Europe
A hierarchical decomposition for explaining ML performance discrepancies
Machine learning (ML) algorithms can often differ in performance across domains.
Where's Waldo: Diffusion Features For Personalized Segmentation and Retrieval
While supervised methods are effective, they require extensive labeled data for training. Recently, self-supervised foundation models have been introduced to these tasks showing comparable results to supervised methods.
Efficient Video-to-Audio Generation Network with Rectified Flow Matching Y ongqi Wang
V2A model based on rectified flow matching.
Analysis of Corrected Graph Convolutions
Machine learning for node classification on graphs is a prominent area driven by applications such as recommendation systems.
Parseval Regularization for Continual Reinforcement Learning
We show that it provides significant benefits to RL agents on a suite of gridworld, CARL and MetaWorld tasks.
Active Sequential Posterior Estimation for Sample-Efficient Simulation-Based Inference
ASNPE brings an active learning scheme into the inference loop to estimate the utility of simulation parameter candidates to the underlying probabilistic model.
MoMu-Diffusion: On Learning Long-Term Motion-Music Synchronization and Correspondence
Dancing to the musical beats or creating a variety of rhythmically synchronized music for a given motion is a fundamental aspect of human creativity.