Picture for Luu Anh Tuan

Luu Anh Tuan

A Survey of Backdoor Attacks and Defenses on Large Language Models: Implications for Security Measures

Jun 10, 2024
Viaarxiv icon

Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives

Add code
Jun 09, 2024
Viaarxiv icon

SemRoDe: Macro Adversarial Training to Learn Representations That are Robust to Word-Level Attacks

Add code
Mar 27, 2024
Figure 1 for SemRoDe: Macro Adversarial Training to Learn Representations That are Robust to Word-Level Attacks
Figure 2 for SemRoDe: Macro Adversarial Training to Learn Representations That are Robust to Word-Level Attacks
Figure 3 for SemRoDe: Macro Adversarial Training to Learn Representations That are Robust to Word-Level Attacks
Figure 4 for SemRoDe: Macro Adversarial Training to Learn Representations That are Robust to Word-Level Attacks
Viaarxiv icon

ToXCL: A Unified Framework for Toxic Speech Detection and Explanation

Add code
Mar 25, 2024
Viaarxiv icon

Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning

Add code
Feb 25, 2024
Viaarxiv icon

Universal Vulnerabilities in Large Language Models: In-context Learning Backdoor Attacks

Add code
Jan 20, 2024
Figure 1 for Universal Vulnerabilities in Large Language Models: In-context Learning Backdoor Attacks
Figure 2 for Universal Vulnerabilities in Large Language Models: In-context Learning Backdoor Attacks
Figure 3 for Universal Vulnerabilities in Large Language Models: In-context Learning Backdoor Attacks
Figure 4 for Universal Vulnerabilities in Large Language Models: In-context Learning Backdoor Attacks
Viaarxiv icon

READ-PVLA: Recurrent Adapter with Partial Video-Language Alignment for Parameter-Efficient Transfer Learning in Low-Resource Video-Language Modeling

Dec 12, 2023
Figure 1 for READ-PVLA: Recurrent Adapter with Partial Video-Language Alignment for Parameter-Efficient Transfer Learning in Low-Resource Video-Language Modeling
Figure 2 for READ-PVLA: Recurrent Adapter with Partial Video-Language Alignment for Parameter-Efficient Transfer Learning in Low-Resource Video-Language Modeling
Figure 3 for READ-PVLA: Recurrent Adapter with Partial Video-Language Alignment for Parameter-Efficient Transfer Learning in Low-Resource Video-Language Modeling
Figure 4 for READ-PVLA: Recurrent Adapter with Partial Video-Language Alignment for Parameter-Efficient Transfer Learning in Low-Resource Video-Language Modeling
Viaarxiv icon

DemaFormer: Damped Exponential Moving Average Transformer with Energy-Based Modeling for Temporal Language Grounding

Dec 05, 2023
Figure 1 for DemaFormer: Damped Exponential Moving Average Transformer with Energy-Based Modeling for Temporal Language Grounding
Figure 2 for DemaFormer: Damped Exponential Moving Average Transformer with Energy-Based Modeling for Temporal Language Grounding
Figure 3 for DemaFormer: Damped Exponential Moving Average Transformer with Energy-Based Modeling for Temporal Language Grounding
Figure 4 for DemaFormer: Damped Exponential Moving Average Transformer with Energy-Based Modeling for Temporal Language Grounding
Viaarxiv icon

Improving Multimodal Sentiment Analysis: Supervised Angular Margin-based Contrastive Learning for Enhanced Fusion Representation

Dec 04, 2023
Figure 1 for Improving Multimodal Sentiment Analysis: Supervised Angular Margin-based Contrastive Learning for Enhanced Fusion Representation
Figure 2 for Improving Multimodal Sentiment Analysis: Supervised Angular Margin-based Contrastive Learning for Enhanced Fusion Representation
Figure 3 for Improving Multimodal Sentiment Analysis: Supervised Angular Margin-based Contrastive Learning for Enhanced Fusion Representation
Figure 4 for Improving Multimodal Sentiment Analysis: Supervised Angular Margin-based Contrastive Learning for Enhanced Fusion Representation
Viaarxiv icon

Expand BERT Representation with Visual Information via Grounded Language Learning with Multimodal Partial Alignment

Dec 04, 2023
Figure 1 for Expand BERT Representation with Visual Information via Grounded Language Learning with Multimodal Partial Alignment
Figure 2 for Expand BERT Representation with Visual Information via Grounded Language Learning with Multimodal Partial Alignment
Figure 3 for Expand BERT Representation with Visual Information via Grounded Language Learning with Multimodal Partial Alignment
Figure 4 for Expand BERT Representation with Visual Information via Grounded Language Learning with Multimodal Partial Alignment
Viaarxiv icon