13 papers
HarnessEval-W: Agentifying the Evaluation of Visual Worlds
Weiliang Chen, Haowen Sun, Jun Gao +40
A benchmark should deliver more than a scalar score: what makes an evaluation trustworthy is the reasoning that justifies the score. This is especially critical for world models, w…
VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning
Junxiang Xu, Ruisi Wang, Fanyi Pu +49
Native visual reasoning treats visual generation as the medium of reasoning itself: visual states (i.e. images and videos) are not merely inputs to be understood or outputs to be r…
Apple-: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence
Runmao Yao, Kairui Hu, Yukang Cao +11
Modern video generation models are increasingly hailed as emerging world models with an internalized grasp of physical law. Yet existing benchmarks largely evaluate physical plausi…
Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond
Meng Chu, Xuan Billy Zhang, Kevin Qinghong Lin +47
As AI systems move from generating text to accomplishing goals through sustained interaction, the ability to model environment dynamics becomes a central bottleneck. Agents that ma…
Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulation
Mutian Xu, Tianbao Zhang, Tianqi Liu +3
Simulating robot-world interactions is a cornerstone of Embodied AI. Recently, a few works have shown promise in leveraging video generations to transcend the rigid visual/physical…
Demystifying Video Reasoning
Ruisi Wang, Zhongang Cai, Fanyi Pu +11
Recent advances in video generation have revealed an unexpected phenomenon: diffusion-based video models exhibit non-trivial reasoning capabilities. Prior work attributes this to a…
WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World
Ao Liang, Lingdong Kong, Tianyi Yan +19
Generative world models are reshaping embodied AI, enabling agents to synthesize realistic 4D driving environments that look convincing but often fail physically or behaviorally. D…
RealDPO: Real or Not Real, that is the Preference
Guo Cheng, Danni Yang, Ziqi Huang +3
Video generative models have recently achieved notable advancements in synthesis quality. However, generating complex motions remains a critical challenge, as existing models often…
Simulating the Visual World with Artificial Intelligence: A Roadmap
Jingtong Yue, Ziqi Huang, Zhaoxi Chen +3
The landscape of video generation is shifting, from a focus on generating visually appealing clips to building virtual environments that support interaction and maintain physical p…
VChain: Chain-of-Visual-Thought for Reasoning in Video Generation
Ziqi Huang, Ning Yu, Gordon Chen +3
Recent video generation models can produce smooth and visually appealing clips, but they often struggle to synthesize complex dynamics with a coherent chain of consequences. Accura…
Stencil: Subject-Driven Generation with Context Guidance
Gordon Chen, Ziqi Huang, Cheston Tan +1
Recent text-to-image diffusion models can generate striking visuals from text prompts, but they often fail to maintain subject consistency across generations and contexts. One majo…
CineScale: Tuning-Free High-Resolution Video Generation
Haonan Qiu, Gordon Chen, Ning Yu +3
Video diffusion models have achieved remarkable progress in recent years, yet generating high-resolution videos remain a fundamental challenge. Most video generators are trained at…
Cut2Next: Generating Next Shot via In-Context Tuning
Jingwen He, Hongbo Liu, Jiajun Li +4
Effective multi-shot generation demands purposeful, film-like transitions and strict cinematic continuity. Current methods, however, often prioritize basic visual consistency, negl…