6 accepted papers
The multi-agent trajectory planning problem is a difficult problem in robotics due to its computational complexity and real-world environment complexity with uncertainty, non-linearity, and real-time requirements. Many existing solutions are either search-based or optimization-based approaches with…
Individual user profiles and interaction histories play a significant role in providing customized experiences in real-world applications such as chatbots, social media, retail, and education. Adaptive user representation learning by utilizing user personalized information has be-come increasingly c…
We present a simple yet effective approach to build multilingual speech-to-text (ST) translation through efficient transfer learning from a pretrained speech encoder and text decoder. Our key finding is that a minimalistic LNA (LayerNorm and Attention) finetuning can achieve zero-shot crosslingual a…
Recent studies have demonstrated the cross-lingual alignment ability of multilingual pretrained language models. In this work, we found that the cross-lingual alignment can be further improved by training seq2seq models on sentence pairs mined using their own encoder outputs. We utilized these findi…
The Transformer model has achieved state-of-the-art performance in many sequence modeling tasks. However, how to leverage model capacity with large or variable depths is still an open challenge. We present a probabilistic framework to automatically learn which layer(s) to use by learning the posteri…
We present a method to validate a cognitive model, based on the cognitive architecture ACT-R, in dynamic human-automation systems with discrete human input. We are inspired by the general problem of K-choice games as a proxy for many decision making applications in dynamical systems. We model the hu…