Picture for Yifan Li

Yifan Li

"Glue pizza and eat rocks" -- Exploiting Vulnerabilities in Retrieval-Augmented Generative Models

Add code
Jun 26, 2024
Viaarxiv icon

KnobTree: Intelligent Database Parameter Configuration via Explainable Reinforcement Learning

Add code
Jun 21, 2024
Viaarxiv icon

Towards Event-oriented Long Video Understanding

Add code
Jun 20, 2024
Figure 1 for Towards Event-oriented Long Video Understanding
Figure 2 for Towards Event-oriented Long Video Understanding
Figure 3 for Towards Event-oriented Long Video Understanding
Figure 4 for Towards Event-oriented Long Video Understanding
Viaarxiv icon

Machine learning-based Near-field Emitter Localization via Grouped Hybrid Analog and Digital Massive MIMO Receive Array

Add code
Jun 14, 2024
Viaarxiv icon

TacShade A New 3D-printed Soft Optical Tactile Sensor Based on Light, Shadow and Greyscale for Shape Reconstruction

Add code
Jun 01, 2024
Figure 1 for TacShade A New 3D-printed Soft Optical Tactile Sensor Based on Light, Shadow and Greyscale for Shape Reconstruction
Figure 2 for TacShade A New 3D-printed Soft Optical Tactile Sensor Based on Light, Shadow and Greyscale for Shape Reconstruction
Figure 3 for TacShade A New 3D-printed Soft Optical Tactile Sensor Based on Light, Shadow and Greyscale for Shape Reconstruction
Figure 4 for TacShade A New 3D-printed Soft Optical Tactile Sensor Based on Light, Shadow and Greyscale for Shape Reconstruction
Viaarxiv icon

Facial Affective Behavior Analysis with Instruction Tuning

Add code
Apr 07, 2024
Figure 1 for Facial Affective Behavior Analysis with Instruction Tuning
Figure 2 for Facial Affective Behavior Analysis with Instruction Tuning
Figure 3 for Facial Affective Behavior Analysis with Instruction Tuning
Figure 4 for Facial Affective Behavior Analysis with Instruction Tuning
Viaarxiv icon

Weakly-Supervised 3D Scene Graph Generation via Visual-Linguistic Assisted Pseudo-labeling

Add code
Apr 03, 2024
Figure 1 for Weakly-Supervised 3D Scene Graph Generation via Visual-Linguistic Assisted Pseudo-labeling
Figure 2 for Weakly-Supervised 3D Scene Graph Generation via Visual-Linguistic Assisted Pseudo-labeling
Figure 3 for Weakly-Supervised 3D Scene Graph Generation via Visual-Linguistic Assisted Pseudo-labeling
Figure 4 for Weakly-Supervised 3D Scene Graph Generation via Visual-Linguistic Assisted Pseudo-labeling
Viaarxiv icon

Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

Add code
Mar 14, 2024
Figure 1 for Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models
Figure 2 for Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models
Figure 3 for Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models
Figure 4 for Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models
Viaarxiv icon

The Wolf Within: Covert Injection of Malice into MLLM Societies via an MLLM Operative

Add code
Feb 20, 2024
Figure 1 for The Wolf Within: Covert Injection of Malice into MLLM Societies via an MLLM Operative
Figure 2 for The Wolf Within: Covert Injection of Malice into MLLM Societies via an MLLM Operative
Figure 3 for The Wolf Within: Covert Injection of Malice into MLLM Societies via an MLLM Operative
Figure 4 for The Wolf Within: Covert Injection of Malice into MLLM Societies via an MLLM Operative
Viaarxiv icon

Repositioning the Subject within Image

Add code
Jan 30, 2024
Figure 1 for Repositioning the Subject within Image
Figure 2 for Repositioning the Subject within Image
Figure 3 for Repositioning the Subject within Image
Figure 4 for Repositioning the Subject within Image
Viaarxiv icon