11 papers
MDN-VJEPA: Multimodal Probabilistic Joint-Embedding World Models
Yongchao Huang
Joint-Embedding Predictive Architectures (JEPAs) learn world models by predicting future representations rather than reconstructing observations. Variational JEPA (VJEPA) gives thi…
4DGS-JEPA: Temporally Compositional Joint-Embedding Prediction for Dynamic Gaussian Splatting
Yongchao Huang
Dynamic Gaussian Splatting provides an explicit representation of evolving 3D scenes, but existing approaches are primarily optimized for reconstruction, future-state generation, o…
Your Probabilistic JEPA Is Secretly a Hidden Markov Model: A State-Space Interpretation of Joint-Embedding Predictive Learning
Yongchao Huang
A hidden Markov model (HMM) combines three roles: inference of a hidden-state belief from observations, propagation through a Markov transition, and emission back to observation sp…
SJEPA: Learning Elegant Latent Dynamics with Hybrid Symbolic-Neural Predictors
Yongchao Huang
Joint-embedding predictive architectures learn abstract states by predicting target embeddings from context embeddings, but their transition models are typically opaque neural maps…
Gaussian Mixture Attention: Linear-Time Sequence Mixing via Probabilistic Latent Routing
Yongchao Huang, Hassan Raza
The dense token-to-token interaction pattern of standard dot-product attention remains a central bottleneck in scaling Transformer architectures to long contexts. We introduce \tex…
Knowledge, Rules and Their Embeddings: Two Paths towards Neuro-Symbolic JEPA
Yongchao Huang, Hassan Raza
Modern self-supervised predictive architectures excel at capturing complex statistical correlations from high-dimensional data but lack mechanisms to internalize verifiable human l…
VJEPA: Variational Joint Embedding Predictive Architectures as Probabilistic World Models
Yongchao Huang
Joint Embedding Predictive Architectures (JEPA) offer a scalable paradigm for self-supervised learning by predicting latent representations rather than reconstructing high-entropy…
Sampling via Gaussian Mixture Approximations
Yongchao Huang
We present a family of \textit{Gaussian Mixture Approximation} (GMA) samplers for sampling unnormalised target densities, encompassing \textit{weights-only GMA} (W-GMA), \textit{La…
Semantic Fusion with Fuzzy-Membership Features for Controllable Language Modelling
Yongchao Huang, Hassan Raza
We propose semantic fusion, a lightweight scheme that augments a Transformer language model (LM) with a parallel, fuzzy-membership feature channel that encodes token-level semantic…
RL as Regressor: A Reinforcement Learning Approach for Function Approximation
Yongchao Huang
Standard regression techniques, while powerful, are often constrained by predefined, differentiable loss functions such as mean squared error. These functions may not fully capture…
Probabilistic and reinforced mining of association rules
Yongchao Huang
This work introduces 4 novel probabilistic and reinforcement-driven methods for association rule mining (ARM): Gaussian process-based association rule mining (GPAR), Bayesian ARM (…