Cairong Zhao

Bootstrapping MLLM for Weakly‑Supervised Class‑Agnostic Object Counting

Asynchronous Matching with Dynamic Sampling for Multimodal Dataset Distillation

Exploring Interpretability for Visual Prompt Tuning with Cross-layer Concepts

CharacterShot: Controllable and Consistent 4D Character Animation

Joint Adaptation of Uni-modal Foundation Models for Multi-modal Alzheimer's Disease Diagnosis

Trade in Minutes! Rationality-Driven Agentic System for Quantitative Financial Trading

Cross-Batch Gradient Consistency for Adaptive Loss Balancing in Knowledge Distillation

Uni$^2$Det: Unified and Universal Framework for Prompt-Guided Multi-dataset 3D Detection

FaceShot: Bring Any Character into Life

StyleShot: A snapshot on any style