Chuan Guo

20

Papers

127

Total Citations

Papers (20)

AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs

MotionDreamer: One-to-Many Motion Synthesis with Localized Generative Masked Transformer

Differentially Private Representation Learning via Image Captioning

Generating Diverse and Natural 3D Human Motions From Text

MotionMix: Weakly-Supervised Diffusion for Controllable Motion Generation

TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integration

TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts

Supervised Word Mover's Distance

EventHPE: Event-Based 3D Human Pose and Shape Estimation

ViP: A Differentially Private Foundation Model for Computer Vision

Simple Black-box Adversarial Attacks

Breaking the Glass Ceiling for Embedding-Based Classifiers for Large Output Spaces

A New Defense Against Adversarial Images: Turning a Weakness into a Strength

ReAct: Out-of-distribution Detection With Rectified Activations

Online Adaptation to Label Distribution Shift

Fixes That Fail: Self-Defeating Improvements in Machine-Learning Systems

BulletTrain: Accelerating Robust Neural Network Training via Boundary Example Mining

Do SSL Models Have Déjà Vu? A Case of Unintended Memorization in Self-supervised Learning

Bounding the Invertibility of Privacy-preserving Instance Encoding using Fisher Information

On Calibration of Modern Neural Networks