565 citations · 1.7k across the 68 of their papers we have counts for
9 papers · 1 filter
Cross-Modal Generalization: Learning in Low Resource Modalities via Meta-Alignment
Paul Pu Liang, Peter Wu, Liu Ziyin +2
The natural world is abundant with concepts expressed via visual, acoustic, tactile, and linguistic modalities. Much of the existing progress in multimodal learning, however, focus…
Multimodal Privacy-preserving Mood Prediction from Mobile Data: A Preliminary Study
Terrance Liu, Paul Pu Liang, Michal Muszynski +5
Mental health conditions remain under-diagnosed even in countries with common access to advanced medical care. The ability to accurately and efficiently predict mood from easily co…
An Investigation of how Label Smoothing Affects Generalization
Blair Chen, Liu Ziyin, Zihao Wang +1
It has been hypothesized that label smoothing can reduce overfitting and improve generalization, and current empirical evidence seems to corroborate these effects. However, there i…
Towards Debiasing Sentence Representations
Paul Pu Liang, Irene Mengze Li, Emily Zheng +3
As natural language processing methods are increasingly deployed in real-world scenarios such as healthcare, legal systems, and social science, it becomes necessary to recognize th…
Anchor & Transform: Learning Sparse Embeddings for Large Vocabularies
Paul Pu Liang, Manzil Zaheer, Yuan Wang +1
Learning continuous representations of discrete objects such as text, users, movies, and URLs lies at the heart of many applications including language and user modeling. When usin…
Diverse and Admissible Trajectory Forecasting through Multimodal Context Understanding
Seong Hyeon Park, Gyubok Lee, Manoj Bhat +6
Multi-agent trajectory forecasting in autonomous driving requires an agent to accurately anticipate the behaviors of the surrounding vehicles and pedestrians, for safe and reliable…
On Emergent Communication in Competitive Multi-Agent Teams
Paul Pu Liang, Jeffrey Chen, Ruslan Salakhutdinov +2
Several recent works have found the emergence of grounded compositional language in the communication protocols developed by mostly cooperative multi-agent systems when learned end…
Learning Not to Learn in the Presence of Noisy Labels
Liu Ziyin, Blair Chen, Ru Wang +4
Learning in the presence of label noise is a challenging yet important task: it is crucial to design models that are robust in the presence of mislabeled datasets. In this paper, w…
Think Locally, Act Globally: Federated Learning with Local and Global Representations
Paul Pu Liang, Terrance Liu, Liu Ziyin +5
Federated learning is a method of training models on private data distributed over multiple devices. To keep device data private, the global model is trained by only communicating…