Our research focuses on creating natural, human-like interactions between people and computers. We're building the foundation for a future where technology understands and responds to us the way we naturally communicate.
Developing advanced models that understand context, emotion, and intent in human speech. Our work focuses on creating more nuanced and contextually aware conversational AI.
• Real-time speech recognition and synthesis
• Contextual understanding and memory
• Emotional intelligence in conversations
Integrating voice, vision, and gesture recognition to create seamless human-computer interfaces that feel natural and intuitive.
• Computer vision and scene understanding
• Gesture and facial expression recognition
• Cross-modal learning and fusion
Building systems that learn and adapt to individual users, creating personalized experiences that improve over time through continuous interaction.
• Long-term memory and user modeling
• Adaptive learning algorithms
• Privacy-preserving personalization
Conference on Neural Information Processing Systems, 2024
Smith, J., Johnson, A., Chen, L.
International Conference on Machine Learning, 2024
Chen, L., Williams, R., Smith, J.
ACM Conference on Computer and Communications Security, 2023
Johnson, A., Davis, M., Chen, L.