Re-evaluating the Need for Visual Signals in Unsupervised Grammar Induction B Li, R Corona, K Mangalam, C Chen, D Flaherty, S Belongie, ... Findings of the Association for Computational Linguistics: NAACL 2024, 1113-1123, 2024 | | 2024 |
Llm2llm: Boosting llms with novel iterative data enhancement N Lee, T Wattanawong, S Kim, K Mangalam, S Shen, G Anumanchipali, ... arXiv preprint arXiv:2403.15042, 2024 | 7 | 2024 |
xT: Nested Tokenization for Larger Context in Large Images R Gupta, S Li, T Zhu, J Malik, T Darrell, K Mangalam arXiv preprint arXiv:2403.01915, 2024 | 1 | 2024 |
Speculative decoding with big little decoder S Kim, K Mangalam, S Moon, J Malik, MW Mahoney, A Gholami, ... Advances in Neural Information Processing Systems 36, 2024 | 33 | 2024 |
Egoschema: A diagnostic benchmark for very long-form video language understanding K Mangalam, R Akshulakov, J Malik Advances in Neural Information Processing Systems 36, 2024 | 54 | 2024 |
Dr2Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning C Zhao, S Liu, K Mangalam, G Qian, F Zohra, A Alghannam, J Malik, ... Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2024 | 1 | 2024 |
Do Vision and Language Encoders Represent the World Similarly? M Maniparambil, R Akshulakov, YAD Djilali, M El Amine Seddik, ... Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2024 | | 2024 |
Sequential modeling enables scalable learning for large vision models Y Bai, X Geng, K Mangalam, A Bar, AL Yuille, T Darrell, J Malik, AA Efros Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2024 | 63 | 2024 |
Perceiving People over Long Periods: Algorithms, Architectures & Datasets K Mangalam | | 2023 |
Adaptive Human Trajectory Prediction via Latent Corridors N Thakkar, K Mangalam, A Bajcsy, J Malik arXiv preprint arXiv:2312.06653, 2023 | | 2023 |
PaReprop: Fast Parallelized Reversible Backpropagation T Zhu, K Mangalam arXiv preprint arXiv:2306.09342, 2023 | 1 | 2023 |
Latency-Aware Short-Term Video Action Anticipation and its Application in Trajectory Prediction H Girase, K Mangalam, J Malik | | 2023 |
Latency matters: Real-time action forecasting transformer H Girase, N Agarwal, C Choi, K Mangalam Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023 | 12 | 2023 |
Diffusion models as masked autoencoders C Wei, K Mangalam, PY Huang, Y Li, H Fan, H Xu, H Wang, C Xie, ... Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2023 | 31 | 2023 |
Big little transformer decoder S Kim, K Mangalam, J Malik, MW Mahoney, A Gholami, K Keutzer arXiv preprint arXiv:2302.07863 1, 2023 | 22 | 2023 |
Re2TAL: Rewiring pretrained video backbones for reversible temporal action localization C Zhao, S Liu, K Mangalam, B Ghanem Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023 | 19 | 2023 |
A Vision-free Baseline for Multimodal Grammar Induction B Li, R Corona, K Mangalam, C Chen, D Flaherty, S Belongie, ... arXiv preprint arXiv:2212.10564, 2022 | 1 | 2022 |
Does unsupervised grammar induction need pixels? B Li*, R Corona*, K Mangalam*, C Chen, D Flaherty, S Belongie, ... arXiv preprint arXiv:2212.10564, 2022 | 3 | 2022 |
Bringing image scene structure to video via frame-clip consistency of object tokens E Ben Avraham, R Herzig, K Mangalam, A Bar, A Rohrbach, L Karlinsky, ... Advances in Neural Information Processing Systems 35, 26839-26855, 2022 | 12 | 2022 |
Squeezeformer: An efficient transformer for automatic speech recognition S Kim, A Gholami, A Shaw, N Lee, K Mangalam, J Malik, MW Mahoney, ... Advances in Neural Information Processing Systems 35, 9361-9373, 2022 | 80 | 2022 |