---
title: "Yoshua Bengio — all works — Elamur Research"
description: "All 120 works of Yoshua Bengio in the Elamur Research library, the most cited first: our summaries where we have them, else the original."
canonical: "https://research.elamur.ai/free/en/authors/yoshua-bengio/works/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/yoshua-bengio/works/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Yoshua Bengio](https://md.research.elamur.ai/free/en/authors/yoshua-bengio/) / all works

# Yoshua Bengio — all works

120 works · page 1 of 2 · 1–100 · [← Yoshua Bengio](https://md.research.elamur.ai/free/en/authors/yoshua-bengio/)

**1** [2](https://md.research.elamur.ai/free/en/authors/yoshua-bengio/works/page/2/) [next →](https://md.research.elamur.ai/free/en/authors/yoshua-bengio/works/page/2/)

1. **[Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation](https://md.research.elamur.ai/free/en/papers/cho-2014-learning-phrase-representations-rnn-encoder/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Kyunghyun Cho, Bart van Merriënboer, Caglar Gulcehre, et al.*2014 · 26,725 citations*
2. [**Neural Machine Translation by Jointly Learning to Align and Translate arXiv:1409.0473**Dzmitry Bahdanau, Kyunghyun Cho, Yoshua Bengio*2014 · 19,287 citations*](https://md.research.elamur.ai/free/en/papers/bahdanau-2014-neural-machine-translation-jointly-learning/)
3. **[Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling ↗](https://arxiv.org/abs/1412.3555) arXiv:1412.3555 · no summary yet**Junyoung Chung et al.*2014 · 10,908 citations*
4. [**Graph Attention Networks arXiv:1710.10903**Petar Veličkovic, Guillem Cucurull, Arantxa Casanova, et al.*2017 · 9,035 citations*](https://md.research.elamur.ai/free/en/papers/veli-vckovic-2017-graph-attention-networks/)
5. [**On the Properties of Neural Machine Translation: Encoder-Decoder Approaches arXiv:1409.1259**Kyunghyun Cho, Bart van Merrienboer, Dzmitry Bahdanau, et al.*2014 · 7,803 citations*](https://md.research.elamur.ai/free/en/papers/cho-2014-properties-neural-machine-translation-encoder/)
6. [**Show, Attend and Tell: Neural Image Caption Generation with Visual Attention arXiv:1502.03044**Kelvin Xu, Jimmy Ba, Ryan Kiros, et al.*2015 · 7,670 citations*](https://md.research.elamur.ai/free/en/papers/xu-2015-show-attend-tell-neural-image/)
7. [**Generative Adversarial Nets**Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, et al.*2014 · 5,790 citations*](https://md.research.elamur.ai/free/en/papers/goodfellow-2014-generative-adversarial-nets/)
8. **[HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://md.research.elamur.ai/free/en/papers/yang-2018-hotpotqa-dataset-diverse-explainable-multi/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Zhilin Yang, Peng Qi, Saizheng Zhang, et al.*2018 · 3,557 citations*
9. **[Word Representations: A Simple and General Method for Semi-Supervised Learning](https://md.research.elamur.ai/free/en/papers/turian-2010-word-representations-simple-general-method/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Joseph Turian, Lev-Arie Ratinov, Yoshua Bengio*2010 · 2,450 citations*
10. [**Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1 arXiv:1602.02830**Matthieu Courbariaux, Itay Hubara, Daniel Soudry, et al.*2016 · 2,143 citations*](https://md.research.elamur.ai/free/en/papers/courbariaux-2016-binarized-neural-networks-training-deep/)
11. [**BinaryConnect: Training Deep Neural Networks with binary weights during propagations arXiv:1511.00363**Matthieu Courbariaux, Yoshua Bengio, Jean-Pierre David*2015 · 1,885 citations*](https://md.research.elamur.ai/free/en/papers/courbariaux-2015-binaryconnect-training-deep-neural-networks/)
12. [**Attention-Based Models for Speech Recognition arXiv:1506.07503**Jan Chorowski, Dzmitry Bahdanau, Dmitriy Serdyuk, et al.*2015 · 1,819 citations*](https://md.research.elamur.ai/free/en/papers/chorowski-2015-attention-based-models-speech-recognition/)
