| Intriguing Properties of Vision Transformers M Naseer, K Ranasinghe, S Khan, M Hayat, FS Khan, MH Yang Advances in Neural Information Processing Systems (NeurIPS'21), 2021 | 894 | 2021 |
| Self-supervised Video Transformer K Ranasinghe, M Naseer, S Khan, FS Khan, M Ryoo Conference on Computer Vision and Pattern Recognition (CVPR'22), 2022 | 149 | 2022 |
| On Improving Adversarial Transferability of Vision Transformers M Naseer, K Ranasinghe, S Khan, FS Khan, F Porikli International Conference on Learning Representations (ICLR'22), 2022 | 136 | 2022 |
| Orthogonal Projection Loss K Ranasinghe, M Naseer, M Hayat, S Khan, FS Khan International Conference on Computer Vision (ICCV'21), 2021 | 123 | 2021 |
| Perceptual Grouping in Contrastive Vision-Language Models K Ranasinghe, B McKinzie, S Ravi, Y Yang, A Toshev, J Shlens International Conference on Computer Vision (ICCV'23), 2023 | 96* | 2023 |
| Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA J Park, K Ranasinghe, K Kahatapitiya, W Ryu, D Kim, MS Ryoo European Chapter of the Association for Computational Linguistics (EACL '26), 2024 | 57 | 2024 |
| Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs K Ranasinghe, SN Shukla, O Poursaeed, MS Ryoo, TY Lin Conference on Computer Vision and Pattern Recognition (CVPR'24), 2024 | 57 | 2024 |
| LLaRA: Supercharging Robot Learning Data for Vision-Language Policy X Li, C Mata, J Park, K Kahatapitiya, YS Jang, J Shang, K Ranasinghe, ... International Conference on Learning Representations (ICLR'25), 2025 | 56 | 2025 |
| Language Repository for Long Video Understanding K Kahatapitiya, K Ranasinghe, J Park, MS Ryoo arXiv preprint arXiv:2403.14622, 2024 | 52 | 2024 |
| Peekaboo: Text to Image Diffusion Models are Zero-Shot Segmentors R Burgert, K Ranasinghe, X Li, MS Ryoo O-DRUM '23 (Workshop at CVPR'23), 2023 | 48 | 2023 |
| Understanding Long Videos with Multimodal Language Models K Ranasinghe, X Li, K Kahatapitiya, MS Ryoo International Conference on Learning Representations (ICLR'25), 2025 | 34* | 2025 |
| Language-based Action Concept Spaces Improve Video Self-Supervised Learning K Ranasinghe, M Ryoo Advances in Neural Information Processing Systems (NeurIPS'23), 2023 | 20 | 2023 |
| xgen-mm-vid (blip-3-video): You only need 32 tokens to represent a video even in vlms MS Ryoo, H Zhou, S Kendre, C Qin, L Xue, M Shu, J Park, K Ranasinghe, ... arXiv preprint arXiv:2410.16267, 2025 | 18 | 2025 |
| Combined Static and Motion Features for Activity Recognition in Videos S Ramasinghe, J Rajasegaran, V Jayasundara, K Ranasinghe, ... IEEE Transactions on Circuits and Systems for Video Technology, 2019 | 17* | 2019 |
| Diffusion Illusions: Hiding Images in Plain Sight R Burgert, K Ranasinghe, X Li, M Ryoo SIGGRAPH 2024, 2024 | 16 | 2024 |
| Bipartite Conditional Random Fields for Panoptic Segmentation S Jayasumana, K Ranasinghe, M Jayawardhana, S Liyanaarachchi, ... The British Machine Vision Conference (BMVC '21), 2020 | 12 | 2020 |
| Conditional Generative Modeling via Learning the Latent Space S Ramasinghe, K Ranasinghe, S Khan, N Barnes, S Gould International Conference on Learning Representations (ICLR'21), 2020 | 11 | 2020 |
| Pixel Motion as Universal Representation for Robot Control K Ranasinghe, X Li, ER Nguyen, C Mata, J Park, MS Ryoo arXiv preprint arXiv:2505.07817, 2025 | 5 | 2025 |
| Hierarchical Text-to-Vision Self Supervised Alignment for Improved Histopathology Representation Learning H Watawana, K Ranasinghe, T Mahmood, M Naseer, S Khan, FS Khan MICCAI 2024, 2024 | 5 | 2024 |
| CoPT: Unsupervised Domain Adaptive Segmentation Using Domain-Agnostic Text Embeddings C Mata, K Ranasinghe, MS Ryoo ECCV 2024, 2024 | 4 | 2024 |
Michael S. RyooStony Brook University; Salesforce AIVerified email at cs.stonybrook.edu
