← Rohit Girdhar

Publications

1. 2026
   Muse Image and Video In Meta AI Blog, 2026
2. 2026
   Fast, High-Fidelity Video Editing In Meta AI & Instagram Edits, 2026
3. 2026
   Human detectors are surprisingly powerful reward models In arXiv, 2026
4. 2025
   Toward Diffusible High-Dimensional Latent Spaces: A Frequency Perspective In CVPR, 2026
5. 2025
   Diffusion Autoencoders are Scalable Image Tokenizers In arXiv, 2025
6. 2025
   LLMs can see and hear without any training In ICML, 2025
7. 2024
   MotiF: Making Text Count in Image Animation with Motion Focal Loss In CVPR, 2025
8. 2024
   Movie Gen: A Cast of Media Foundation Models In arXiv, 2024
9. 2024
   The Llama 3 Herd of Models In arXiv, 2024
10. 2024
    SoundingActions: Learning How Actions Sound from Narrated Egocentric Videos In CVPR, 2024
11. 2024
    InstanceDiffusion: Instance-level Control for Image Generation In CVPR, 2024
12. 2023
    Generating Illustrated Instructions In CVPR, 2024
13. 2023
    Motion-Conditioned Image Animation for Video Editing In arXiv, 2023
14. 2023
    VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation In CVPR, 2024
15. 2023
    Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning In ECCV, 2024
16. 2023
    ImageBind: One Embedding Space To Bind Them All In CVPR, 2023 (Highlighted Presentation)
17. 2023
    The effectiveness of MAE pre-pretraining for billion-scale pretraining In ICCV, 2023
18. 2023
    CutLER: Cut and Learn for Unsupervised Object Detection and Instance Segmentation In CVPR, 2023
19. 2023
    HierVL: Learning Hierarchical Video-Language Embeddings In CVPR, 2023 (Highlighted Presentation)
20. 2022
    Learning Video Representations from Large Language Models In CVPR, 2023 (Highlighted Presentation)
21. 2022
    OmniMAE: Single Model Masked Pretraining on Images and Videos In CVPR, 2023
22. 2022
    Omnivore: A Single Model for Many Visual Modalities In CVPR, 2022 (Oral Presentation)
23. 2022
    Ego4D: Around the World in 3,000 Hours of Egocentric Video In CVPR, 2022 (Best paper finalist)
24. 2022
    Detecting Twenty-thousand Classes using Image-level Supervision In ECCV, 2022
25. 2021
    Mask2Former for Video Instance Segmentation In arXiv, 2021
26. 2021
    Masked-attention Mask Transformer for Universal Image Segmentation In CVPR, 2022
27. 2021
    3DETR: An End-to-End Transformer Model for 3D Object Detection In ICCV, 2021 (Oral Presentation)
28. 2021
    Anticipative Video Transformer In ICCV, 2021
29. 2021
    3D Spatial Recognition without Spatially Labeled 3D In CVPR, 2021
30. 2021
    Self-Supervised Pretraining of 3D Features on any Point-Cloud In CVPR, 2021
31. 2021
    Physical Reasoning Using Dynamics Aware Embeddings In ICML Workshops, 2021
32. 2020
    Forward Prediction for Physical Reasoning In ICML Workshops, 2021
33. 2019
    CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning In ICLR, 2020 (Oral Presentation)
34. 2019
    MetaPix: Few-Shot Video Retargeting In ICLR, 2020
35. 2019
    DistInit: Learning Video Representations Without a Single Labeled Video In ICCV, 2019
36. 2018
    Video Action Transformer Network In CVPR, 2019 (Oral Presentation)
37. 2017
    Detect-and-Track: Efficient Pose Estimation in Videos In CVPR, 2018
38. 2017
    Attentional Pooling for Action Recognition In NeurIPS, 2017
39. 2017
    ActionVLAD: Learning spatio-temporal aggregation for action classification In CVPR, 2017
40. 2016
    Binge Watching: Scaling Affordance Learning from Sitcoms In CVPR, 2017 (Spotlight Presentation)
41. 2016
    Learning a Predictable and Generative Vector Representation for Objects In ECCV, 2016 (Spotlight Presentation)