera-controllable, and semantically structured interactive world modeling.

Problem

Existing video datasets do not simultaneously support long-horizon dynamics, precise camera control, and structured semantic representations needed for interactive world models.

Approach

A large-scale game video dataset with minute-scale clips that pairs long-horizon gameplay with camera control and structured semantic annotations for training interactive world models.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
fine-tune HY-World 1.5 on about 600 hours of GameVerseHY-World 1.5 · VBench, 60s generationSubject Consistency: 66.92 -> 68.45Improved
fine-tune HY-World 1.5 on GameVerseHY-World 1.5 · VBench, 60s generationOverall Consistency: 14.48 -> 15.69Improved
fine-tune HY-World 1.5 on GameVerseHY-World 1.5 · WorldScore, 60s generationWS-Static: 53.33 -> 55.13Improved
fine-tune HY-World 1.5 on GameVerseHY-World 1.5 · WorldScore, 60s generation3D Consistency: 66.94 -> 73.42Improved
fine-tune HY-World 1.5 on GameVerseHY-World 1.5 · WorldScore, 60s generationCamera Control: 28.58 -> 28.90Improved
fine-tune HY-World 1.5 on GameVerseHY-World 1.5 · reference-frame similarityCLIP similarity at 30s: 0.609 -> 0.642Improved
fine-tune HY-World 1.5 on GameVerseHY-World 1.5 · Subject Consistency by activitySubject Consistency: improvements of 1.15, 1.85, 2.49, and 1.58 pointsImproved
fine-tune LTX-Video 2.3 on GameVerse with camera and caption conditioning (versus LingBot, different architecture)LTX-Video 2.3 · WorldScore, 60s generationCamera Control: 24.33 vs LingBot 31.69Hurt
GameVerse fine-tuned HY-World versus LingBot on perceptual qualityHY-World-FT · VBench, 60s generationImaging Quality: 49.34 vs LingBot 56.70Hurt
use Wan2.2 instead of LTX-Video 2.3 backbone (no fine-tuning) (ablation)original backbones · VBench, 5/10/15sAesthetic and Imaging Quality: average advantages of 1.87 and 11.64 pointsImproved

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