Alert button

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

Comparing a composite model versus chained models to locate a nearest visual object

Jun 02, 2023
Antoine Le Borgne, Xavier Marjou, Fanny Parzysz, Tayeb Lemlouma

Figure 1 for Comparing a composite model versus chained models to locate a nearest visual object
Figure 2 for Comparing a composite model versus chained models to locate a nearest visual object
Figure 3 for Comparing a composite model versus chained models to locate a nearest visual object
Figure 4 for Comparing a composite model versus chained models to locate a nearest visual object
Viaarxiv icon

Privacy Distillation: Reducing Re-identification Risk of Multimodal Diffusion Models

Jun 02, 2023
Virginia Fernandez, Pedro Sanchez, Walter Hugo Lopez Pinaya, Grzegorz Jacenków, Sotirios A. Tsaftaris, Jorge Cardoso

Figure 1 for Privacy Distillation: Reducing Re-identification Risk of Multimodal Diffusion Models
Figure 2 for Privacy Distillation: Reducing Re-identification Risk of Multimodal Diffusion Models
Figure 3 for Privacy Distillation: Reducing Re-identification Risk of Multimodal Diffusion Models
Figure 4 for Privacy Distillation: Reducing Re-identification Risk of Multimodal Diffusion Models
Viaarxiv icon

Sequence-to-Sequence Pre-training with Unified Modality Masking for Visual Document Understanding

May 16, 2023
Shuwei Feng, Tianyang Zhan, Zhanming Jie, Trung Quoc Luong, Xiaoran Jin

Figure 1 for Sequence-to-Sequence Pre-training with Unified Modality Masking for Visual Document Understanding
Figure 2 for Sequence-to-Sequence Pre-training with Unified Modality Masking for Visual Document Understanding
Figure 3 for Sequence-to-Sequence Pre-training with Unified Modality Masking for Visual Document Understanding
Figure 4 for Sequence-to-Sequence Pre-training with Unified Modality Masking for Visual Document Understanding
Viaarxiv icon

Summaries as Captions: Generating Figure Captions for Scientific Documents with Automated Text Summarization

Feb 23, 2023
Chieh-Yang Huang, Ting-Yao Hsu, Ryan Rossi, Ani Nenkova, Sungchul Kim, Gromit Yeuk-Yin Chan, Eunyee Koh, Clyde Lee Giles, Ting-Hao 'Kenneth' Huang

Figure 1 for Summaries as Captions: Generating Figure Captions for Scientific Documents with Automated Text Summarization
Figure 2 for Summaries as Captions: Generating Figure Captions for Scientific Documents with Automated Text Summarization
Figure 3 for Summaries as Captions: Generating Figure Captions for Scientific Documents with Automated Text Summarization
Figure 4 for Summaries as Captions: Generating Figure Captions for Scientific Documents with Automated Text Summarization
Viaarxiv icon

Leveraging supplementary text data to kick-start automatic speech recognition system development with limited transcriptions

Feb 09, 2023
Nay San, Martijn Bartelds, Blaine Billings, Ella de Falco, Hendi Feriza, Johan Safri, Wawan Sahrozi, Ben Foley, Bradley McDonnell, Dan Jurafsky

Figure 1 for Leveraging supplementary text data to kick-start automatic speech recognition system development with limited transcriptions
Viaarxiv icon

Real or Fake Text?: Investigating Human Ability to Detect Boundaries Between Human-Written and Machine-Generated Text

Dec 24, 2022
Liam Dugan, Daphne Ippolito, Arun Kirubarajan, Sherry Shi, Chris Callison-Burch

Figure 1 for Real or Fake Text?: Investigating Human Ability to Detect Boundaries Between Human-Written and Machine-Generated Text
Figure 2 for Real or Fake Text?: Investigating Human Ability to Detect Boundaries Between Human-Written and Machine-Generated Text
Figure 3 for Real or Fake Text?: Investigating Human Ability to Detect Boundaries Between Human-Written and Machine-Generated Text
Figure 4 for Real or Fake Text?: Investigating Human Ability to Detect Boundaries Between Human-Written and Machine-Generated Text
Viaarxiv icon

Investigating the Effect of Relative Positional Embeddings on AMR-to-Text Generation with Structural Adapters

Feb 12, 2023
Sebastien Montella, Alexis Nasr, Johannes Heinecke, Frederic Bechet, Lina M. Rojas-Barahona

Figure 1 for Investigating the Effect of Relative Positional Embeddings on AMR-to-Text Generation with Structural Adapters
Figure 2 for Investigating the Effect of Relative Positional Embeddings on AMR-to-Text Generation with Structural Adapters
Figure 3 for Investigating the Effect of Relative Positional Embeddings on AMR-to-Text Generation with Structural Adapters
Figure 4 for Investigating the Effect of Relative Positional Embeddings on AMR-to-Text Generation with Structural Adapters
Viaarxiv icon

Learn What Is Possible, Then Choose What Is Best: Disentangling One-To-Many Relations in Language Through Text-based Games

Apr 14, 2023
Benjamin Towle, Ke Zhou

Figure 1 for Learn What Is Possible, Then Choose What Is Best: Disentangling One-To-Many Relations in Language Through Text-based Games
Figure 2 for Learn What Is Possible, Then Choose What Is Best: Disentangling One-To-Many Relations in Language Through Text-based Games
Figure 3 for Learn What Is Possible, Then Choose What Is Best: Disentangling One-To-Many Relations in Language Through Text-based Games
Figure 4 for Learn What Is Possible, Then Choose What Is Best: Disentangling One-To-Many Relations in Language Through Text-based Games
Viaarxiv icon

Tractable Control for Autoregressive Language Generation

Apr 18, 2023
Honghua Zhang, Meihua Dang, Nanyun Peng, Guy Van den Broeck

Figure 1 for Tractable Control for Autoregressive Language Generation
Figure 2 for Tractable Control for Autoregressive Language Generation
Figure 3 for Tractable Control for Autoregressive Language Generation
Figure 4 for Tractable Control for Autoregressive Language Generation
Viaarxiv icon

Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception

May 10, 2023
Hassan Akbari, Dan Kondratyuk, Yin Cui, Rachel Hornung, Huisheng Wang, Hartwig Adam

Figure 1 for Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception
Figure 2 for Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception
Figure 3 for Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception
Figure 4 for Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception
Viaarxiv icon