Picture for Akshat Shrivastava

Akshat Shrivastava

PRoDeliberation: Parallel Robust Deliberation for End-to-End Spoken Language Understanding

Add code
Jun 12, 2024
Viaarxiv icon

PrE-Text: Training Language Models on Private Federated Data in the Age of LLMs

Add code
Jun 05, 2024
Viaarxiv icon

LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding

Add code
Apr 29, 2024
Figure 1 for LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding
Figure 2 for LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding
Figure 3 for LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding
Figure 4 for LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding
Viaarxiv icon

Small But Funny: A Feedback-Driven Approach to Humor Distillation

Add code
Feb 28, 2024
Viaarxiv icon

Augmenting text for spoken language understanding with Large Language Models

Add code
Sep 17, 2023
Figure 1 for Augmenting text for spoken language understanding with Large Language Models
Figure 2 for Augmenting text for spoken language understanding with Large Language Models
Figure 3 for Augmenting text for spoken language understanding with Large Language Models
Figure 4 for Augmenting text for spoken language understanding with Large Language Models
Viaarxiv icon

Modality Confidence Aware Training for Robust End-to-End Spoken Language Understanding

Add code
Jul 22, 2023
Figure 1 for Modality Confidence Aware Training for Robust End-to-End Spoken Language Understanding
Figure 2 for Modality Confidence Aware Training for Robust End-to-End Spoken Language Understanding
Figure 3 for Modality Confidence Aware Training for Robust End-to-End Spoken Language Understanding
Figure 4 for Modality Confidence Aware Training for Robust End-to-End Spoken Language Understanding
Viaarxiv icon

TreePiece: Faster Semantic Parsing via Tree Tokenization

Add code
Mar 30, 2023
Figure 1 for TreePiece: Faster Semantic Parsing via Tree Tokenization
Figure 2 for TreePiece: Faster Semantic Parsing via Tree Tokenization
Figure 3 for TreePiece: Faster Semantic Parsing via Tree Tokenization
Figure 4 for TreePiece: Faster Semantic Parsing via Tree Tokenization
Viaarxiv icon

Privately Customizing Prefinetuning to Better Match User Data in Federated Learning

Add code
Feb 23, 2023
Figure 1 for Privately Customizing Prefinetuning to Better Match User Data in Federated Learning
Figure 2 for Privately Customizing Prefinetuning to Better Match User Data in Federated Learning
Figure 3 for Privately Customizing Prefinetuning to Better Match User Data in Federated Learning
Figure 4 for Privately Customizing Prefinetuning to Better Match User Data in Federated Learning
Viaarxiv icon

Introducing Semantics into Speech Encoders

Add code
Nov 15, 2022
Figure 1 for Introducing Semantics into Speech Encoders
Figure 2 for Introducing Semantics into Speech Encoders
Figure 3 for Introducing Semantics into Speech Encoders
Figure 4 for Introducing Semantics into Speech Encoders
Viaarxiv icon

Data-Efficiency with a Single GPU: An Exploration of Transfer Methods for Small Language Models

Add code
Oct 08, 2022
Figure 1 for Data-Efficiency with a Single GPU: An Exploration of Transfer Methods for Small Language Models
Figure 2 for Data-Efficiency with a Single GPU: An Exploration of Transfer Methods for Small Language Models
Figure 3 for Data-Efficiency with a Single GPU: An Exploration of Transfer Methods for Small Language Models
Figure 4 for Data-Efficiency with a Single GPU: An Exploration of Transfer Methods for Small Language Models
Viaarxiv icon