Chuan Guo

papers

1,466

total citations

papers (17)

ReAct: Out-of-distribution Detection With Rectified Activations

NEURIPS 2021arXiv

601

citations

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

ECCV 2022arXiv

354

citations

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

NEURIPS 2023arXiv

citations

BulletTrain: Accelerating Robust Neural Network Training via Boundary Example Mining

NEURIPS 2021arXiv

citations

GSD: View-Guided Gaussian Splatting Diffusion for 3D Reconstruction

ECCV 2024arXiv

citations

ViP: A Differentially Private Foundation Model for Computer Vision

ICML 2024arXiv

citations

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

NEURIPS 2023arXiv

citations

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

NEURIPS 2021arXiv

citations

MotionMix: Weakly-Supervised Diffusion for Controllable Motion Generation

AAAI 2024arXiv

citations

Differentially Private Representation Learning via Image Captioning

ICML 2024arXiv

citations

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

ICLR 2025arXiv

citations

Generating Diverse and Natural 3D Human Motions From Text

CVPR 2022

citations

Chuan Guo

papers (17)

ReAct: Out-of-distribution Detection With Rectified Activations

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

AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs

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

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

Online Adaptation to Label Distribution Shift

InterMask: 3D Human Interaction Generation via Collaborative Masked Modeling

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

BulletTrain: Accelerating Robust Neural Network Training via Boundary Example Mining

GSD: View-Guided Gaussian Splatting Diffusion for 3D Reconstruction

ViP: A Differentially Private Foundation Model for Computer Vision

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

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

MotionMix: Weakly-Supervised Diffusion for Controllable Motion Generation

Differentially Private Representation Learning via Image Captioning

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

Generating Diverse and Natural 3D Human Motions From Text

papers (17)

ReAct: Out-of-distribution Detection With Rectified Activations

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

AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs

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

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

Online Adaptation to Label Distribution Shift

InterMask: 3D Human Interaction Generation via Collaborative Masked Modeling

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

BulletTrain: Accelerating Robust Neural Network Training via Boundary Example Mining

GSD: View-Guided Gaussian Splatting Diffusion for 3D Reconstruction

ViP: A Differentially Private Foundation Model for Computer Vision

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

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

MotionMix: Weakly-Supervised Diffusion for Controllable Motion Generation

Differentially Private Representation Learning via Image Captioning

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

Generating Diverse and Natural 3D Human Motions From Text