13. [**A Structured Self-attentive Sentence Embedding arXiv:1703.03130**Zhouhan Lin, Minwei Feng, Cicero Nogueira dos Santos, et al.*2017 · 1,797 citations*](https://md.research.elamur.ai/free/en/papers/lin-2017-structured-self-attentive-sentence-embedding/)
14. [**Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations arXiv:1609.07061**Itay Hubara, Matthieu Courbariaux, Daniel Soudry, et al.*2016 · 1,610 citations*](https://md.research.elamur.ai/free/en/papers/hubara-2016-quantized-neural-networks-training-neural/)
15. **[End-to-end attention-based large vocabulary speech recognition ↗](https://doi.org/10.1109/icassp.2016.7472618) IEEE International Conference on Acoustics Speech and Signal Processing · no summary yet**Dzmitry Bahdanau et al.*2016 · 1,179 citations*
16. [**Theano: new features and speed improvements arXiv:1211.5590**Frédéric Bastien, Pascal Lamblin, Razvan Pascanu, et al.*2012 · 1,111 citations*](https://md.research.elamur.ai/free/en/papers/bastien-2012-theano-new-features-speed-improvements/)
17. **[On Using Very Large Target Vocabulary for Neural Machine Translation](https://md.research.elamur.ai/free/en/papers/jean-2015-very-large-target-vocabulary-neural/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Sébastien Jean, Kyunghyun Cho, Roland Memisevic, et al.*2015 · 1,013 citations*
18. [**A Neural Probabilistic Language Model JMLR 3:1137–1155**Yoshua Bengio, Réjean Ducharme, Pascal Vincent, et al.*2003 · 985 citations*](https://md.research.elamur.ai/free/en/papers/bengio-2003-neural-probabilistic-language-model/)
19. **[Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanism](https://md.research.elamur.ai/free/en/papers/firat-2016-multi-way-multilingual-neural-machine/) [Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)](https://md.research.elamur.ai/free/en/venues/naacl/)**Orhan Firat, Kyunghyun Cho, Yoshua Bengio*2016 · 833 citations*
20. **[Identifying and attacking the saddle point problem in high-dimensional non-convex optimization ↗](https://arxiv.org/abs/1406.2572) arXiv (Cornell University) · no summary yet**Yann Dauphin et al.*2014 · 818 citations*
21. **[On the Number of Linear Regions of Deep Neural Networks ↗](https://arxiv.org/abs/1402.1869) arXiv (Cornell University) · no summary yet**Guido Montúfar et al.*2014 · 811 citations*
22. [**Curriculum Learning**Yoshua Bengio, Jérôme Louradour, Ronan Collobert, et al.*Mova's core list · 724 citations*](https://md.research.elamur.ai/free/en/papers/bengio-2009-curriculum-learning/)
23. **[Pointing the Unknown Words](https://md.research.elamur.ai/free/en/papers/gulcehre-2016-pointing-unknown-words/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Caglar Gulcehre, Sungjin Ahn, Ramesh Nallapati, et al.*2016 · 651 citations*
24. [**On Using Monolingual Corpora in Neural Machine Translation arXiv:1503.03535**Caglar Gulcehre, Orhan Firat, Kelvin Xu, et al.*2015 · 639 citations*](https://md.research.elamur.ai/free/en/papers/gulcehre-2015-using-monolingual-corpora-neural-machine/)
25. **[Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space ↗](https://doi.org/10.1109/cvpr.2017.374) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Anh Nguyen et al.*2017 · 610 citations*
26. **[Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models](https://md.research.elamur.ai/free/en/papers/serban-2015-building-end-end-dialogue-systems/) [Proceedings of the AAAI Conference on Artificial Intelligence](https://md.research.elamur.ai/free/en/venues/proceedings-of-the-aaai-conference-on-artificial-intelligence/)**Iulian V. Serban, Alessandro Sordoni, Yoshua Bengio, et al.*2015 · 551 citations*
27. **[A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues](https://md.research.elamur.ai/free/en/papers/serban-2016-hierarchical-latent-variable-encoder-decoder/) [Proceedings of the AAAI Conference on Artificial Intelligence](https://md.research.elamur.ai/free/en/venues/proceedings-of-the-aaai-conference-on-artificial-intelligence/)**Iulian Vlad Serban, Alessandro Sordoni, Ryan Lowe, et al.*2016 · 547 citations*
