no code implementations • 21 Mar 2024 • Xiang Fan, Anand Bhattad, Ranjay Krishna
We introduce Videoshop, a training-free video editing algorithm for localized semantic edits.
1 code implementation • 28 Jun 2023 • Paul Pu Liang, Yiwei Lyu, Xiang Fan, Arav Agarwal, Yun Cheng, Louis-Philippe Morency, Ruslan Salakhutdinov
Learning multimodal representations involves integrating information from multiple heterogeneous sources of data.
no code implementations • 23 May 2023 • Li Pan, Lv Peizhuo, Chen Kai, Cai Yuling, Xiang Fan, Zhang Shengzhi
Compared to traditional neural networks with a single exit, a multi-exit network has multiple exits that allow for early output from intermediate layers of the model, thus bringing significant improvement in computational efficiency while maintaining similar recognition accuracy.
1 code implementation • NeurIPS 2023 • Paul Pu Liang, Yun Cheng, Xiang Fan, Chun Kai Ling, Suzanne Nie, Richard Chen, Zihao Deng, Nicholas Allen, Randy Auerbach, Faisal Mahmood, Ruslan Salakhutdinov, Louis-Philippe Morency
The recent explosion of interest in multimodal applications has resulted in a wide selection of datasets and methods for representing and integrating information from different modalities.
1 code implementation • 10 Nov 2022 • Xiang Fan, Yiwei Lyu, Paul Pu Liang, Ruslan Salakhutdinov, Louis-Philippe Morency
Existing techniques for controlling the distribution of generated text only work with quantified distributions, which require pre-defined categories, proportions of the distribution, or an existing corpus following the desired distributions.
1 code implementation • 2 Mar 2022 • Paul Pu Liang, Yiwei Lyu, Xiang Fan, Jeffrey Tsaw, Yudong Liu, Shentong Mo, Dani Yogatama, Louis-Philippe Morency, Ruslan Salakhutdinov
Many real-world problems are inherently multimodal, from spoken language, gestures, and paralinguistics humans use to communicate, to force, proprioception, and visual sensors on robots.
2 code implementations • 15 Jul 2021 • Paul Pu Liang, Yiwei Lyu, Xiang Fan, Zetian Wu, Yun Cheng, Jason Wu, Leslie Chen, Peter Wu, Michelle A. Lee, Yuke Zhu, Ruslan Salakhutdinov, Louis-Philippe Morency
In order to accelerate progress towards understudied modalities and tasks while ensuring real-world robustness, we release MultiBench, a systematic and unified large-scale benchmark spanning 15 datasets, 10 modalities, 20 prediction tasks, and 6 research areas.