Peng Sun

22

Papers

12

Total Citations

Papers (22)

GIFT: Unlocking Full Potential of Labels in Distilled Dataset at Near-zero Cost

DSRC: Learning Density-Insensitive and Semantic-Aware Collaborative Representation Against Corruptions

Unlocking the Power of LSTM for Long Term Time Series Forecasting

A Dual Stealthy Backdoor: From Both Spatial and Frequency Perspectives

ERMVP: Communication-Efficient and Collaboration-Robust Multi-Vehicle Perception in Challenging Environments

Byzantine-robust Decentralized Federated Learning via Dual-domain Clustering and Trust Bootstrapping

On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm

Energy-based Backdoor Defense without Task-Specific Samples and Model Retraining

Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning

Tagging Like Humans: Diverse and Distinct Image Annotation

Graph-Guided Architecture Search for Real-Time Semantic Segmentation

Deep RGB-D Saliency Detection With Depth-Sensitive Attention and Automatic Multi-Modal Fusion

Towards Transferable Targeted Adversarial Examples

Privacy-Preserving Adversarial Facial Features

Event-Based Frame Interpolation With Ad-Hoc Deblurring

Spatio-Temporal Domain Awareness for Multi-Agent Collaborative Perception

Event-Based Fusion for Motion Deblurring with Cross-Modal Attention

Bridging the Gap Between Ideal and Real-world Evaluation: Benchmarking AI-Generated Image Detection in Challenging Scenarios

Towards Annotation-Free Evaluation: KPAScore for Human Keypoint Detection

End-to-end Active Object Tracking via Reinforcement Learning

An Algorithmic Framework of Variable Metric Over-Relaxed Hybrid Proximal Extra-Gradient Method

Grid-Wise Control for Multi-Agent Reinforcement Learning in Video Game AI