4 papers
Dynamics-Informed Action Learning for Goal-Conditioned Latent Planning
Yinuo Jiang, Guangzhi Wang, Yiran Wang +4
Latent world models enable visual control by planning action sequences in compact representation spaces, but a gap remains between how latent dynamics are learned and how they are…
TaskFrame: Connecting Task-Level Planning with Frame-Level Control for Game Agents
Guangzhi Wang, Junfu Pu, Yiran Wang +10
Building general game agents requires both high-level task reasoning and low-latency action control in rapidly changing visual environments. These capabilities favor models with su…
Learnable Hodge-Laplacian Driven Mixture of Experts for Steady-PDE Surrogates on Coarse Unstructured Meshes
Stavros Nousias, Akis Nousias, Konstantinos Gkrispanis
Surrogate models approximate the solutions of partial differential equations (PDEs) for given geometries and boundary conditions. Conventional Transformer-based approaches typicall…
GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay
Yiran Wang, Xingyilang Yin, Junfu Pu +12
Modern video games provide a measurable testbed for AI models, combining abilities of visual understanding, instruction decomposition, goal planning, and precise action control ove…