Picture for Shankar Kumar

Shankar Kumar

Long-Form Speech Translation through Segmentation with Finite-State Decoding Constraints on Large Language Models

Oct 23, 2023
Figure 1 for Long-Form Speech Translation through Segmentation with Finite-State Decoding Constraints on Large Language Models
Figure 2 for Long-Form Speech Translation through Segmentation with Finite-State Decoding Constraints on Large Language Models
Figure 3 for Long-Form Speech Translation through Segmentation with Finite-State Decoding Constraints on Large Language Models
Figure 4 for Long-Form Speech Translation through Segmentation with Finite-State Decoding Constraints on Large Language Models
Viaarxiv icon

Heterogeneous Federated Learning Using Knowledge Codistillation

Oct 04, 2023
Figure 1 for Heterogeneous Federated Learning Using Knowledge Codistillation
Figure 2 for Heterogeneous Federated Learning Using Knowledge Codistillation
Figure 3 for Heterogeneous Federated Learning Using Knowledge Codistillation
Figure 4 for Heterogeneous Federated Learning Using Knowledge Codistillation
Viaarxiv icon

Towards an On-device Agent for Text Rewriting

Add code
Aug 22, 2023
Figure 1 for Towards an On-device Agent for Text Rewriting
Figure 2 for Towards an On-device Agent for Text Rewriting
Figure 3 for Towards an On-device Agent for Text Rewriting
Figure 4 for Towards an On-device Agent for Text Rewriting
Viaarxiv icon

Semantic Segmentation with Bidirectional Language Models Improves Long-form ASR

May 28, 2023
Figure 1 for Semantic Segmentation with Bidirectional Language Models Improves Long-form ASR
Figure 2 for Semantic Segmentation with Bidirectional Language Models Improves Long-form ASR
Figure 3 for Semantic Segmentation with Bidirectional Language Models Improves Long-form ASR
Figure 4 for Semantic Segmentation with Bidirectional Language Models Improves Long-form ASR
Viaarxiv icon

Measuring Re-identification Risk

Add code
Apr 12, 2023
Figure 1 for Measuring Re-identification Risk
Figure 2 for Measuring Re-identification Risk
Figure 3 for Measuring Re-identification Risk
Figure 4 for Measuring Re-identification Risk
Viaarxiv icon

Improved Long-Form Spoken Language Translation with Large Language Models

Dec 19, 2022
Figure 1 for Improved Long-Form Spoken Language Translation with Large Language Models
Figure 2 for Improved Long-Form Spoken Language Translation with Large Language Models
Figure 3 for Improved Long-Form Spoken Language Translation with Large Language Models
Figure 4 for Improved Long-Form Spoken Language Translation with Large Language Models
Viaarxiv icon

Conciseness: An Overlooked Language Task

Add code
Nov 08, 2022
Figure 1 for Conciseness: An Overlooked Language Task
Figure 2 for Conciseness: An Overlooked Language Task
Figure 3 for Conciseness: An Overlooked Language Task
Figure 4 for Conciseness: An Overlooked Language Task
Viaarxiv icon

Simple and Effective Gradient-Based Tuning of Sequence-to-Sequence Models

Add code
Sep 10, 2022
Figure 1 for Simple and Effective Gradient-Based Tuning of Sequence-to-Sequence Models
Figure 2 for Simple and Effective Gradient-Based Tuning of Sequence-to-Sequence Models
Figure 3 for Simple and Effective Gradient-Based Tuning of Sequence-to-Sequence Models
Figure 4 for Simple and Effective Gradient-Based Tuning of Sequence-to-Sequence Models
Viaarxiv icon

Text Generation with Text-Editing Models

Add code
Jun 14, 2022
Figure 1 for Text Generation with Text-Editing Models
Figure 2 for Text Generation with Text-Editing Models
Figure 3 for Text Generation with Text-Editing Models
Figure 4 for Text Generation with Text-Editing Models
Viaarxiv icon

Jam or Cream First? Modeling Ambiguity in Neural Machine Translation with SCONES

May 02, 2022
Figure 1 for Jam or Cream First? Modeling Ambiguity in Neural Machine Translation with SCONES
Figure 2 for Jam or Cream First? Modeling Ambiguity in Neural Machine Translation with SCONES
Figure 3 for Jam or Cream First? Modeling Ambiguity in Neural Machine Translation with SCONES
Figure 4 for Jam or Cream First? Modeling Ambiguity in Neural Machine Translation with SCONES
Viaarxiv icon