Picture for Zihan Zhong

Zihan Zhong

AutoGluon-Multimodal (AutoMM): Supercharging Multimodal AutoML with Foundation Models

Add code
Apr 30, 2024
Viaarxiv icon

Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything Model

Add code
Jan 31, 2024
Viaarxiv icon

UniBoost: Unsupervised Unimodal Pre-training for Boosting Zero-shot Vision-Language Tasks

Add code
Jun 07, 2023
Viaarxiv icon

Tailoring Instructions to Student's Learning Levels Boosts Knowledge Distillation

Add code
May 16, 2023
Figure 1 for Tailoring Instructions to Student's Learning Levels Boosts Knowledge Distillation
Figure 2 for Tailoring Instructions to Student's Learning Levels Boosts Knowledge Distillation
Figure 3 for Tailoring Instructions to Student's Learning Levels Boosts Knowledge Distillation
Figure 4 for Tailoring Instructions to Student's Learning Levels Boosts Knowledge Distillation
Viaarxiv icon

Towards Arbitrary Text-driven Image Manipulation via Space Alignment

Add code
Jan 25, 2023
Viaarxiv icon