Picture for Ziqing Yang

Ziqing Yang

SOS! Soft Prompt Attack Against Open-Source Large Language Models

Add code
Jul 03, 2024
Viaarxiv icon

Comprehensive Assessment of Jailbreak Attacks Against LLMs

Add code
Feb 08, 2024
Viaarxiv icon

SecurityNet: Assessing Machine Learning Vulnerabilities on Public Models

Add code
Oct 19, 2023
Figure 1 for SecurityNet: Assessing Machine Learning Vulnerabilities on Public Models
Figure 2 for SecurityNet: Assessing Machine Learning Vulnerabilities on Public Models
Figure 3 for SecurityNet: Assessing Machine Learning Vulnerabilities on Public Models
Figure 4 for SecurityNet: Assessing Machine Learning Vulnerabilities on Public Models
Viaarxiv icon

IDOL: Indicator-oriented Logic Pre-training for Logical Reasoning

Add code
Jun 27, 2023
Figure 1 for IDOL: Indicator-oriented Logic Pre-training for Logical Reasoning
Figure 2 for IDOL: Indicator-oriented Logic Pre-training for Logical Reasoning
Figure 3 for IDOL: Indicator-oriented Logic Pre-training for Logical Reasoning
Figure 4 for IDOL: Indicator-oriented Logic Pre-training for Logical Reasoning
Viaarxiv icon

Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca

Add code
Apr 17, 2023
Figure 1 for Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca
Figure 2 for Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca
Figure 3 for Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca
Figure 4 for Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca
Viaarxiv icon

MiniRBT: A Two-stage Distilled Small Chinese Pre-trained Model

Add code
Apr 03, 2023
Figure 1 for MiniRBT: A Two-stage Distilled Small Chinese Pre-trained Model
Figure 2 for MiniRBT: A Two-stage Distilled Small Chinese Pre-trained Model
Figure 3 for MiniRBT: A Two-stage Distilled Small Chinese Pre-trained Model
Figure 4 for MiniRBT: A Two-stage Distilled Small Chinese Pre-trained Model
Viaarxiv icon

From Visual Prompt Learning to Zero-Shot Transfer: Mapping Is All You Need

Add code
Mar 09, 2023
Figure 1 for From Visual Prompt Learning to Zero-Shot Transfer: Mapping Is All You Need
Figure 2 for From Visual Prompt Learning to Zero-Shot Transfer: Mapping Is All You Need
Figure 3 for From Visual Prompt Learning to Zero-Shot Transfer: Mapping Is All You Need
Figure 4 for From Visual Prompt Learning to Zero-Shot Transfer: Mapping Is All You Need
Viaarxiv icon

Gradient-based Intra-attention Pruning on Pre-trained Language Models

Add code
Dec 15, 2022
Figure 1 for Gradient-based Intra-attention Pruning on Pre-trained Language Models
Figure 2 for Gradient-based Intra-attention Pruning on Pre-trained Language Models
Figure 3 for Gradient-based Intra-attention Pruning on Pre-trained Language Models
Figure 4 for Gradient-based Intra-attention Pruning on Pre-trained Language Models
Viaarxiv icon

Data Poisoning Attacks Against Multimodal Encoders

Add code
Sep 30, 2022
Figure 1 for Data Poisoning Attacks Against Multimodal Encoders
Figure 2 for Data Poisoning Attacks Against Multimodal Encoders
Figure 3 for Data Poisoning Attacks Against Multimodal Encoders
Figure 4 for Data Poisoning Attacks Against Multimodal Encoders
Viaarxiv icon

HIT at SemEval-2022 Task 2: Pre-trained Language Model for Idioms Detection

Add code
Apr 13, 2022
Figure 1 for HIT at SemEval-2022 Task 2: Pre-trained Language Model for Idioms Detection
Figure 2 for HIT at SemEval-2022 Task 2: Pre-trained Language Model for Idioms Detection
Figure 3 for HIT at SemEval-2022 Task 2: Pre-trained Language Model for Idioms Detection
Figure 4 for HIT at SemEval-2022 Task 2: Pre-trained Language Model for Idioms Detection
Viaarxiv icon