Technology
Sounding Bodies: Modeling 3D Spatial Sound of Humans Using Body Pose and Audio
The system consumes, as input, audio signals from headset microphones and body pose, and produces, as output, a 3D sound field surrounding the transmitter's
Talking Heads: Understanding Inter-layer Communication in Transformer Language Models
These failure cases are particularly troubling because they are not systematic; it is very difficult to predict when, for example, the order of information seemingly randomly causes a model to fail [Pezeshkpour and Hruschka, 2023, Liu et al., 2024, Li and Gao, 2024, Zheng et al.,
Unsupervised Homography Estimation on Multimodal Image Pair via Alternating Optimization
In response, unsupervised learning approaches have emerged.
DRAUC: An Instance-wise Distributionally Robust AUC Optimization Framework
Distributionally Robust Optimization (DRO) enhances model performance by optimizing it for the local worst-case scenario, but directly integrating AUC optimization with DRO results in an intractable optimization problem.
Real-Time Selection Under General Constraints via Predictive Inference
Real-time decision-making gets more attention in the big data era.