Search Results for author:
Found 10 papers, 0 papers with code
MRF-Chat: Improving Dialogue with Markov Random Fields
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.
Adaptive Collaboration Strategy for LLMs in Medical Decision Making
Our novel framework, Medical Decision-making Agents (MDAgents) aims to address this gap by automatically assigning the effective collaboration structure for LLMs.
Improving Dialogue Agents by Decomposing One Global Explicit Annotation with Local Implicit Multimodal Feedback
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.
Health-LLM: Large Language Models for Health Prediction via Wearable Sensor Data
Notably, we observe that our context enhancement can yield up to 23. 8% improvement in performance.
Modeling Empathic Similarity in Personal Narratives
The most meaningful connections between people are often fostered through expression of shared vulnerability and emotional experiences in personal narratives.
HIINT: Historical, Intra- and Inter- personal Dynamics Modeling with Cross-person Memory Transformer
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.
Multipar-T: Multiparty-Transformer for Capturing Contingent Behaviors in Group Conversations
As we move closer to real-world AI systems, AI agents must be able to deal with multiparty (group) conversations.
Joint Engagement Classification using Video Augmentation Techniques for Multi-person Human-robot Interaction
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.
Explainable AI for Suicide Risk Assessment Using Eye Activities and Head Gestures
The prevalence of suicide has been on the rise since the 20th century, causing severe emotional damage to individuals, families, and communities alike.
Dyadic Speech-based Affect Recognition using DAMI-P2C Parent-child Multimodal Interaction Dataset
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.
