1 citations · 1 across the 8 of their papers we have counts for
10 papers
LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories
Zhanhao Liang, Tao Yang, Jie Wu +2
This paper focuses on the alignment of flow matching models with human preferences. A promising way is fine-tuning by directly backpropagating reward gradients through the differen…
Flexible Geometric Guidance for Probabilistic Human Pose Estimation with Diffusion Models
Francis Snelgar, Ming Xu, Stephen Gould +2
3D human pose estimation from 2D images is a challenging problem due to depth ambiguity and occlusion. Because of these challenges the task is underdetermined, where there exists m…
Gromov Wasserstein Optimal Transport for Semantic Correspondences
Francis Snelgar, Stephen Gould, Ming Xu +2
Establishing correspondences between image pairs is a long studied problem in computer vision. With recent large-scale foundation models showing strong zero-shot performance on dow…
SimFlow: Simplified and End-to-End Training of Latent Normalizing Flows
Qinyu Zhao, Guangting Zheng, Tao Yang +4
Normalizing Flows (NFs) learn invertible mappings between the data and a Gaussian distribution. Prior works usually suffer from two limitations. First, they add random noise to tra…
Confidence and Dispersity as Signals: Unsupervised Model Evaluation and Ranking
Weijian Deng, Weijie Tu, Ibrahim Radwan +3
Assessing model generalization under distribution shift is essential for real-world deployment, particularly when labeled test data is unavailable. This paper presents a unified an…
DiSA: Diffusion Step Annealing in Autoregressive Image Generation
Qinyu Zhao, Jaskirat Singh, Ming Xu +3
An increasing number of autoregressive models, such as MAR, FlowAR, xAR, and Harmon adopt diffusion sampling to improve the quality of image generation. However, this strategy lead…
ARINAR: Bi-Level Autoregressive Feature-by-Feature Generative Models
Qinyu Zhao, Stephen Gould, Liang Zheng
Existing autoregressive (AR) image generative models use a token-by-token generation schema. That is, they predict a per-token probability distribution and sample the next token fr…
Can We Predict Performance of Large Models across Vision-Language Tasks?
Qinyu Zhao, Ming Xu, Kartik Gupta +3
Evaluating large vision-language models (LVLMs) is very expensive, due to high computational cost and the wide variety of tasks. The good news is that if we already have some obser…
The First to Know: How Token Distributions Reveal Hidden Knowledge in Large Vision-Language Models?
Qinyu Zhao, Ming Xu, Kartik Gupta +3
Large vision-language models (LVLMs), designed to interpret and respond to human instructions, occasionally generate hallucinated or harmful content due to inappropriate instructio…
Towards Optimal Feature-Shaping Methods for Out-of-Distribution Detection
Qinyu Zhao, Ming Xu, Kartik Gupta +3
Feature shaping refers to a family of methods that exhibit state-of-the-art performance for out-of-distribution (OOD) detection. These approaches manipulate the feature representat…