28. **[Towards an Automatic Turing Test: Learning to Evaluate Dialogue Responses](https://md.research.elamur.ai/free/en/papers/lowe-2017-towards-automatic-turing-test-learning/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Ryan Lowe, Michael Noseworthy, Iulian V. Serban, et al.*2017 · 499 citations*
29. **[Investigation of recurrent-neural-network architectures and learning methods for spoken language understanding ↗](https://doi.org/10.21437/interspeech.2013-596) Interspeech (USB) · no summary yet**Grégoire Mesnil et al.*2013 · 485 citations*
30. **[Experience Grounds Language](https://md.research.elamur.ai/free/en/papers/bisk-2020-experience-grounds-language/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Yonatan Bisk, Ari Holtzman, Jesse Thomason, et al.*2020 · 439 citations*
31. **[Gated Feedback Recurrent Neural Networks ↗](https://arxiv.org/abs/1502.02367) arXiv (Cornell University) · no summary yet**Chung, Junyoung et al.*2015 · 438 citations*
32. **[End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Results ↗](https://arxiv.org/abs/1412.1602) arXiv (Cornell University) · no summary yet**Jan Chorowski et al.*2014 · 416 citations*
33. **[A Character-level Decoder without Explicit Segmentation for Neural Machine Translation](https://md.research.elamur.ai/free/en/papers/chung-2016-character-level-decoder-without-explicit/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Junyoung Chung, Kyunghyun Cho, Yoshua Bengio*2016 · 413 citations*
34. [**Representation Learning: A Review and New Perspectives arXiv:1206.5538**Yoshua Bengio, Aaron Courville, Pascal Vincent*2012 · 383 citations*](https://md.research.elamur.ai/free/en/papers/bengio-2012-representation-learning-review-new-perspectives/)
35. **[Managing extreme AI risks amid rapid progress ↗](https://doi.org/10.1126/science.adn0117) Science · no summary yet**Yoshua Bengio et al.*2024 · 382 citations*
36. **[Describing Multimedia Content Using Attention-Based Encoder-Decoder Networks ↗](https://doi.org/10.1109/tmm.2015.2477044) IEEE Transactions on Multimedia · no summary yet**Kyunghyun Cho, Aaron C. Courville, Yoshua Bengio*2015 · 361 citations*
37. **[Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid Question-Answer Corpus ↗](https://aclanthology.org/P16-1056/) Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yet**Iulian Vlad Serban et al.*2016 · 351 citations*
38. [**An Actor-Critic Algorithm for Sequence Prediction arXiv:1607.07086**Dzmitry Bahdanau, Philemon Brakel, Kelvin Xu, et al.*2016 · 335 citations*](https://md.research.elamur.ai/free/en/papers/bahdanau-2016-actor-critic-algorithm-sequence-prediction/)
39. **[Speech Model Pre-Training for End-to-End Spoken Language Understanding ↗](https://doi.org/10.21437/interspeech.2019-2396) Interspeech (USB) · no summary yet**Loren Lugosch et al.*2019 · 328 citations*
40. **[Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims ↗](https://arxiv.org/abs/2004.07213) arXiv:2004.07213 · no summary yet**Miles Brundage et al.*2020 · 320 citations*
41. [**How to Construct Deep Recurrent Neural Networks arXiv:1312.6026**Razvan Pascanu, Caglar Gulcehre, Kyunghyun Cho, et al.*2013 · 302 citations*](https://md.research.elamur.ai/free/en/papers/pascanu-2013-construct-deep-recurrent-neural-networks/)
42. [**Hierarchical Multiscale Recurrent Neural Networks arXiv:1609.01704**Junyoung Chung, Sungjin Ahn, Yoshua Bengio*2016 · 288 citations*](https://md.research.elamur.ai/free/en/papers/chung-2016-hierarchical-multiscale-recurrent-neural-networks/)
43. **[ReSeg: A Recurrent Neural Network-Based Model for Semantic Segmentation ↗](https://doi.org/10.1109/cvprw.2016.60) IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · no summary yet**Francesco Visin et al.*2016 · 285 citations*
44. [**FigureQA: An Annotated Figure Dataset for Visual Reasoning arXiv:1710.07300**Samira Ebrahimi Kahou, Vincent Michalski, Adam Atkinson, et al.*2017 · 240 citations*](https://md.research.elamur.ai/free/en/papers/kahou-2017-figureqa-annotated-figure-dataset-visual/)
