Zero-shot World Models Are Developmentally Efficient Learners.

Klemen Kotar

Khai Loong Aw Klemen Kotar Wanhee Lee Seungwoo Kim Khaled Jedoui Rahul Mysore Venkatesh Lilian Naing Chen Michael C. Frank Daniel L. K. Yamins Zero-shot World Models Are Developmentally Efficient Learners. 2026 April abs/2604.10333 CoRR https://doi.org/10.48550/arXiv.2604.10333 db/journals/corr/corr2604.html#abs-2604-10333 streams/journals/corr

Wanhee Lee Klemen Kotar Rahul Mysore Venkatesh Jared Watrous Honglin Chen Khai Loong Aw Daniel L. K. Yamins Unified 3D Scene Understanding Through Physical World Modeling. 2026 May abs/2605.24321 CoRR https://doi.org/10.48550/arXiv.2605.24321 db/journals/corr/corr2605.html#abs-2605-24321 streams/journals/corr

Rahul Mysore Venkatesh Klemen Kotar Lilian Naing Chen Wanhee Lee Gia Ancone Seungwoo Kim Luca Thomas Wheeler Jared Watrous Honglin Chen Daniel Bear Stefan Stojanov Daniel L. K. Yamins Physical Object Understanding with a Physically Controllable World Model. 2026 June abs/2606.00439 CoRR https://doi.org/10.48550/arXiv.2606.00439 db/journals/corr/corr2606.html#abs-2606-00439 streams/journals/corr

Wanhee Lee Klemen Kotar Rahul Mysore Venkatesh Jared Watrous Daniel L. K. Yamins Perceptual 3D Simulation With Physical World Modeling. 2026 June abs/2606.27575 CoRR https://doi.org/10.48550/arXiv.2606.27575 db/journals/corr/corr2606.html#abs-2606-27575 streams/journals/corr

Greta Tuckute Klemen Kotar Evelina Fedorenko Daniel Yamins Representing Speech Through Autoregressive Prediction of Cochlear Tokens. 2025 INTERSPEECH https://doi.org/10.21437/Interspeech.2025-2044 conf/interspeech/2025 db/conf/interspeech/interspeech2025.html#TuckuteKFY25 Seungwoo Kim Khai Loong Aw Klemen Kotar Cristóbal Eyzaguirre Wanhee Lee Yunong Liu Jared Watrous Stefan Stojanov Juan Carlos Niebles Jiajun Wu 0001 Daniel L. K. Yamins Taming generative video models for zero-shot optical flow extraction. 2025 NeurIPS http://papers.nips.cc/paper_files/paper/2025/hash/bcc97a47e54a9bec240cf5e5aadfd8fb-Abstract-Conference.html conf/nips/2025 db/conf/nips/neurips2025.html#KimAKELLWSNWY25

Wanhee Lee Klemen Kotar Rahul Mysore Venkatesh Jared Watrous Honglin Chen Khai Loong Aw Daniel L. K. Yamins 3D Scene Understanding Through Local Random Access Sequence Modeling. 2025 April abs/2504.03875 CoRR https://doi.org/10.48550/arXiv.2504.03875 db/journals/corr/corr2504.html#abs-2504-03875 streams/journals/corr

Klemen Kotar Greta Tuckute Model Connectomes: A Generational Approach to Data-Efficient Language Models. 2025 April abs/2504.21047 CoRR https://doi.org/10.48550/arXiv.2504.21047 db/journals/corr/corr2504.html#abs-2504-21047 streams/journals/corr

Seungwoo Kim Khai Loong Aw Klemen Kotar Cristóbal Eyzaguirre Wanhee Lee Yunong Liu Jared Watrous Stefan Stojanov Juan Carlos Niebles Jiajun Wu 0001 Daniel L. K. Yamins Taming generative video models for zero-shot optical flow extraction. 2025 July abs/2507.09082 CoRR https://doi.org/10.48550/arXiv.2507.09082 db/journals/corr/corr2507.html#abs-2507-09082 streams/journals/corr

