Harsh Mehta

Artificial Intelligence · 2019–2024

A researcher in the Science corpus: 9 papers; trusts 235 researchers and is trusted by 2 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 123 citations into it; #31,477 of 35,345 by trust here, #7,471 by citations
• Computer Vision and Pattern Recognition — 82 citations into it; #19,331 of 21,575 by trust here, #9,872 by citations
• Natural Language Processing — 48 citations into it; #5,077 of 5,688 by trust here, #5,092 by citations
• Model Architectures — 38 citations into it
• Large Language Models — 31 citations into it
• Reinforcement Learning — 21 citations into it
• Optimization & Training — 19 citations into it
• Computational Mechanics — 9 citations into it

Whom Harsh Mehta trusts overall

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

1. Diederik P. Kingma
2. Geoffrey E. Hinton
3. Kaiming He
4. Noam Shazeer
5. Yoshua Bengio
6. Alex Krizhevsky
7. Ilya Sutskever
8. Jacob Devlin
9. Jimmy Ba
10. Yann LeCun

Who trusts Harsh Mehta overall

1. Mingde Zhao
2. Tri Dao
3. Kunchang Li
4. Peter Anderson
5. Michael Poli
6. Alexander Ku
7. Xingyu Xie
8. Daniel Y. Fu
9. Vihan Jain

Papers from Harsh Mehta's perspective

Ordered by how strongly the researchers Harsh Mehta 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. Attention is All you Need (Neural Information Processing Systems)
4. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
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. ImageNet Large Scale Visual Recognition Challenge

Their papers

• Transferable Representation Learning in Vision-and-Language Navigation (2019) — 95 citations
• Transformer Memory as a Differentiable Search Index (2022) — 444 citations
• Long Range Language Modeling via Gated State Spaces (2022) — 377 citations
• Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context (2024) — 3,818 citations
• VALAN: Vision and Language Agent Navigation (2019) — 8 citations
• Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models (2023) — 266 citations
• Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models (2022) — 2,561 citations
• Momentum Improves Normalized SGD (2020) — 196 citations
• Retouchdown: Adding Touchdown to StreetLearn as a Shareable Resource for Language Grounding Tasks in Street View (2020) — 29 citations