Asia
T2I-CompBench: A Comprehensive Benchmark for Open-world Compositional Text-to-image Generation
We introduce a new approach, Generative mOdel finetun-ing with Reward-driven Sample selection (GORS), to boost the compositional text-to-image generation abilities of pretrained text-to-image models.
Causal Inference in the Closed-Loop: Marginal Structural Models for Sequential Excursion Effects Alexander W. Levis
To fill this gap, we introduce a nonparametric causal inference framework for analyzing "closed-loop" designs, which use
Nearly Minimax Optimal Regret for Multinomial Logistic Bandit
Hence, the following research questions arise: What is the optimal regret lower bound in contextual MNL bandits?
Neural Sampling in Hierarchical Exponential-family Energy-based Models
Bayesian brain theory suggests that the brain employs generative models to understand the external world.
Understanding and Improving Training-free Loss-based Diffusion Guidance
In this paper, we aim to develop a deeper understanding of training-free guidance, as well as overcome its limitations.
