1 citations · 2 across the 10 of their papers we have counts for
12 papers
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…
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…
Line-Search Filter Differential Dynamic Programming for Optimal Control with Nonlinear Equality Constraints
Ming Xu, Stephen Gould, Iman Shames
We present FilterDDP, a differential dynamic programming algorithm for solving discrete-time, optimal control problems (OCPs) with nonlinear equality constraints. Unlike prior meth…
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…
Negative Token Merging: Image-based Adversarial Feature Guidance
Jaskirat Singh, Lindsey Li, Weijia Shi +7
Text-based adversarial guidance using a negative prompt has emerged as a widely adopted approach to steer diffusion models away from producing undesired concepts. While useful, per…
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…
Temporally Consistent Unbalanced Optimal Transport for Unsupervised Action Segmentation
Ming Xu, Stephen Gould
We propose a novel approach to the action segmentation task for long, untrimmed videos, based on solving an optimal transport problem. By encoding a temporal consistency prior into…
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…
Revisiting Implicit Differentiation for Learning Problems in Optimal Control
Ming Xu, Timothy Molloy, Stephen Gould
This paper proposes a new method for differentiating through optimal trajectories arising from non-convex, constrained discrete-time optimal control (COC) problems using the implic…