Tag
This paper proposes modeling the CLIP latent space using Mixtures of von Mises–Fisher distributions on the unit hypersphere, capturing its directional and multimodal structure better than Gaussian assumptions. The model improves long-tailed and out-of-distribution detection and provides a semantic decomposition of CLIP embeddings.
This paper introduces PGRE, a probabilistic model for dynamic knowledge graphs that captures inter-relational dependencies using Poisson-Gamma and Markov processes, achieving competitive link prediction performance especially in sparse settings.
Proposes a hierarchical Bayesian framework for meta-learning in dynamical systems from multiple sparse, noisy datasets, using gradient-based MCMC with an embedded ODE solver for efficient posterior inference of shared and dataset-specific parameters.
Proposes NF-CoT, a latent reasoning framework using normalizing flows to model continuous thoughts in LLMs, preserving autoregressive advantages and achieving better code generation performance with lower cost.