45. **[Learning to Understand Phrases by Embedding the Dictionary](https://md.research.elamur.ai/free/en/papers/hill-2016-learning-understand-phrases-embedding-dictionary/) [Transactions of the Association for Computational Linguistics (TACL)](https://md.research.elamur.ai/free/en/venues/tacl/)**Felix Hill, Kyunghyun Cho, Anna Korhonen, et al.*2016 · 236 citations*
46. **[Learning Problem-Agnostic Speech Representations from Multiple Self-Supervised Tasks ↗](https://doi.org/10.21437/interspeech.2019-2605) Interspeech (USB) · no summary yet**Santiago Pascual et al.*2019 · 234 citations*
47. **[Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation ↗](https://doi.org/10.1609/aaai.v31i1.10984) Proceedings of the AAAI Conference on Artificial Intelligence · no summary yet**Iulian Vlad Serban et al.*2017 · 229 citations*
48. **[ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks ↗](https://arxiv.org/abs/1505.00393) arXiv (Cornell University) · no summary yet**Francesco Visin et al.*2015 · 228 citations*
49. **[Fine-grained attention mechanism for neural machine translation ↗](https://doi.org/10.1016/j.neucom.2018.01.007) Neurocomputing · no summary yet**Heeyoul Choi, Kyunghyun Cho, Yoshua Bengio*2018 · 208 citations*
50. **[Montreal Neural Machine Translation Systems for WMT'15 ↗](https://aclanthology.org/W15-3014/) Proceedings of the Tenth Workshop on Statistical Machine Translation · no summary yet**Sébastien Jean et al.*2015 · 185 citations*
51. **[HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution ↗](https://arxiv.org/abs/2306.15794) arXiv (Cornell University) · no summary yet**Nguyen, Eric et al.*2023 · 184 citations*
52. **[Hyena Hierarchy: Towards Larger Convolutional Language Models ↗](https://arxiv.org/abs/2302.10866) arXiv:2302.10866 · no summary yet**Michael Poli et al.*2023 · 182 citations*
53. [**Theano: A Python framework for fast computation of mathematical expressions arXiv:1605.02688**The Theano Development Team, Rami Al-Rfou, Guillaume Alain, et al.*2016 · 179 citations*](https://md.research.elamur.ai/free/en/papers/the-theano-development-team-2016-theano-python-framework-fast-computation/)
54. **[Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study ↗](https://aclanthology.org/P19-1004/) Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · no summary yet**Chinnadhurai Sankar et al.*2019 · 174 citations*
55. **[Learned-Norm Pooling for Deep Feedforward and Recurrent Neural Networks ↗](https://doi.org/10.1007/978-3-662-44848-9_34) Lecture notes in computer science · no summary yet**Çağlar Gülçehre et al.*2014 · 171 citations*
56. **[Blocks and Fuel: Frameworks for deep learning ↗](https://arxiv.org/abs/1506.00619) arXiv:1506.00619 · no summary yet**Bart van Merrienboer et al.*2015 · 152 citations*
57. **[FloW: A Dataset and Benchmark for Floating Waste Detection in Inland Waters ↗](https://doi.org/10.1109/iccv48922.2021.01077) IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yet**Yuwei Cheng et al.*2021 · 149 citations*
58. **[On integrating a language model into neural machine translation ↗](https://doi.org/10.1016/j.csl.2017.01.014) Computer Speech & Language · no summary yet**Çağlar Gülçehre et al.*2017 · 148 citations*
59. [**A Neural Knowledge Language Model arXiv:1608.00318**Sungjin Ahn, Heeyoul Choi, Tanel Pärnamaa, et al.*2016 · 146 citations*](https://md.research.elamur.ai/free/en/papers/ahn-2016-neural-knowledge-language-model/)
60. **[Denoising Criterion for Variational Auto-Encoding Framework ↗](https://doi.org/10.1609/aaai.v31i1.10777) Proceedings of the AAAI Conference on Artificial Intelligence · no summary yet**Daniel Im Jiwoong Im et al.*2017 · 144 citations*
61. **[Straight to the Tree: Constituency Parsing with Neural Syntactic Distance ↗](https://aclanthology.org/P18-1108/) Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yet**Yikang Shen et al.*2018 · 132 citations*
