WorldMark: A Unified Benchmark Suite for Interactive Video World Models

About this episode

The episode discusses WorldMark, a benchmark suite designed for fair evaluation of interactive video generation models.

🤗 Upvotes: 30 | cs.CV Authors: Xiaojie Xu, Zhengyuan Lin, Kang He, Yukang Feng, Xiaofeng Mao, Yuanyang Yin, Kaipeng Zhang, Yongtao Ge Title: WorldMark: A Unified Benchmark Suite for Interactive Video World Models Arxiv: http://arxiv.org/abs/2604.21686v1 Abstract: Interactive video generation models such as Genie, YUME, HY-World, and Matrix-Game are advancing rapidly, yet every model is evaluated on its own benchmark with private scenes and trajectories, making fair cross-model comparison impossible. Existing public benchmarks offer useful metrics such as trajectory error, aesthetic scores, and VLM-based judgments, but none supplies the standardized test conditions -- identical scenes, identical action sequences, and a unified control interface -- needed to make those metrics comparable across models with heterogeneous inputs. We introduce WorldMark, the first benchmark that provides such a common playing field for interactive Image-to-Video world models. WorldMark contributes: (1) a unified action-mapping layer that translates a shared WASD-style action vocabulary into each model's native control format, enabling apples-to-apples comparison across six major models on identical…

People in this episode

Hosts: Jingwen Liang, Gengyu Wang

Topics covered

• interactive video generation
• benchmarking
• model comparison
• video world models
• evaluation metrics

Keywords

• WorldMark
• benchmark suite
• interactive video
• model evaluation
• video generation

Mentioned in this episode

Organizations: Genie, YUME, HY-World, Matrix-Game

Books & works: WorldMark: A Unified Benchmark Suite for Interactive Video World Models

More episodes of Daily Paper Cast

• EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments · June 13, 2026 · 24 min
• MiniMax Sparse Attention · June 13, 2026 · 26 min
• SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning · June 13, 2026 · 23 min
• InterleaveThinker: Reinforcing Agentic Interleaved Generation · June 13, 2026 · 21 min
• FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents · June 13, 2026 · 23 min
• Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? · June 13, 2026 · 20 min