Kaiyang Zhou

14

Papers

3

Total Citations

Papers (14)

Bootstrapping Grounded Chain-of-Thought in Multimodal LLMs for Data-Efficient Model Adaptation

Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models

Prompting Vision Foundation Models for Pathology Image Analysis

Open-Vocabulary Calibration for Fine-tuned CLIP

Conditional Prompt Learning for Vision-Language Models

Panoptic Video Scene Graph Generation

Omni-Scale Feature Learning for Person Re-Identification

Energy-Based Open-World Uncertainty Modeling for Confidence Calibration

Learning to Generate Novel Domains for Domain Generalization

Open-Vocabulary DETR with Conditional Matching

Panoptic Scene Graph Generation

OpenOOD: Benchmarking Generalized Out-of-Distribution Detection

What Makes Good Examples for Visual In-Context Learning?

4D Panoptic Scene Graph Generation