Lokesh Gupta

2 papers · 2022–2024 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (10)

Venues

IJCAI (1) Interspeech (1)

Top co-authors

Yanming Wang (1) Kaiqi Zhao (1) Nathan Susanj (1) Taeho Kim (1) Hieu Nguyen (1) Ming Zhao (1) Sangtae Ha (1) Vatshank Chaturvedi (1) Seyeon Kim (1) Yongin Kwon (1)

Research topics

Artificial Intelligence (2) Deep Learning (2) Machine Learning (2) Application Areas (2) Core AI (2) Natural Language Processing (1) Speech & Audio (1) Learning Types (1) Optimization & Theory · Machine Learning (1) Optimization & Theory · Deep Learning (1) Recognition (1) Resources & Methods (1)

Keywords

model compression (1) knowledge distillation (1) speech recognition (1) automatic speech recognition (1) long short-term memory (1) recurrent neural network (1) model fine-tuning (1) memory optimization (1) distributed fine-tuning (1) gpu memory estimation (1) multi-gpu setup (1) recurrent neural network transducer (1) large language model fine-tuning (1) large language model (1) transformer model (1) neural network transducer (1)

Papers

LLMem: Estimating GPU Memory Usage for Fine-Tuning Pre-Trained LLMs IJCAI 2024 Knowledge Distillation via Module Replacing for Automatic Speech Recognition with Recurrent Neural Network Transducer Interspeech 2022