2 citations · 7 across the 32 of their papers we have counts for
11 papers · 1 filter
PAWBench: How Far Are We from Probabilistically Aligned World Modeling?
Yuandong Pu, Le Zhuo, Sayak Paul +11
Recent video generation models are increasingly framed as world models. Many physical processes can unfold in more than one valid way. Therefore, a world model should reproduce not…
WorldRover: A Scalable Synthetic Video Data Engine for World Exploration with Rich Annotations
Xiaojie Xu, Zhengyuan Lin, Runyi Li +3
Learning to generate or reconstruct explorable worlds requires video paired with more than RGB: camera motion, scene geometry, temporal correspondence and, for interactive models,…
Towards Physics-Faithful Generation of Scientific Diagrams
Minghui Zhang, Jinxin Shi, Yifan Chang +12
Text-to-image generation has reached photorealistic quality, yet state-of-the-art systems remain unreliable at producing scientific diagrams, whose value depends not on appearance…
See2Think: Do Multimodal Models Really Use Intermediate Visual States?
Siyu Yan, Zhuoran Yan, Haiying Xu +10
Multimodal large language models increasingly use sketches, annotations, tools, and intermediate images during reasoning, but it remains unclear whether they truly rely on these vi…
Are Text-to-Image Models Inductivist Turkeys? A Counterfactual Benchmark for Causal Reasoning
Jiayi Lei, Yuandong Pu, Xingyu Han +8
Text-to-image (T2I) generation models have achieved remarkable progress in producing visually realistic images from natural language prompts. Yet it remains unclear whether their s…
Faithful, Enriched, and Precise: Benchmarking Natural-Science Illustration Generation by T2I models
Yifan Chang, Jiaxin Ai, Jianwen Sun +9
Scientific illustrations are essential tools for communicating research findings, especially in natural science, where they visualize complex concepts and processes. As Text-to-Ima…