Mrinmaya Sachan

Artificial Intelligence · 2015–2025

A researcher in the Science corpus: 14 papers; trusts 736 researchers and is trusted by 35 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 288 citations into it; #7,559 of 35,345 by trust here, #8,365 by citations
• Natural Language Processing — 206 citations into it; #1,417 of 5,688 by trust here, #1,753 by citations
• Computer Vision and Pattern Recognition — 93 citations into it; #6,693 of 21,575 by trust here, #7,027 by citations
• Evaluation & Benchmarks — 60 citations into it
• Large Language Models — 38 citations into it; #566 of 799 by trust here, #757 by citations
• Information Systems — 25 citations into it
• Model Architectures — 24 citations into it
• Prompting & Reasoning — 22 citations into it; #235 of 359 by trust here, #324 by citations

Whom Mrinmaya Sachan trusts overall

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

1. Yoshua Bengio
2. Geoffrey E. Hinton
3. Ilya Sutskever
4. Diederik P. Kingma
5. Alex Krizhevsky
6. Alex Graves
7. Jason Aaron Edward Weston
8. Yann LeCun
9. Kaiming He
10. Oriol Vinyals

Who trusts Mrinmaya Sachan overall

1. Eric P. Xing
2. Yang Trista Cao
3. Pan Lu
4. Adam Trischler
5. Igor Labutov
6. Hal Daumé Iii
7. Yang Fan
8. Ishan Misra
9. Qing Li
10. Johannes Welbl

Papers from Mrinmaya Sachan's perspective

Ordered by how strongly the researchers Mrinmaya Sachan 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. Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
10. Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)

Their papers

• Easy Questions First? A Case Study on Curriculum Learning for Question Answering (2016) — 96 citations
• Learning Answer-Entailing Structures for Machine Comprehension (2015) — 62 citations
• Contextual Parameter Generation for Universal Neural Machine Translation (2018) — 152 citations
• Learning to Solve Geometry Problems from Natural Language Demonstrations in Textbooks (2017) — 55 citations
• Self-Training for Jointly Learning to Ask and Answer Questions (2018) — 88 citations
• From Textbooks to Knowledge: A Case Study in Harvesting Axiomatic Knowledge from Textbooks to Solve Geometry Problems (2017) — 48 citations
• The Medium Is Not the Message: Deconfounding Text Embeddings via Linear Concept Erasure (2025)
• The Medium Is Not the Message: Deconfounding Document Embeddings via Linear Concept Erasure (2025)
• Membership Inference Attacks against Language Models via Neighbourhood Comparison (2023) — 339 citations
• Distilling Multi-Step Reasoning Capabilities of Large Language Models into Smaller Models via Semantic Decompositions (2022) — 49 citations
• Distilling Reasoning Capabilities into Smaller Language Models (2022) — 270 citations
• BlonDe: An Automatic Evaluation Metric for Document-level Machine Translation (2021) — 75 citations
• Science Question Answering using Instructional Materials (2016) — 25 citations
• An Active Learning Approach to Coreference Resolution (2015) — 23 citations