Picture for Xiangming Gu

Xiangming Gu

When Attention Sink Emerges in Language Models: An Empirical View

Add code
Oct 14, 2024
Viaarxiv icon

On Calibration of LLM-based Guard Models for Reliable Content Moderation

Add code
Oct 14, 2024
Viaarxiv icon

Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast

Add code
Feb 13, 2024
Viaarxiv icon

On Memorization in Diffusion Models

Add code
Oct 04, 2023
Viaarxiv icon

Elucidate Gender Fairness in Singing Voice Transcription

Add code
Aug 05, 2023
Viaarxiv icon

Deep Audio-Visual Singing Voice Transcription based on Self-Supervised Learning Models

Add code
Apr 24, 2023
Viaarxiv icon

Towards Transfer Learning of wav2vec 2.0 for Automatic Lyric Transcription

Add code
Jul 20, 2022
Figure 1 for Towards Transfer Learning of wav2vec 2.0 for Automatic Lyric Transcription
Figure 2 for Towards Transfer Learning of wav2vec 2.0 for Automatic Lyric Transcription
Figure 3 for Towards Transfer Learning of wav2vec 2.0 for Automatic Lyric Transcription
Figure 4 for Towards Transfer Learning of wav2vec 2.0 for Automatic Lyric Transcription
Viaarxiv icon

MM-ALT: A Multimodal Automatic Lyric Transcription System

Add code
Jul 13, 2022
Figure 1 for MM-ALT: A Multimodal Automatic Lyric Transcription System
Figure 2 for MM-ALT: A Multimodal Automatic Lyric Transcription System
Figure 3 for MM-ALT: A Multimodal Automatic Lyric Transcription System
Figure 4 for MM-ALT: A Multimodal Automatic Lyric Transcription System
Viaarxiv icon

Distilling a Deep Neural Network into a Takagi-Sugeno-Kang Fuzzy Inference System

Add code
Oct 10, 2020
Figure 1 for Distilling a Deep Neural Network into a Takagi-Sugeno-Kang Fuzzy Inference System
Figure 2 for Distilling a Deep Neural Network into a Takagi-Sugeno-Kang Fuzzy Inference System
Figure 3 for Distilling a Deep Neural Network into a Takagi-Sugeno-Kang Fuzzy Inference System
Figure 4 for Distilling a Deep Neural Network into a Takagi-Sugeno-Kang Fuzzy Inference System
Viaarxiv icon