62. [**BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning arXiv:1810.08272**Maxime Chevalier-Boisvert, Dzmitry Bahdanau, Salem Lahlou, et al.*2018 · 123 citations*](https://md.research.elamur.ai/free/en/papers/chevalier-boisvert-2018-babyai-platform-study-sample-efficiency/)
63. **[Multi-Prediction Deep Boltzmann Machines ↗](https://openalex.org/W2098617596) neural information processing systems · no summary yet**Ian Goodfellow et al.*2013 · 121 citations*
64. **[Context-dependent word representation for neural machine translation ↗](https://doi.org/10.1016/j.csl.2017.01.007) Computer Speech & Language · no summary yet**Heeyoul Choi, Kyunghyun Cho, Yoshua Bengio*2017 · 118 citations*
65. [**Gradient based sample selection for online continual learning arXiv:1903.08671**Rahaf Aljundi, Min Lin, Baptiste Goujaud, et al.*2019 · 115 citations*](https://md.research.elamur.ai/free/en/papers/aljundi-2019-gradient-based-sample-selection-online/)
66. **[Architectural Complexity Measures of Recurrent Neural Networks ↗](https://arxiv.org/abs/1602.08210) arXiv (Cornell University) · no summary yet**Saizheng Zhang et al.*2016 · 115 citations*
67. **[Multi-way, multilingual neural machine translation ↗](https://doi.org/10.1016/j.csl.2016.10.006) Computer Speech & Language · no summary yet**Orhan Fırat et al.*2016 · 114 citations*
68. **[Boundary-Seeking Generative Adversarial Networks ↗](https://arxiv.org/abs/1702.08431) arXiv (Cornell University) · no summary yet**R Devon Hjelm et al.*2017 · 113 citations*
69. **[Overcoming the Curse of Sentence Length for Neural Machine Translation using Automatic Segmentation ↗](https://aclanthology.org/W14-4009/) Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation · no summary yet**Jean Pouget-Abadie et al.*2014 · 96 citations*
70. **[Learning to Compute Word Embeddings On the Fly ↗](https://arxiv.org/abs/1706.00286) arXiv (Cornell University) · no summary yet**Dzmitry Bahdanau et al.*2017 · 91 citations*
71. **[On Multiplicative Integration with Recurrent Neural Networks ↗](https://arxiv.org/abs/1606.06630) arXiv (Cornell University) · no summary yet**Yuhuai Wu et al.*2016 · 69 citations*
72. **[CLOSURE: Assessing Systematic Generalization of CLEVR Models ↗](https://arxiv.org/abs/1912.05783) arXiv (Cornell University) · no summary yet**Dzmitry Bahdanau et al.*2019 · 67 citations*
73. **[Slow, Decorrelated Features for Pretraining Complex Cell-like Networks ↗](https://openalex.org/W2168345951) neural information processing systems · no summary yet**Yoshua Bengio, James Bergstra*2009 · 64 citations*
74. **[The representational geometry of word meanings acquired by neural machine translation models ↗](https://doi.org/10.1007/s10590-017-9194-2) Machine Translation · no summary yet**Felix Hill et al.*2017 · 58 citations*
75. **[Embedding Word Similarity with Neural Machine Translation ↗](https://arxiv.org/abs/1412.6448) arXiv (Cornell University) · no summary yet**Felix Hill et al.*2014 · 58 citations*
76. **[Dynamic Neural Turing Machine with Continuous and Discrete Addressing Schemes ↗](https://doi.org/10.1162/neco_a_01060) Neural Computation · no summary yet**Çağlar Gülçehre et al.*2018 · 56 citations*
77. **[Not All Neural Embeddings are Born Equal ↗](https://arxiv.org/abs/1410.0718) arXiv (Cornell University) · no summary yet**Felix Hill et al.*2014 · 53 citations*
78. **[Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving ↗](https://arxiv.org/abs/2405.12205) arXiv:2405.12205 · no summary yet**Aniket Didolkar et al.*2024 · 45 citations*
79. **[International AI Safety Report ↗](https://arxiv.org/abs/2501.17805) arXiv (Cornell University) · no summary yet**Yoshua Bengio et al.*2025 · 41 citations*
80. **[GEO-Bench: Toward Foundation Models for Earth Monitoring ↗](https://doi.org/10.52202/075280-2223) neural information processing systems · no summary yet**Alexandre Lacoste et al.*2023 · 41 citations*
81. **[Commonsense mining as knowledge base completion? A study on the impact of novelty ↗](https://aclanthology.org/W18-1002/) Proceedings of the Workshop on Generalization in the Age of Deep Learning · no summary yet**Stanislaw Jastrzębski et al.*2018 · 41 citations*
