KK
Klemen Kotar
cs.CVcs.AIcs.LGcs.ROcs.CLcs.MAcs.SDeess.AS
On Valency
published · living versionsW_cvbxu6ya·v1 · currentpublished
FlowBench: Counterfactual Imagination Training for Spatial Intelligence
with Yifan Liu, Baihan Zhang, Khai Loong Aw, Daniel L. K. Yamins
1 version
Preprints & journals
19 papers in the corpus · 2020–2026Perceptual 3D Simulation With Physical World Modeling2606.27575v1 · Wanhee Lee, Klemen Kotar, Rahul Mysore Venkatesh et al.2026 · 0 citationsarXiv
Physical Object Understanding with a Physically Controllable World Model2606.00439v1 · Rahul Venkatesh, Klemen Kotar, Lilian Naing Chen et al.2026 · 0 citationsarXiv
Unified 3D Scene Understanding Through Physical World Modeling2605.24321v1 · Wanhee Lee, Klemen Kotar, Rahul Mysore Venkatesh et al.2026 · 0 citationsarXiv
Zero-shot World Models Are Developmentally Efficient Learners2604.10333v2 · Khai Loong Aw, Klemen Kotar, Wanhee Lee et al.2026 · 0 citationsarXiv
World Modeling with Probabilistic Structure Integration2509.09737v1 · Klemen Kotar, Wanhee Lee, Rahul Venkatesh et al.2025 · 0 citationsarXiv
Representing Speech Through Autoregressive Prediction of Cochlear Tokens2508.11598v1 · Greta Tuckute, Klemen Kotar, Evelina Fedorenko et al.2025 · 0 citationsarXiv
Discovering and using Spelke segments2507.16038v1 · Rahul Venkatesh, Klemen Kotar, Lilian Naing Chen et al.2025 · 0 citationsarXiv
Taming generative video models for zero-shot optical flow extraction2507.09082v2 · Seungwoo Kim, Khai Loong Aw, Klemen Kotar et al.2025 · 0 citationsarXiv
Model Connectomes: A Generational Approach to Data-Efficient Language Models2504.21047v1 · Klemen Kotar, Greta Tuckute2025 · 0 citationsarXiv
3D Scene Understanding Through Local Random Access Sequence Modeling2504.03875v1 · Wanhee Lee, Klemen Kotar, Rahul Mysore Venkatesh et al.2025 · 0 citationsarXiv
Understanding Physical Dynamics with Counterfactual World Modeling2312.06721v3 · Rahul Venkatesh, Honglin Chen, Kevin Feigelis et al.2023 · 2 citationsarXiv
WhisBERT: Multimodal Text-Audio Language Modeling on 100M Words2312.02931v2 · Lukas Wolf, Greta Tuckute, Klemen Kotar et al.2023 · 4 citationsarXiv
Are These the Same Apple? Comparing Images Based on Object Intrinsics2311.00750v1 · Klemen Kotar, Stephen Tian, Hong-Xing Yu et al.2023 · 3 citationsarXiv
Unifying (Machine) Vision via Counterfactual World Modeling2306.01828v1 · Daniel M. Bear, Kevin Feigelis, Honglin Chen et al.2023 · 8 citationsarXiv
ENTL: Embodied Navigation Trajectory Learner2304.02639v3 · Klemen Kotar, Aaron Walsman, Roozbeh Mottaghi2023 · 6 citationsarXiv
Break and Make: Interactive Structural Understanding Using LEGO Bricks2207.13738v1 · Aaron Walsman, Muru Zhang, Klemen Kotar et al.2022 · 17 citationsarXiv
Interactron: Embodied Adaptive Object Detection2202.00660v3 · Klemen Kotar, Roozbeh Mottaghi2022 · 34 citationsarXiv
Contrasting Contrastive Self-Supervised Representation Learning Pipelines2103.14005v2 · Klemen Kotar, Gabriel Ilharco, Ludwig Schmidt et al.2021 · 28 citationsarXiv
AllenAct: A Framework for Embodied AI Research2008.12760v1 · Luca Weihs, Jordi Salvador, Klemen Kotar et al.2020 · 43 citationsarXiv
Career total: 24 works. 19 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.