1 citations · 1 across the 9 of their papers we have counts for
5 papers · 1 filter
Enhancing Few-Shot Out-of-Distribution Detection with Gradient Aligned Context Optimization
Baoshun Tong, Kaiyu Song, Hanjiang Lai
Few-shot out-of-distribution (OOD) detection aims to detect OOD images from unseen classes with only a few labeled in-distribution (ID) images. To detect OOD images and classify ID…
Test-time Alignment-Enhanced Adapter for Vision-Language Models
Baoshun Tong, Kaiyu Song, Hanjiang Lai
Test-time adaptation with pre-trained vision-language models (VLMs) has attracted increasing attention for tackling the issue of distribution shift during the test phase. While pri…
Leveraging Previous Steps: A Training-free Fast Solver for Flow Diffusion
Kaiyu Song, Hanjiang Lai
Flow diffusion models (FDMs) have recently shown potential in generation tasks due to the high generation quality. However, the current ordinary differential equation (ODE) solver…
Flow Matching Posterior Sampling: A Training-free Conditional Generation for Flow Matching
Kaiyu Song, Hanjiang Lai, Yan Pan +2
Training-free conditional generation based on flow matching aims to leverage pre-trained unconditional flow matching models to perform conditional generation without retraining. Re…
Improving Training-free Conditional Diffusion Model via Fisher Information
Kaiyu Song, Hanjiang Lai
Training-free conditional diffusion models have received great attention in conditional image generation tasks. However, they require a computationally expensive conditional score…