Picture for Hai Zhao

Hai Zhao

Department of Computer Science and Engineering, Shanghai Jiao Tong University, Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering, Shanghai Jiao Tong University, MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University

VHASR: A Multimodal Speech Recognition System With Vision Hotwords

Add code
Oct 01, 2024
Figure 1 for VHASR: A Multimodal Speech Recognition System With Vision Hotwords
Figure 2 for VHASR: A Multimodal Speech Recognition System With Vision Hotwords
Figure 3 for VHASR: A Multimodal Speech Recognition System With Vision Hotwords
Figure 4 for VHASR: A Multimodal Speech Recognition System With Vision Hotwords
Viaarxiv icon

Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models

Add code
Sep 30, 2024
Figure 1 for Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models
Figure 2 for Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models
Figure 3 for Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models
Figure 4 for Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models
Viaarxiv icon

A Coin Has Two Sides: A Novel Detector-Corrector Framework for Chinese Spelling Correction

Add code
Sep 06, 2024
Figure 1 for A Coin Has Two Sides: A Novel Detector-Corrector Framework for Chinese Spelling Correction
Figure 2 for A Coin Has Two Sides: A Novel Detector-Corrector Framework for Chinese Spelling Correction
Figure 3 for A Coin Has Two Sides: A Novel Detector-Corrector Framework for Chinese Spelling Correction
Figure 4 for A Coin Has Two Sides: A Novel Detector-Corrector Framework for Chinese Spelling Correction
Viaarxiv icon

Nothing in Excess: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering

Add code
Aug 21, 2024
Viaarxiv icon

MEGen: Generative Backdoor in Large Language Models via Model Editing

Add code
Aug 20, 2024
Figure 1 for MEGen: Generative Backdoor in Large Language Models via Model Editing
Figure 2 for MEGen: Generative Backdoor in Large Language Models via Model Editing
Figure 3 for MEGen: Generative Backdoor in Large Language Models via Model Editing
Figure 4 for MEGen: Generative Backdoor in Large Language Models via Model Editing
Viaarxiv icon

Self-Directed Turing Test for Large Language Models

Add code
Aug 19, 2024
Figure 1 for Self-Directed Turing Test for Large Language Models
Figure 2 for Self-Directed Turing Test for Large Language Models
Figure 3 for Self-Directed Turing Test for Large Language Models
Figure 4 for Self-Directed Turing Test for Large Language Models
Viaarxiv icon

BatGPT-Chem: A Foundation Large Model For Retrosynthesis Prediction

Add code
Aug 19, 2024
Figure 1 for BatGPT-Chem: A Foundation Large Model For Retrosynthesis Prediction
Figure 2 for BatGPT-Chem: A Foundation Large Model For Retrosynthesis Prediction
Figure 3 for BatGPT-Chem: A Foundation Large Model For Retrosynthesis Prediction
Figure 4 for BatGPT-Chem: A Foundation Large Model For Retrosynthesis Prediction
Viaarxiv icon

Game Development as Human-LLM Interaction

Add code
Aug 18, 2024
Viaarxiv icon

Scaling Virtual World with Delta-Engine

Add code
Aug 11, 2024
Viaarxiv icon

Caution for the Environment: Multimodal Agents are Susceptible to Environmental Distractions

Add code
Aug 05, 2024
Figure 1 for Caution for the Environment: Multimodal Agents are Susceptible to Environmental Distractions
Figure 2 for Caution for the Environment: Multimodal Agents are Susceptible to Environmental Distractions
Figure 3 for Caution for the Environment: Multimodal Agents are Susceptible to Environmental Distractions
Figure 4 for Caution for the Environment: Multimodal Agents are Susceptible to Environmental Distractions
Viaarxiv icon