Rishabh Kabra

Most-cited papers

1. PaliGemma: A versatile 3B VLM for transfer

   L. Beyer, A. Steiner, André Susano Pinto, Alexander Kolesnikov +31 more

   2024arXiv.org851 citations

   Semantic Scholar

   Save

2. MONet: Unsupervised Scene Decomposition and Representation

   Christopher P. Burgess, L. Matthey, Nicholas Watters, Rishabh Kabra +3 more

   2019arXiv.org637 citations

   Semantic Scholar

   Save

3. Multi-Object Representation Learning with Iterative Variational Inference

   Klaus Greff, Raphael Lopez Kaufman, Rishabh Kabra, Nicholas Watters +5 more

   2019International Conference on Machine Learning604 citations

   Semantic Scholar

   Save

4. An investigation of model-free planning

   A. Guez, Mehdi Mirza, K. Gregor, Rishabh Kabra +9 more

   2019International Conference on Machine Learning138 citations

   Semantic Scholar

   Save

5. SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition

   Rishabh Kabra, Daniel Zoran, Goker Erdogan, L. Matthey +4 more

   2021Neural Information Processing Systems91 citations

   Semantic Scholar

   Save

6. PARTS: Unsupervised segmentation with slots, attention and independence maximization

   Daniel Zoran, Rishabh Kabra, Alexander Lerchner, Danilo Jimenez Rezende

   2021IEEE International Conference on Computer Vision54 citations

   Semantic Scholar

   Save

7. Scaling 4D Representations

   João Carreira, Dilara Gokay, Michael King, Chu-Han Zhang +31 more

   2024arXiv.org32 citations

   Semantic Scholar

   Save

8. Neural Assets: 3D-Aware Multi-Object Scene Synthesis with Image Diffusion Models

   Kelsey R. Allen, Yusuf Aytar, Igor Gilitschenski, Drew A. Hudson +5 more

   2024Neural Information Processing Systems32 citations

   Semantic Scholar

   Save

9. Unsupervised Object-Based Transition Models for 3D Partially Observable Environments

   A. Creswell, Rishabh Kabra, Christopher P. Burgess, M. Shanahan

   2021Neural Information Processing Systems30 citations

   Semantic Scholar

   Save

10. OpenWorldSAM: Extending SAM2 for Universal Image Segmentation with Language Prompts

    Shi-Ting Xiao, Rishabh Kabra, Yuhang Li, Donghyun Lee +2 more

    2025Neural Information Processing Systems18 citations

    Semantic Scholar

    Save

11. From Image to Video: An Empirical Study of Diffusion Representations

    Pedro Vélez, Luisa F. Polan'ia, Yi Yang, Chu-Han Zhang +3 more

    2025IEEE International Conference on Computer Vision17 citations Open access

    Semantic Scholar

    Save

12. Video Generation Models are General-Purpose Vision Learners

    Le-Tian Wang, Chu-Han Zhang, Rishabh Kabra, J. Uijlings +8 more

    2026arXiv.org16 citations

    Semantic Scholar

    Save

13. AlignNet: Unsupervised Entity Alignment

    A. Creswell, Kyriacos Nikiforou, O. Vinyals, Andre Saraiva +7 more

    2020arXiv.org14 citations

    Semantic Scholar

    Save

14. Moving Off-the-Grid: Scene-Grounded Video Representations

    João Carreira, Carl Doersch, A. Dosovitskiy, Dilara Gokay +12 more

    2024Neural Information Processing Systems13 citations

    Semantic Scholar

    Save

15. Leveraging VLM-Based Pipelines to Annotate 3D Objects

    Rishabh Kabra, L. Matthey, Alexander Lerchner, N. Mitra

    2023International Conference on Machine Learning12 citations

    Semantic Scholar

    Save

16. Constellation: Learning relational abstractions over objects for compositional imagination

    James C. R. Whittington, Rishabh Kabra, L. Matthey, Christopher P. Burgess +1 more

    2021arXiv.org6 citations

    Semantic Scholar

    Save

17. A Mixed Diet Makes DINO An Omnivorous Vision Encoder

    Rishabh Kabra, M. Ovsjanikov, Drew A. Hudson, Ye Xia +4 more

    2026arXiv.org4 citations

    Semantic Scholar

    Save

18. Frozen Forecasting: A Unified Evaluation

    Jacob Walker, Pedro Vélez, Luisa Polania Cabrera, Guangyao Zhou +6 more

    20254 citations

    Semantic Scholar

    Save

19. Evaluating VLMs for Score-Based, Multi-Probe Annotation of 3D Objects

    Rishabh Kabra, L. Matthey, Alexander Lerchner, Niloy J. Mitra

    2023arXiv.org3 citations

    Semantic Scholar

    Save

20. TAPVid-MV: A Benchmark for Tracking Any Point in 3D Across Multiple Views

    Skanda Koppula, Frano Rajic, Abdullah Faiz Ur Rahman, Yi Yang +8 more

    20261 citations

    Semantic Scholar

    Save

21. How to Spin an Object: First, Get the Shape Right

    Rishabh Kabra, Drew A. Hudson, Sjoerd van Steenkiste, Joao Carreira +1 more

    20240 citations

    Semantic Scholar

    Save