Human-AI Interaction

VASA-1: Real-time, lifelike talking faces generated from a single image and audio!

Greedy algorithms outperform conformal prediction in creating prediction sets that maximize human expert accuracy in classification tasks.

SpGesture: A source-free domain-adaptive SEMG gesture recognition system using a novel Spiking Jaccard Attentive Neural Network achieves real-time performance with high accuracy.

Generative AI’s unique characteristics necessitate new pricing strategies; this paper models a sequential pricing game between competing firms, revealing the first-mover’s performance needs to be sign…

PiMForce: Robust hand pressure estimation using 3D hand posture and sEMG!

MambaTalk: Efficient holistic gesture synthesis using selective state space models to overcome computational complexity and improve gesture quality.

AI agents trained with Empowerment via Successor Representations (ESR) empower humans by maximizing their control over environmental outcomes, eliminating the need for human intention inference, unlik…

LangGround: MARL agents learn human-interpretable communication via LLM-grounded training, enabling effective human-agent collaboration.

Boosting preference learning, this research uses human response times to improve linear bandit algorithms, significantly accelerating preference identification.

AI struggles with collaborating effectively with humans due to unpredictable human behavior. This paper introduces Collaborative Bayesian Policy Reuse (CBPR), a novel framework that leverages meta-ta…