Alert button

"Text": models, code, and papers
Alert button

Step by Step Loss Goes Very Far: Multi-Step Quantization for Adversarial Text Attacks

Feb 10, 2023
Piotr Gaiński, Klaudia Bałazy

Figure 1 for Step by Step Loss Goes Very Far: Multi-Step Quantization for Adversarial Text Attacks
Figure 2 for Step by Step Loss Goes Very Far: Multi-Step Quantization for Adversarial Text Attacks
Figure 3 for Step by Step Loss Goes Very Far: Multi-Step Quantization for Adversarial Text Attacks
Figure 4 for Step by Step Loss Goes Very Far: Multi-Step Quantization for Adversarial Text Attacks
Viaarxiv icon

Application-Agnostic Language Modeling for On-Device ASR

May 16, 2023
Markus Nußbaum-Thom, Lyan Verwimp, Youssef Oualil

Figure 1 for Application-Agnostic Language Modeling for On-Device ASR
Figure 2 for Application-Agnostic Language Modeling for On-Device ASR
Figure 3 for Application-Agnostic Language Modeling for On-Device ASR
Figure 4 for Application-Agnostic Language Modeling for On-Device ASR
Viaarxiv icon

3D Open-vocabulary Segmentation with Foundation Models

May 24, 2023
Kunhao Liu, Fangneng Zhan, Jiahui Zhang, Muyu Xu, Yingchen Yu, Abdulmotaleb El Saddik, Christian Theobalt, Eric Xing, Shijian Lu

Figure 1 for 3D Open-vocabulary Segmentation with Foundation Models
Figure 2 for 3D Open-vocabulary Segmentation with Foundation Models
Figure 3 for 3D Open-vocabulary Segmentation with Foundation Models
Figure 4 for 3D Open-vocabulary Segmentation with Foundation Models
Viaarxiv icon

Instruct2Act: Mapping Multi-modality Instructions to Robotic Actions with Large Language Model

May 24, 2023
Siyuan Huang, Zhengkai Jiang, Hao Dong, Yu Qiao, Peng Gao, Hongsheng Li

Figure 1 for Instruct2Act: Mapping Multi-modality Instructions to Robotic Actions with Large Language Model
Figure 2 for Instruct2Act: Mapping Multi-modality Instructions to Robotic Actions with Large Language Model
Figure 3 for Instruct2Act: Mapping Multi-modality Instructions to Robotic Actions with Large Language Model
Figure 4 for Instruct2Act: Mapping Multi-modality Instructions to Robotic Actions with Large Language Model
Viaarxiv icon

AV-TranSpeech: Audio-Visual Robust Speech-to-Speech Translation

May 24, 2023
Rongjie Huang, Huadai Liu, Xize Cheng, Yi Ren, Linjun Li, Zhenhui Ye, Jinzheng He, Lichao Zhang, Jinglin Liu, Xiang Yin, Zhou Zhao

Figure 1 for AV-TranSpeech: Audio-Visual Robust Speech-to-Speech Translation
Figure 2 for AV-TranSpeech: Audio-Visual Robust Speech-to-Speech Translation
Figure 3 for AV-TranSpeech: Audio-Visual Robust Speech-to-Speech Translation
Figure 4 for AV-TranSpeech: Audio-Visual Robust Speech-to-Speech Translation
Viaarxiv icon

ChatFace: Chat-Guided Real Face Editing via Diffusion Latent Space Manipulation

May 24, 2023
Dongxu Yue, Qin Guo, Munan Ning, Jiaxi Cui, Yuesheng Zhu, Li Yuan

Figure 1 for ChatFace: Chat-Guided Real Face Editing via Diffusion Latent Space Manipulation
Figure 2 for ChatFace: Chat-Guided Real Face Editing via Diffusion Latent Space Manipulation
Figure 3 for ChatFace: Chat-Guided Real Face Editing via Diffusion Latent Space Manipulation
Figure 4 for ChatFace: Chat-Guided Real Face Editing via Diffusion Latent Space Manipulation
Viaarxiv icon

In-Context Impersonation Reveals Large Language Models' Strengths and Biases

May 24, 2023
Leonard Salewski, Stephan Alaniz, Isabel Rio-Torto, Eric Schulz, Zeynep Akata

Figure 1 for In-Context Impersonation Reveals Large Language Models' Strengths and Biases
Figure 2 for In-Context Impersonation Reveals Large Language Models' Strengths and Biases
Figure 3 for In-Context Impersonation Reveals Large Language Models' Strengths and Biases
Figure 4 for In-Context Impersonation Reveals Large Language Models' Strengths and Biases
Viaarxiv icon

Centering the Margins: Outlier-Based Identification of Harmed Populations in Toxicity Detection

May 24, 2023
Vyoma Raman, Eve Fleisig, Dan Klein

Figure 1 for Centering the Margins: Outlier-Based Identification of Harmed Populations in Toxicity Detection
Figure 2 for Centering the Margins: Outlier-Based Identification of Harmed Populations in Toxicity Detection
Figure 3 for Centering the Margins: Outlier-Based Identification of Harmed Populations in Toxicity Detection
Figure 4 for Centering the Margins: Outlier-Based Identification of Harmed Populations in Toxicity Detection
Viaarxiv icon

TACR: A Table-alignment-based Cell-selection and Reasoning Model for Hybrid Question-Answering

May 24, 2023
Jian Wu, Yicheng Xu, Yan Gao, Jian-Guang Lou, Börje F. Karlsson, Manabu Okumura

Figure 1 for TACR: A Table-alignment-based Cell-selection and Reasoning Model for Hybrid Question-Answering
Figure 2 for TACR: A Table-alignment-based Cell-selection and Reasoning Model for Hybrid Question-Answering
Figure 3 for TACR: A Table-alignment-based Cell-selection and Reasoning Model for Hybrid Question-Answering
Figure 4 for TACR: A Table-alignment-based Cell-selection and Reasoning Model for Hybrid Question-Answering
Viaarxiv icon

NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers

May 04, 2023
Kai Shen, Zeqian Ju, Xu Tan, Yanqing Liu, Yichong Leng, Lei He, Tao Qin, Sheng Zhao, Jiang Bian

Figure 1 for NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers
Figure 2 for NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers
Figure 3 for NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers
Figure 4 for NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers
Viaarxiv icon