7 papers
CausalWM: Causal Chain-of-Thought Reasoning for Embodied World Model
Ziming Xu, Shuang Liang, Ruobing Han +10
Embodied world models learn to predict future physical dynamics from visual observations and control signals, where physical knowledge is implicitly entangled within latent represe…
Differentiable Mesh State Estimation via Factor Graph Inference for Deformable Object Reconstruction
Lidia Al-Zogbi, Fangjie Li, Samuel Tobin +13
Estimating deformable object states remains a fundamental challenge in robotics and simulation. We propose a novel factor graph-based framework for probabilistic mesh state estimat…
Generalization and Memorization in Rectified Flow
Mingxing Rao, Daniel Moyer
Generative models based on the Flow Matching objective, particularly Rectified Flow, have emerged as a dominant paradigm for efficient, high-fidelity image synthesis. However, whil…
Latent Diffusion Inversion Requires Understanding the Latent Space
Mingxing Rao, Bowen Qu, Daniel Moyer
The recovery of training data from generative models ("model inversion") has been extensively studied for diffusion models in the data domain as a memorization/overfitting phenomen…
Score-based Membership Inference on Diffusion Models
Mingxing Rao, Bowen Qu, Daniel Moyer
Membership inference attacks (MIAs) against Diffusion Models (DMs) raise pressing privacy concerns by revealing whether a sample was part of the training set. While existing method…
Training Noise Token Pruning
Mingxing Rao, Bohan Jiang, Daniel Moyer
In the present work we present Training Noise Token (TNT) Pruning for vision transformers. Our method relaxes the discrete token dropping condition to continuous additive noise, pr…
Zero-shot Prompt-based Video Encoder for Surgical Gesture Recognition
Mingxing Rao, Yinhong Qin, Soheil Kolouri +2
Purpose: In order to produce a surgical gesture recognition system that can support a wide variety of procedures, either a very large annotated dataset must be acquired, or fitted…