Rahul Mysore Venkatesh Klemen Kotar Lilian Naing Chen Seungwoo Kim Luca Thomas Wheeler Jared Watrous Ashley Xu Gia Ancone Wanhee Lee Honglin Chen Daniel Bear Stefan Stojanov Daniel Yamins Discovering and using Spelke segments. 2025 July abs/2507.16038 CoRR https://doi.org/10.48550/arXiv.2507.16038 db/journals/corr/corr2507.html#abs-2507-16038 streams/journals/corr

Greta Tuckute Klemen Kotar Evelina Fedorenko Daniel L. K. Yamins Representing Speech Through Autoregressive Prediction of Cochlear Tokens. 2025 August abs/2508.11598 CoRR https://doi.org/10.48550/arXiv.2508.11598 db/journals/corr/corr2508.html#abs-2508-11598 streams/journals/corr

Klemen Kotar Wanhee Lee Rahul Mysore Venkatesh Honglin Chen Daniel Bear Jared Watrous Simon Kim Khai Loong Aw Lilian Naing Chen Stefan Stojanov Kevin T. Feigelis Imran Thobani Alex Durango Khaled Jedoui Atlas Kazemian Dan Yamins World Modeling with Probabilistic Structure Integration. 2025 September abs/2509.09737 CoRR https://doi.org/10.48550/arXiv.2509.09737 db/journals/corr/corr2509.html#abs-2509-09737 streams/journals/corr

Rahul Mysore Venkatesh Honglin Chen Kevin T. Feigelis Daniel M. Bear Khaled Jedoui Klemen Kotar Felix J. Binder Wanhee Lee Sherry Liu Kevin A. Smith 0001 Judith E. Fan Daniel L. K. Yamins Understanding Physical Dynamics with Counterfactual World Modeling. 368-387 2024 ECCV (24) https://doi.org/10.1007/978-3-031-72691-0_21 conf/eccv/2024-24 db/conf/eccv/eccv2024-24.html#VenkateshCFBJKBLLSFY24 streams/conf/eccv Klemen Kotar Aaron Walsman Roozbeh Mottaghi ENTL: Embodied Navigation Trajectory Learner. 10829-10838 2023 ICCV https://doi.org/10.1109/ICCV51070.2023.00997 conf/iccv/2023 db/conf/iccv/iccv2023.html#KotarWM23 Klemen Kotar Stephen Tian Hong-Xing Yu Dan Yamins Jiajun Wu 0001 Are These the Same Apple? Comparing Images Based on Object Intrinsics. 2023 NeurIPS http://papers.nips.cc/paper_files/paper/2023/hash/803c6ab3d62346e004ef70211d2d15b8-Abstract-Datasets_and_Benchmarks.html conf/nips/2023 db/conf/nips/neurips2023.html#KotarTYY023

Klemen Kotar Aaron Walsman Roozbeh Mottaghi ENTL: Embodied Navigation Trajectory Learner. 2023 abs/2304.02639 CoRR https://doi.org/10.48550/arXiv.2304.02639 db/journals/corr/corr2304.html#abs-2304-02639

Daniel M. Bear Kevin T. Feigelis Honglin Chen Wanhee Lee Rahul Mysore Venkatesh Klemen Kotar Alex Durango Daniel L. K. Yamins Unifying (Machine) Vision via Counterfactual World Modeling. 2023 abs/2306.01828 CoRR https://doi.org/10.48550/arXiv.2306.01828 db/journals/corr/corr2306.html#abs-2306-01828

Klemen Kotar Stephen Tian Hong-Xing Yu Daniel L. K. Yamins Jiajun Wu 0001 Are These the Same Apple? Comparing Images Based on Object Intrinsics. 2023 abs/2311.00750 CoRR https://doi.org/10.48550/arXiv.2311.00750 db/journals/corr/corr2311.html#abs-2311-00750

Lukas Wolf Greta Tuckute Klemen Kotar Eghbal Hosseini Tamar Regev Ethan Wilcox Alex Warstadt WhisBERT: Multimodal Text-Audio Language Modeling on 100M Words. 2023 abs/2312.02931 CoRR https://doi.org/10.48550/arXiv.2312.02931 db/journals/corr/corr2312.html#abs-2312-02931

