Alexander Pondaven

selected publications

1. ECCV

   ActionParty: Multi-Subject Action Binding in Generative Video Games

   Pondaven, Alexander, Wu, Ziyi, Gilitschenski, Igor, Torr, Philip, Tulyakov, Sergey, Pizzati, Fabio, and Siarohin, Aliaksandr

   In ECCV 2026

   Abs arXiv Bib Website

   Recent advances in video diffusion have enabled world models that simulate interactive environments, but these are largely restricted to single-agent settings. We tackle action binding — associating specific actions with their corresponding subjects — and propose ActionParty, an action-controllable multi-subject world model for generative video games. It introduces subject state tokens that persistently capture each subject’s state, and a spatial biasing mechanism that disentangles global frame rendering from individual action-controlled subject updates. On the Melting Pot benchmark, ActionParty is the first video world model to control up to seven players simultaneously across 46 environments.

   @inproceedings{pondaven2026actionparty,
     title = {ActionParty: Multi-Subject Action Binding in Generative Video Games},
     author = {Pondaven, Alexander and Wu, Ziyi and Gilitschenski, Igor and Torr, Philip and Tulyakov, Sergey and Pizzati, Fabio and Siarohin, Aliaksandr},
     booktitle = {ECCV},
     year = {2026},
   }

   
2. CVPR

   Video Motion Transfer with Diffusion Transformers

   Pondaven, Alexander, Siarohin, Aliaksandr, Tulyakov, Sergey, Torr, Philip, and Pizzati, Fabio

   2025

   arXiv Bib Code Website

   @article{pondaven2025ditflow,
     title = {Video Motion Transfer with Diffusion Transformers},
     author = {Pondaven, Alexander and Siarohin, Aliaksandr and Tulyakov, Sergey and Torr, Philip and Pizzati, Fabio},
     booktitle = {CVPR},
     year = {2025},
   }

   
3. NeurIPS-W

   Convolutional Neural Processes for Inpainting Satellite Images: Application to Water Body Segmentation

   Pondaven, Alexander, Bakler, Märt, Guo, Donghu, Hashim, Hamzah, Ignatov, Martin G, Bhatt, Samir, Flaxman, Seth, Mishra, Swapnil, Alhajjar, Elie, and Zhu, Harrison

   In NeurIPS 2022 Workshop on Tackling Climate Change with Machine Learning 2022

   arXiv Bib HTML Slides

   @inproceedings{pondaven2022convolutional,
     title = {Convolutional Neural Processes for Inpainting Satellite Images: Application to Water Body Segmentation},
     author = {Pondaven, Alexander and Bakler, Märt and Guo, Donghu and Hashim, Hamzah and Ignatov, Martin G and Bhatt, Samir and Flaxman, Seth and Mishra, Swapnil and Alhajjar, Elie and Zhu, Harrison},
     booktitle = {NeurIPS 2022 Workshop on Tackling Climate Change with Machine Learning},
     url = {https://www.climatechange.ai/papers/neurips2022/24},
     year = {2022},
   }