Yandong Li

papers

968

total citations

papers (14)

Neural Networks Are More Productive Teachers Than Human Raters: Active Mixup for Data-Efficient Knowledge Distillation From a Blackbox Model

CVPR 2020arXiv

citations

On Model Calibration for Long-Tailed Object Detection and Instance Segmentation

NEURIPS 2021arXiv

citations

MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection

ICCV 2021arXiv

citations

BachGAN: High-Resolution Image Synthesis From Salient Object Layout

CVPR 2020arXiv

citations

Towards Authentic Face Restoration with Iterative Diffusion Models and Beyond

ICCV 2023arXiv

citations

Perturbing Attention Gives You More Bang for the Buck: Subtle Imaging Perturbations That Efficiently Fool Customized Diffusion Models

CVPR 2024arXiv

citations

Scaling Inference Time Compute for Diffusion Models

CVPR 2025

citations

Rethinking Deep Face Restoration

CVPR 2022

citations

Train-Once-for-All Personalization

CVPR 2023

citations

Yandong Li

papers (14)

MoViNets: Mobile Video Networks for Efficient Video Recognition

Subject-driven Text-to-Image Generation via Apprenticeship Learning

Instruct-Imagen: Image Generation with Multi-modal Instruction

Improving Object Detection with Selective Self-Supervised Self-Training

Ranking Neural Checkpoints

Neural Networks Are More Productive Teachers Than Human Raters: Active Mixup for Data-Efficient Knowledge Distillation From a Blackbox Model

On Model Calibration for Long-Tailed Object Detection and Instance Segmentation

MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection

BachGAN: High-Resolution Image Synthesis From Salient Object Layout

Towards Authentic Face Restoration with Iterative Diffusion Models and Beyond

Perturbing Attention Gives You More Bang for the Buck: Subtle Imaging Perturbations That Efficiently Fool Customized Diffusion Models

Scaling Inference Time Compute for Diffusion Models

Rethinking Deep Face Restoration

Train-Once-for-All Personalization

papers (14)

MoViNets: Mobile Video Networks for Efficient Video Recognition

Subject-driven Text-to-Image Generation via Apprenticeship Learning

Instruct-Imagen: Image Generation with Multi-modal Instruction

Improving Object Detection with Selective Self-Supervised Self-Training

Ranking Neural Checkpoints

Neural Networks Are More Productive Teachers Than Human Raters: Active Mixup for Data-Efficient Knowledge Distillation From a Blackbox Model

On Model Calibration for Long-Tailed Object Detection and Instance Segmentation

MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection

BachGAN: High-Resolution Image Synthesis From Salient Object Layout

Towards Authentic Face Restoration with Iterative Diffusion Models and Beyond

Perturbing Attention Gives You More Bang for the Buck: Subtle Imaging Perturbations That Efficiently Fool Customized Diffusion Models

Scaling Inference Time Compute for Diffusion Models

Rethinking Deep Face Restoration

Train-Once-for-All Personalization