Alert button
Picture for Florian Metze

Florian Metze

Alert button

Error-aware Quantization through Noise Tempering

Dec 11, 2022
Zheng Wang, Juncheng B Li, Shuhui Qu, Florian Metze, Emma Strubell

Figure 1 for Error-aware Quantization through Noise Tempering
Figure 2 for Error-aware Quantization through Noise Tempering
Figure 3 for Error-aware Quantization through Noise Tempering
Figure 4 for Error-aware Quantization through Noise Tempering
Viaarxiv icon

Normalized Contrastive Learning for Text-Video Retrieval

Nov 30, 2022
Yookoon Park, Mahmoud Azab, Bo Xiong, Seungwhan Moon, Florian Metze, Gourab Kundu, Kirmani Ahmed

Figure 1 for Normalized Contrastive Learning for Text-Video Retrieval
Figure 2 for Normalized Contrastive Learning for Text-Video Retrieval
Figure 3 for Normalized Contrastive Learning for Text-Video Retrieval
Figure 4 for Normalized Contrastive Learning for Text-Video Retrieval
Viaarxiv icon

Token-level Sequence Labeling for Spoken Language Understanding using Compositional End-to-End Models

Oct 27, 2022
Siddhant Arora, Siddharth Dalmia, Brian Yan, Florian Metze, Alan W Black, Shinji Watanabe

Figure 1 for Token-level Sequence Labeling for Spoken Language Understanding using Compositional End-to-End Models
Figure 2 for Token-level Sequence Labeling for Spoken Language Understanding using Compositional End-to-End Models
Figure 3 for Token-level Sequence Labeling for Spoken Language Understanding using Compositional End-to-End Models
Figure 4 for Token-level Sequence Labeling for Spoken Language Understanding using Compositional End-to-End Models
Viaarxiv icon

SQuAT: Sharpness- and Quantization-Aware Training for BERT

Oct 13, 2022
Zheng Wang, Juncheng B Li, Shuhui Qu, Florian Metze, Emma Strubell

Figure 1 for SQuAT: Sharpness- and Quantization-Aware Training for BERT
Figure 2 for SQuAT: Sharpness- and Quantization-Aware Training for BERT
Figure 3 for SQuAT: Sharpness- and Quantization-Aware Training for BERT
Figure 4 for SQuAT: Sharpness- and Quantization-Aware Training for BERT
Viaarxiv icon

CTC Alignments Improve Autoregressive Translation

Oct 11, 2022
Brian Yan, Siddharth Dalmia, Yosuke Higuchi, Graham Neubig, Florian Metze, Alan W Black, Shinji Watanabe

Figure 1 for CTC Alignments Improve Autoregressive Translation
Figure 2 for CTC Alignments Improve Autoregressive Translation
Figure 3 for CTC Alignments Improve Autoregressive Translation
Figure 4 for CTC Alignments Improve Autoregressive Translation
Viaarxiv icon

ASR2K: Speech Recognition for Around 2000 Languages without Audio

Sep 06, 2022
Xinjian Li, Florian Metze, David R Mortensen, Alan W Black, Shinji Watanabe

Figure 1 for ASR2K: Speech Recognition for Around 2000 Languages without Audio
Figure 2 for ASR2K: Speech Recognition for Around 2000 Languages without Audio
Figure 3 for ASR2K: Speech Recognition for Around 2000 Languages without Audio
Figure 4 for ASR2K: Speech Recognition for Around 2000 Languages without Audio
Viaarxiv icon

Masked Autoencoders that Listen

Jul 13, 2022
Po-Yao, Huang, Hu Xu, Juncheng Li, Alexei Baevski, Michael Auli, Wojciech Galuba, Florian Metze, Christoph Feichtenhofer

Figure 1 for Masked Autoencoders that Listen
Figure 2 for Masked Autoencoders that Listen
Figure 3 for Masked Autoencoders that Listen
Figure 4 for Masked Autoencoders that Listen
Viaarxiv icon

LegoNN: Building Modular Encoder-Decoder Models

Jun 07, 2022
Siddharth Dalmia, Dmytro Okhonko, Mike Lewis, Sergey Edunov, Shinji Watanabe, Florian Metze, Luke Zettlemoyer, Abdelrahman Mohamed

Figure 1 for LegoNN: Building Modular Encoder-Decoder Models
Figure 2 for LegoNN: Building Modular Encoder-Decoder Models
Figure 3 for LegoNN: Building Modular Encoder-Decoder Models
Figure 4 for LegoNN: Building Modular Encoder-Decoder Models
Viaarxiv icon

On Advances in Text Generation from Images Beyond Captioning: A Case Study in Self-Rationalization

May 24, 2022
Shruti Palaskar, Akshita Bhagia, Yonatan Bisk, Florian Metze, Alan W Black, Ana Marasovic

Figure 1 for On Advances in Text Generation from Images Beyond Captioning: A Case Study in Self-Rationalization
Figure 2 for On Advances in Text Generation from Images Beyond Captioning: A Case Study in Self-Rationalization
Figure 3 for On Advances in Text Generation from Images Beyond Captioning: A Case Study in Self-Rationalization
Figure 4 for On Advances in Text Generation from Images Beyond Captioning: A Case Study in Self-Rationalization
Viaarxiv icon

Robustness of Neural Architectures for Audio Event Detection

May 06, 2022
Juncheng B Li, Shuhui Qu, Florian Metze

Figure 1 for Robustness of Neural Architectures for Audio Event Detection
Figure 2 for Robustness of Neural Architectures for Audio Event Detection
Figure 3 for Robustness of Neural Architectures for Audio Event Detection
Figure 4 for Robustness of Neural Architectures for Audio Event Detection
Viaarxiv icon