Rahul Mysore Venkatesh Honglin Chen Kevin T. Feigelis Daniel M. Bear Khaled Jedoui Klemen Kotar Felix J. Binder Wanhee Lee Sherry Liu Kevin A. Smith 0001 Judith E. Fan Daniel L. K. Yamins Counterfactual World Modeling for Physical Dynamics Understanding. 2023 abs/2312.06721 CoRR https://doi.org/10.48550/arXiv.2312.06721 db/journals/corr/corr2312.html#abs-2312-06721

Klemen Kotar Roozbeh Mottaghi Interactron: Embodied Adaptive Object Detection. 14840-14849 2022 CVPR https://doi.org/10.1109/CVPR52688.2022.01444 conf/cvpr/2022 db/conf/cvpr/cvpr2022.html#KotarM22 Aaron Walsman Muru Zhang Klemen Kotar Karthik Desingh Ali Farhadi Dieter Fox Break and Make: Interactive Structural Understanding Using LEGO Bricks. 90-107 2022 ECCV (28) https://doi.org/10.1007/978-3-031-19815-1_6 conf/eccv/2022-28 db/conf/eccv/eccv2022-28.html#WalsmanZKDFF22

Klemen Kotar Roozbeh Mottaghi Interactron: Embodied Adaptive Object Detection. 2022 abs/2202.00660 CoRR https://arxiv.org/abs/2202.00660 db/journals/corr/corr2202.html#abs-2202-00660

Aaron Walsman Muru Zhang Klemen Kotar Karthik Desingh Ali Farhadi Dieter Fox Break and Make: Interactive Structural Understanding Using LEGO Bricks. 2022 abs/2207.13738 CoRR https://doi.org/10.48550/arXiv.2207.13738 db/journals/corr/corr2207.html#abs-2207-13738

Klemen Kotar Gabriel Ilharco Ludwig Schmidt Kiana Ehsani Roozbeh Mottaghi Contrasting Contrastive Self-Supervised Representation Learning Pipelines. 9929-9939 2021 ICCV https://doi.org/10.1109/ICCV48922.2021.00980 conf/iccv/2021 db/conf/iccv/iccv2021.html#KotarISEM21

Klemen Kotar Gabriel Ilharco Ludwig Schmidt Kiana Ehsani Roozbeh Mottaghi Contrasting Contrastive Self-Supervised Representation Learning Models. 2021 abs/2103.14005 CoRR https://arxiv.org/abs/2103.14005 db/journals/corr/corr2103.html#abs-2103-14005

Luca Weihs Jordi Salvador Klemen Kotar Unnat Jain Kuo-Hao Zeng Roozbeh Mottaghi Aniruddha Kembhavi AllenAct: A Framework for Embodied AI Research. 2020 abs/2008.12760 CoRR https://arxiv.org/abs/2008.12760 db/journals/corr/corr2008.html#abs-2008-12760

Gia Ancone Khai Loong Aw Daniel BearDaniel M. Bear Felix J. Binder Honglin Chen Lilian Naing Chen Karthik Desingh Alex Durango Kiana Ehsani Cristóbal Eyzaguirre Judith E. Fan Ali Farhadi Evelina Fedorenko Kevin T. Feigelis Dieter Fox Michael C. Frank Eghbal Hosseini Gabriel Ilharco Unnat Jain Khaled Jedoui Atlas Kazemian Aniruddha Kembhavi Seungwoo Kim Simon Kim Wanhee Lee Sherry Liu Yunong Liu Roozbeh Mottaghi Juan Carlos Niebles Tamar I. RegevTamar Regev Jordi Salvador Ludwig Schmidt Kevin A. Smith 0001 Stefan Stojanov Imran Thobani Stephen Tian Greta Tuckute Rahul M. V.Rahul Mysore Venkatesh Aaron Walsman Alex Warstadt Jared Watrous Luca Weihs Luca Thomas Wheeler Ethan Wilcox Lukas Wolf Jiajun Wu 0001 Ashley Xu Dan YaminsDaniel YaminsDaniel L. K. Yamins Hong-Xing Yu Kuo-Hao Zeng Muru Zhang