Statistical Learning
ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose Estimation Cรฉdric Rommel
We propose ManiPose, a manifold-constrained multi-hypothesis model for human-pose 2D-to-3D lifting.
Harmony4D: A Video Dataset for In-The-Wild Close Human Interactions
Understanding how humans interact with each other is key to building realistic multi-human virtual reality systems. This area remains relatively unexplored due to the lack of large-scale datasets. Recent datasets focusing on this issue mainly consist of activities captured entirely in controlled indoor environments with choreographed actions, significantly affecting their diversity.
Adaptive Preference Scaling for Reinforcement Learning with Human Feedback
In this paper, we propose a novel adaptive preference loss, underpinned by distributionally robust optimization (DRO), designed to address this uncertainty in preference strength.
Trajectory Flow Matching with Applications to Clinical Time Series Modeling
Neural stochastic differential equations (Neural SDEs) are an attractive modeling technique for this problem, which parameterize the drift and diffusion terms of an SDE with neural networks.
Self-Calibrating Conformal Prediction
In machine learning, model calibration and predictive inference are essential for producing reliable predictions and quantifying uncertainty to support decision-making.