82. **[Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes ↗](https://arxiv.org/abs/1607.00036) arXiv (Cornell University) · no summary yet**Çağlar Gülçehre et al.*2016 · 37 citations*
83. **[Exponentially Increasing the Capacity-to-Computation Ratio for Conditional Computation in Deep Learning ↗](https://arxiv.org/abs/1406.7362) arXiv (Cornell University) · no summary yet**Kyunghyun Cho, Yoshua Bengio*2014 · 37 citations*
84. **[Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety ↗](https://arxiv.org/abs/2507.11473) arXiv (Cornell University) · no summary yet**Tomek Korbak et al.*2025 · 35 citations*
85. **[Task Loss Estimation for Sequence Prediction ↗](https://arxiv.org/abs/1511.06456) arXiv (Cornell University) · no summary yet**Dzmitry Bahdanau et al.*2015 · 29 citations*
86. **[Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems ↗](https://arxiv.org/abs/2405.06624) arXiv (Cornell University) · no summary yet**David Dalrymple et al.*2024 · 24 citations*
87. **[AI-Assisted Generation of Difficult Math Questions ↗](https://arxiv.org/abs/2407.21009) arXiv:2407.21009 · no summary yet**Vedant Shah et al.*2024 · 23 citations*
88. **[Iterative Neural Autoregressive Distribution Estimator (NADE-k) ↗](https://arxiv.org/abs/1406.1485) arXiv (Cornell University) · no summary yet**Tapani Raiko et al.*2014 · 23 citations*
89. **[Self-Evolving Curriculum for LLM Reasoning ↗](https://arxiv.org/abs/2505.14970) arXiv:2505.14970 · no summary yet**Xiaoyin Chen et al.*2025 · 20 citations*
90. **[Machine learning and information theory concepts towards an AI Mathematician ↗](https://arxiv.org/abs/2403.04571) arXiv:2403.04571 · no summary yet**Yoshua Bengio, Nikolay Malkin*2024 · 18 citations*
91. **[Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path? ↗](https://arxiv.org/abs/2502.15657) arXiv:2502.15657 · no summary yet**Yoshua Bengio et al.*2025 · 16 citations*
92. **[Bounding the Test Log-Likelihood of Generative Models ↗](https://arxiv.org/abs/1311.6184) arXiv (Cornell University) · no summary yet**Yoshua Bengio, Yao, Li, Kyunghyun Cho*2013 · 16 citations*
93. **[Learning Dynamics Model in Reinforcement Learning by Incorporating the Long Term Future ↗](https://arxiv.org/abs/1903.01599) arXiv (Cornell University) · no summary yet**Nan Rosemary Ke et al.*2019 · 15 citations*
94. **[Modeling the Long Term Future in Model-Based Reinforcement Learning ↗](https://openalex.org/W2923023063) International Conference on Learning Representations · no summary yet**Nan Rosemary Ke et al.*2018 · 14 citations*
95. **[International Scientific Report on the Safety of Advanced AI (Interim Report) ↗](https://arxiv.org/abs/2412.05282) arXiv (Cornell University) · no summary yet**Yoshua Bengio et al.*2024 · 13 citations*
96. **[Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions ↗](https://doi.org/10.52202/075280-0747) neural information processing systems · no summary yet**Stefano Massaroli et al.*2023 · 13 citations*
97. **[BabyAI 1.1 ↗](https://arxiv.org/abs/2007.12770) arXiv (Cornell University) · no summary yet**David Yu-Tung Hui et al.*2020 · 12 citations*
98. **[NYU-MILA Neural Machine Translation Systems for WMT'16 ↗](https://aclanthology.org/W16-2309/) Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers · no summary yet**Junyoung Chung, Kyunghyun Cho, Yoshua Bengio*2016 · 12 citations*
99. **[On the Equivalence between Deep NADE and Generative Stochastic Networks ↗](https://doi.org/10.1007/978-3-662-44845-8_21) Lecture notes in computer science · no summary yet**Li Yao et al.*2014 · 10 citations*
100. **[Boundary Seeking GANs ↗](https://openalex.org/W2787038193) International Conference on Learning Representations · no summary yet**R Devon Hjelm et al.*2018 · 7 citations*

**1** [2](https://md.research.elamur.ai/free/en/authors/yoshua-bengio/works/page/2/) [next →](https://md.research.elamur.ai/free/en/authors/yoshua-bengio/works/page/2/)