Zhaoyang Li

9

Papers

13

Total Citations

Papers (9)

When Should We Prefer State-to-Visual DAgger over Visual Reinforcement Learning?

Unbiased Video Scene Graph Generation via Visual and Semantic Dual Debiasing

Dual-Agent Optimization framework for Cross-Domain Few-Shot Segmentation

ACT as Human: Multimodal Large Language Model Data Annotation with Critical Thinking

Information Bottleneck Disentanglement for Identity Swapping

FaceInpainter: High Fidelity Face Adaptation to Heterogeneous Domains

A Neural Network for Detailed Human Depth Estimation From a Single Image

Open-Unfairness Adversarial Mitigation for Generalized Deepfake Detection

Generalized Few-Shot Point Cloud Segmentation via LLM-Assisted Hyper-Relation Matching