Peng Cui

papers

842

total citations

papers (28)

Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization

CVPR 2023arXiv

citations

Towards Unsupervised Domain Generalization

CVPR 2022arXiv

citations

Calibrated Reliable Regression using Maximum Mean Discrepancy

NEURIPS 2020arXiv

citations

Flatness-Aware Minimization for Domain Generalization

ICCV 2023arXiv

citations

Learning to Select Base Classes for Few-Shot Classification

CVPR 2020arXiv

citations

Adversarial Eigen Attack on Black-Box Models

CVPR 2022arXiv

citations

Rethinking the Evaluation Protocol of Domain Generalization

CVPR 2024arXiv

citations

Learning Sample Difficulty from Pre-trained Models for Reliable Prediction

NEURIPS 2023arXiv

citations

Confidence-based Reliable Learning under Dual Noises

NEURIPS 2022arXiv

citations

Towards Accelerated Model Training via Bayesian Data Selection

NEURIPS 2023arXiv

citations

Geometry-Calibrated DRO: Combating Over-Pessimism with Free Energy Implications

ICML 2024arXiv

citations

Understanding the Generalization of In-Context Learning in Transformers: An Empirical Study

ICLR 2025arXiv

citations

On the Out-Of-Distribution Generalization of Large Multimodal Models

CVPR 2025

citations

Product Ranking for Revenue Maximization with Multiple Purchases

NEURIPS 2022arXiv

citations

ODP-Bench: Benchmarking Out-of-Distribution Performance Prediction

ICCV 2025arXiv

citations

Environment Inference for Learning Generalizable Dynamical System

NEURIPS 2025arXiv

citations

COUNTS: Benchmarking Object Detectors and Multimodal Large Language Models under Distribution Shifts

CVPR 2025arXiv

citations

Going Beyond Static: Understanding Shifts with Time-Series Attribution

ICLR 2025

citations

Integrated Latent Heterogeneity and Invariance Learning in Kernel Space

NEURIPS 2021

citations

Distributionally Robust Optimization with Data Geometry

NEURIPS 2022

citations

Counterfactual Prediction for Bundle Treatment

NEURIPS 2020

citations

Domain-wise Data Acquisition to Improve Performance under Distribution Shift

ICML 2024

citations

On the Need for a Language Describing Distribution Shifts: Illustrations on Tabular Datasets

NEURIPS 2023

citations

Stability Evaluation through Distributional Perturbation Analysis

ICML 2024

citations

Improving Accuracy and Calibration via Differentiated Deep Mutual Learning

CVPR 2025

citations

Peng Cui

papers (28)

Deep Stable Learning for Out-of-Distribution Generalization

NICO++: Towards Better Benchmarking for Domain Generalization

ZIN: When and How to Learn Invariance Without Environment Partition?

Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization

Towards Unsupervised Domain Generalization

Calibrated Reliable Regression using Maximum Mean Discrepancy

Flatness-Aware Minimization for Domain Generalization

Learning to Select Base Classes for Few-Shot Classification

Adversarial Eigen Attack on Black-Box Models

Rethinking the Evaluation Protocol of Domain Generalization

Learning Sample Difficulty from Pre-trained Models for Reliable Prediction

Confidence-based Reliable Learning under Dual Noises

Towards Accelerated Model Training via Bayesian Data Selection

Geometry-Calibrated DRO: Combating Over-Pessimism with Free Energy Implications

Understanding the Generalization of In-Context Learning in Transformers: An Empirical Study

On the Out-Of-Distribution Generalization of Large Multimodal Models

Product Ranking for Revenue Maximization with Multiple Purchases

ODP-Bench: Benchmarking Out-of-Distribution Performance Prediction

Environment Inference for Learning Generalizable Dynamical System

COUNTS: Benchmarking Object Detectors and Multimodal Large Language Models under Distribution Shifts

Going Beyond Static: Understanding Shifts with Time-Series Attribution

Integrated Latent Heterogeneity and Invariance Learning in Kernel Space

Distributionally Robust Optimization with Data Geometry

Counterfactual Prediction for Bundle Treatment

Domain-wise Data Acquisition to Improve Performance under Distribution Shift

On the Need for a Language Describing Distribution Shifts: Illustrations on Tabular Datasets

Stability Evaluation through Distributional Perturbation Analysis

Improving Accuracy and Calibration via Differentiated Deep Mutual Learning

papers (28)

Deep Stable Learning for Out-of-Distribution Generalization

NICO++: Towards Better Benchmarking for Domain Generalization

ZIN: When and How to Learn Invariance Without Environment Partition?

Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization

Towards Unsupervised Domain Generalization

Calibrated Reliable Regression using Maximum Mean Discrepancy

Flatness-Aware Minimization for Domain Generalization

Learning to Select Base Classes for Few-Shot Classification

Adversarial Eigen Attack on Black-Box Models

Rethinking the Evaluation Protocol of Domain Generalization

Learning Sample Difficulty from Pre-trained Models for Reliable Prediction

Confidence-based Reliable Learning under Dual Noises

Towards Accelerated Model Training via Bayesian Data Selection

Geometry-Calibrated DRO: Combating Over-Pessimism with Free Energy Implications

Understanding the Generalization of In-Context Learning in Transformers: An Empirical Study

On the Out-Of-Distribution Generalization of Large Multimodal Models

Product Ranking for Revenue Maximization with Multiple Purchases

ODP-Bench: Benchmarking Out-of-Distribution Performance Prediction

Environment Inference for Learning Generalizable Dynamical System

COUNTS: Benchmarking Object Detectors and Multimodal Large Language Models under Distribution Shifts

Going Beyond Static: Understanding Shifts with Time-Series Attribution

Integrated Latent Heterogeneity and Invariance Learning in Kernel Space

Distributionally Robust Optimization with Data Geometry

Counterfactual Prediction for Bundle Treatment

Domain-wise Data Acquisition to Improve Performance under Distribution Shift

On the Need for a Language Describing Distribution Shifts: Illustrations on Tabular Datasets

Stability Evaluation through Distributional Perturbation Analysis

Improving Accuracy and Calibration via Differentiated Deep Mutual Learning