Kushal Lakhotia

Artificial Intelligence · 2018–2024

A researcher in the Science corpus: 13 papers; trusts 204 researchers and is trusted by 60 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 420 citations into it; #3,887 of 35,345 by trust here, #2,594 by citations
• Signal Processing — 218 citations into it; #676 of 7,572 by trust here, #309 by citations
• Speech & Audio — 184 citations into it; #155 of 1,076 by trust here, #111 by citations
• Natural Language Processing — 149 citations into it
• Representation & Self-Supervised Learning — 130 citations into it; #836 of 3,145 by trust here, #602 by citations
• Computer Vision and Pattern Recognition — 117 citations into it; #18,052 of 21,575 by trust here, #7,249 by citations
• Large Language Models — 52 citations into it
• Evaluation & Benchmarks — 47 citations into it

Whom Kushal Lakhotia trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Geoffrey E. Hinton
2. Diederik P. Kingma
3. Yoshua Bengio
4. Alex Graves
5. Alex Krizhevsky
6. Ilya Sutskever
7. Aäron van den Oord
8. Kaiming He
9. Oriol Vinyals
10. Yann LeCun

Who trusts Kushal Lakhotia overall

1. Evgeny Kharitonov
2. Tu Nguyen
3. Ann Lee
4. Dong Zhang
5. Jade Copet
6. Wei-Ning Hsu
7. Felix Kreuk
8. Adam Polyak
9. Abdel-rahman Mohamed
10. Yossi Adi

Papers from Kushal Lakhotia's perspective

Ordered by how strongly the researchers Kushal Lakhotia trusts endorse each paper. Same corpus, a different order for every researcher.

1. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
2. ImageNet classification with deep convolutional neural networks
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Attention is All you Need (Neural Information Processing Systems)
5. Long Short-Term Memory
6. ImageNet: A large-scale hierarchical image database
7. Gradient-based learning applied to document recognition
8. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
9. Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
10. Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)

Their papers

• On Generative Spoken Language Modeling from Raw Audio (2021) — 483 citations
• HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units (2021) — 4,844 citations
• XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale (2021) — 1,102 citations
• Speech Resynthesis from Discrete Disentangled Self-Supervised Representations (2021) — 398 citations
• Text-Free Prosody-Aware Generative Spoken Language Modeling (2021) — 159 citations
• Domain-matched Pre-training Tasks for Dense Retrieval (2021) — 72 citations
• textless-lib: a Library for Textless Spoken Language Processing (2022) — 41 citations
• Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One? (2021) — 87 citations
• PyText: A Seamless Path from NLP research to production (2018) — 17 citations
• SUPERB: Speech processing Universal PERformance Benchmark (2021) — 1,225 citations
• SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities (2022) — 133 citations
• The Llama 3 Herd of Models (2024) — 17,085 citations
• Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction (2022) — 490 citations