Latent Block-Diffusion Temporal Point Processes: A Semi-Autoregressive Framework for Asynchronous Event Sequence Generation
Shuai Zhang, Yancheng Chen, Chuan Zhou, Yang Liu, Xixun Lin, Xiangyu Zhao, Jun Zhu, Zhi-Ming Ma
cs.LG, stat.ML
Submitted: 2026-06-23
Code: https://github.com/Zh-Shuai/LBDTPP
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Next Block Prediction: Video Generation via Semi-Autoregressive Modeling
- SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer
- BIFE: Better Interaction, Fewer Errors for Minute-Long Video Generation
- Lecture Notes: Temporal Point Processes and the Conditional Intensity Function
- Understanding Diffusion Models: A Unified Perspective
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks