Search Results for author:
Found 6 papers, 2 papers with code
Training-Free Activation Sparsity in Large Language Models
Activation sparsity can enable practical inference speedups in large language models (LLMs) by reducing the compute and memory-movement required for matrix multiplications during the forward pass.
Mechanistic Design and Scaling of Hybrid Architectures
The development of deep learning architectures is a resource-demanding process, due to a vast design space, long prototyping times, and high compute costs associated with at-scale model training and evaluation.
Self-Aware Feedback-Based Self-Learning in Large-Scale Conversational AI
Self-learning paradigms in large-scale conversational AI agents tend to leverage user feedback in bridging between what they say and what they mean.
A Vocabulary-Free Multilingual Neural Tokenizer for End-to-End Task Learning
Additionally, the dependency on a fixed vocabulary limits the subword models' adaptability across languages and domains.
Personalized Query Rewriting in Conversational AI Agents
Spoken language understanding (SLU) systems in conversational AI agents often experience errors in the form of misrecognitions by automatic speech recognition (ASR) or semantic gaps in natural language understanding (NLU).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+6
Feedback-Based Self-Learning in Large-Scale Conversational AI Agents
Typically, the accuracy of the ML models in these components are improved by manually transcribing and annotating data.
