Picture for Zhen Han

Zhen Han

PERFT: Parameter-Efficient Routed Fine-Tuning for Mixture-of-Expert Model

Add code
Nov 12, 2024
Figure 1 for PERFT: Parameter-Efficient Routed Fine-Tuning for Mixture-of-Expert Model
Figure 2 for PERFT: Parameter-Efficient Routed Fine-Tuning for Mixture-of-Expert Model
Figure 3 for PERFT: Parameter-Efficient Routed Fine-Tuning for Mixture-of-Expert Model
Figure 4 for PERFT: Parameter-Efficient Routed Fine-Tuning for Mixture-of-Expert Model
Viaarxiv icon

Visual Question Decomposition on Multimodal Large Language Models

Add code
Sep 28, 2024
Figure 1 for Visual Question Decomposition on Multimodal Large Language Models
Figure 2 for Visual Question Decomposition on Multimodal Large Language Models
Figure 3 for Visual Question Decomposition on Multimodal Large Language Models
Figure 4 for Visual Question Decomposition on Multimodal Large Language Models
Viaarxiv icon

WebPilot: A Versatile and Autonomous Multi-Agent System for Web Task Execution with Strategic Exploration

Add code
Aug 28, 2024
Viaarxiv icon

IDRetracor: Towards Visual Forensics Against Malicious Face Swapping

Add code
Aug 13, 2024
Figure 1 for IDRetracor: Towards Visual Forensics Against Malicious Face Swapping
Figure 2 for IDRetracor: Towards Visual Forensics Against Malicious Face Swapping
Figure 3 for IDRetracor: Towards Visual Forensics Against Malicious Face Swapping
Figure 4 for IDRetracor: Towards Visual Forensics Against Malicious Face Swapping
Viaarxiv icon

A rapid approach to urban traffic noise mapping with a generative adversarial network

Add code
May 21, 2024
Viaarxiv icon

StyleBooth: Image Style Editing with Multimodal Instruction

Add code
Apr 18, 2024
Viaarxiv icon

Red Teaming GPT-4V: Are GPT-4V Safe Against Uni/Multi-Modal Jailbreak Attacks?

Add code
Apr 04, 2024
Figure 1 for Red Teaming GPT-4V: Are GPT-4V Safe Against Uni/Multi-Modal Jailbreak Attacks?
Figure 2 for Red Teaming GPT-4V: Are GPT-4V Safe Against Uni/Multi-Modal Jailbreak Attacks?
Figure 3 for Red Teaming GPT-4V: Are GPT-4V Safe Against Uni/Multi-Modal Jailbreak Attacks?
Figure 4 for Red Teaming GPT-4V: Are GPT-4V Safe Against Uni/Multi-Modal Jailbreak Attacks?
Viaarxiv icon

Locate, Assign, Refine: Taming Customized Image Inpainting with Text-Subject Guidance

Add code
Mar 28, 2024
Viaarxiv icon

Stop Reasoning! When Multimodal LLMs with Chain-of-Thought Reasoning Meets Adversarial Images

Add code
Feb 22, 2024
Figure 1 for Stop Reasoning! When Multimodal LLMs with Chain-of-Thought Reasoning Meets Adversarial Images
Figure 2 for Stop Reasoning! When Multimodal LLMs with Chain-of-Thought Reasoning Meets Adversarial Images
Figure 3 for Stop Reasoning! When Multimodal LLMs with Chain-of-Thought Reasoning Meets Adversarial Images
Figure 4 for Stop Reasoning! When Multimodal LLMs with Chain-of-Thought Reasoning Meets Adversarial Images
Viaarxiv icon

SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editing

Add code
Dec 18, 2023
Viaarxiv icon