no code implementations • EMNLP 2021 • Ishaan Grover, Matthew Huggins, Cynthia Breazeal, Hae Won Park
Recent state-of-the-art approaches in open-domain dialogue include training end-to-end deep-learning models to learn various conversational features like emotional content of response, symbolic transitions of dialogue contexts in a knowledge graph and persona of the agent and the user, among others.
1 code implementation • 22 Apr 2024 • Yubin Kim, Chanwoo Park, Hyewon Jeong, Yik Siu Chan, Xuhai Xu, Daniel McDuff, Cynthia Breazeal, Hae Won Park
Our novel framework, Medical Decision-making Agents (MDAgents) aims to address this gap by automatically assigning the effective collaboration structure for LLMs.
no code implementations • 17 Mar 2024 • Dong Won Lee, Hae Won Park, Yoon Kim, Cynthia Breazeal, Louis-Philippe Morency
We describe an approach for aligning an LLM-based dialogue agent based on global (i. e., dialogue-level) rewards, while also taking into account naturally-occurring multimodal signals.
no code implementations • 12 Jan 2024 • Yubin Kim, Xuhai Xu, Daniel McDuff, Cynthia Breazeal, Hae Won Park
Notably, we observe that our context enhancement can yield up to 23. 8% improvement in performance.
no code implementations • 23 May 2023 • Jocelyn Shen, Maarten Sap, Pedro Colon-Hernandez, Hae Won Park, Cynthia Breazeal
The most meaningful connections between people are often fostered through expression of shared vulnerability and emotional experiences in personal narratives.
no code implementations • 21 May 2023 • Yubin Kim, Dong Won Lee, Paul Pu Liang, Sharifa Algohwinem, Cynthia Breazeal, Hae Won Park
Accurately modeling affect dynamics, which refers to the changes and fluctuations in emotions and affective displays during human conversations, is crucial for understanding human interactions.
no code implementations • 19 Apr 2023 • Dong Won Lee, Yubin Kim, Rosalind Picard, Cynthia Breazeal, Hae Won Park
As we move closer to real-world AI systems, AI agents must be able to deal with multiparty (group) conversations.
no code implementations • 28 Dec 2022 • Yubin Kim, Huili Chen, Sharifa Alghowinem, Cynthia Breazeal, Hae Won Park
This work serves as the first step toward fully unlocking the potential of end-to-end video understanding models pre-trained on large public datasets and augmented with data augmentation and visualization techniques for affect recognition in the multi-person human-robot interaction in the wild.
no code implementations • 10 Jun 2022 • Siyu Liu, Catherine Lu, Sharifa Alghowinem, Lea Gotoh, Cynthia Breazeal, Hae Won Park
The prevalence of suicide has been on the rise since the 20th century, causing severe emotional damage to individuals, families, and communities alike.
no code implementations • 20 Aug 2020 • Huili Chen, Yue Zhang, Felix Weninger, Rosalind Picard, Cynthia Breazeal, Hae Won Park
Automatic speech-based affect recognition of individuals in dyadic conversation is a challenging task, in part because of its heavy reliance on manual pre-processing.