---
title: "Samy Bengio — all works — Elamur Research"
description: "All 31 works of Samy 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/samy-bengio/works/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/samy-bengio/works/)

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

# Samy Bengio — all works

31 works · [← Samy Bengio](https://md.research.elamur.ai/free/en/authors/samy-bengio/)

1. **[Generating Sentences from a Continuous Space](https://md.research.elamur.ai/free/en/papers/bowman-2016-generating-sentences-continuous-space/) [Conference on Computational Natural Language Learning (CoNLL)](https://md.research.elamur.ai/free/en/venues/conll/)**Samuel R. Bowman, Luke Vilnis, Oriol Vinyals, et al.*2016 · 2,435 citations*
2. **[DeViSE: A Deep Visual-Semantic Embedding Model ↗](https://openalex.org/W2123024445) no summary yet**Andrea Frome et al.*2013 · 2,055 citations*
3. **[Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks ↗](https://arxiv.org/abs/1506.03099) arXiv:1506.03099 · no summary yet**Samy Bengio et al.*2015 · 1,884 citations*
4. **[Tacotron: Towards End-to-End Speech Synthesis ↗](https://doi.org/10.21437/interspeech.2017-1452) Interspeech (USB) · no summary yet**Yuxuan Wang et al.*2017 · 1,786 citations*
5. **[Understanding deep learning requires rethinking generalization ↗](https://arxiv.org/abs/1611.03530) arXiv:1611.03530 · no summary yet**Chiyuan Zhang et al.*2016 · 1,174 citations*
6. **[Show and Tell: Lessons Learned from the 2015 MSCOCO Image Captioning Challenge ↗](https://doi.org/10.1109/tpami.2016.2587640) IEEE Transactions on Pattern Analysis and Machine Intelligence · no summary yet**Oriol Vinyals et al.*2016 · 929 citations*
7. [**Show and Tell: A Neural Image Caption Generator arXiv:1411.4555**Oriol Vinyals, Alexander Toshev, Samy Bengio, et al.*2014 · 729 citations*](https://md.research.elamur.ai/free/en/papers/vinyals-2014-show-tell-neural-image-caption/)
8. **[Device Placement Optimization with Reinforcement Learning ↗](https://arxiv.org/abs/1706.04972) arXiv:1706.04972 · no summary yet**Azalia Mirhoseini et al.*2017 · 343 citations*
9. **[Neural Combinatorial Optimization with Reinforcement Learning ↗](https://arxiv.org/abs/1611.09940) arXiv (Cornell University) · no summary yet**Irwan Bello et al.*2016 · 299 citations*
10. [**GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models arXiv:2410.05229**Iman Mirzadeh, Keivan Alizadeh, Hooman Shahrokhi, et al.*2024 · 273 citations*](https://md.research.elamur.ai/free/en/papers/mirzadeh-2024-gsm-symbolic-understanding-limitations-mathematical/)
11. **[Learning to Remember Rare Events ↗](https://arxiv.org/abs/1703.03129) arXiv:1703.03129 · no summary yet**Łukasz Kaiser et al.*2017 · 258 citations*
12. **[Order Matters: Sequence to sequence for sets ↗](https://arxiv.org/abs/1511.06391) arXiv:1511.06391 · no summary yet**Oriol Vinyals, Samy Bengio, Manjunath Kudlur*2015 · 245 citations*
13. **[A Study on Overfitting in Deep Reinforcement Learning ↗](https://arxiv.org/abs/1804.06893) arXiv (Cornell University) · no summary yet**Chiyuan Zhang et al.*2018 · 242 citations*
14. **[Fast Decoding in Sequence Models using Discrete Latent Variables ↗](https://arxiv.org/abs/1803.03382) arXiv (Cornell University) · no summary yet**Łukasz Kaiser et al.*2018 · 213 citations*
15. **[Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model. ↗](https://arxiv.org/abs/1703.10135) arXiv (Cornell University) · no summary yet**Yuxuan Wang et al.*2017 · 200 citations*
16. **[Tensor2Tensor for Neural Machine Translation](https://md.research.elamur.ai/free/en/papers/vaswani-2018-tensor2tensor-neural-machine-translation/) [Conference of the Association for Machine Translation in the Americas (AMTA)](https://md.research.elamur.ai/free/en/venues/amta/)**Ashish Vaswani, Samy Bengio, Eugene Brevdo, et al.*2018 · 191 citations*
17. **[Context-aware Captions from Context-agnostic Supervision ↗](https://arxiv.org/abs/1701.02870) arXiv:1701.02870 · no summary yet**Ramakrishna Vedantam et al.*2017 · 161 citations*
18. **[Reward Augmented Maximum Likelihood for Neural Structured Prediction ↗](https://arxiv.org/abs/1609.00150) arXiv (Cornell University) · no summary yet**Mohammad Norouzi et al.*2016 · 146 citations*
19. **[Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML ↗](https://arxiv.org/abs/1909.09157) arXiv:1909.09157 · no summary yet**Aniruddh Raghu et al.*2019 · 117 citations*
20. **[Learning semantic relationships for better action retrieval in images ↗](https://doi.org/10.1109/cvpr.2015.7298713) 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**Vignesh Ramanathan et al.*2015 · 113 citations*
21. **[The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity ↗](https://arxiv.org/abs/2506.06941) arXiv:2506.06941 · no summary yet**Parshin Shojaee et al.*2025 · 104 citations*
22. **[What Algorithms can Transformers Learn? A Study in Length Generalization ↗](https://arxiv.org/abs/2310.16028) arXiv:2310.16028 · no summary yet**Hattie Zhou et al.*2023 · 67 citations*
23. **[An Online Sequence-to-Sequence Model Using Partial Conditioning ↗](https://arxiv.org/abs/1511.04868) arXiv (Cornell University) · no summary yet**Navdeep Jaitly et al.*2015 · 49 citations*
24. **[Discrete Autoencoders for Sequence Models ↗](https://arxiv.org/abs/1801.09797) arXiv (Cornell University) · no summary yet**Łukasz Kaiser, Samy Bengio*2018 · 40 citations*
25. **[Can Active Memory Replace Attention? ↗](https://arxiv.org/abs/1610.08613) arXiv (Cornell University) · no summary yet**Łukasz Kaiser, Samy Bengio*2016 · 31 citations*
26. **[Parallel Scheduled Sampling ↗](https://arxiv.org/abs/1906.04331) arXiv (Cornell University) · no summary yet**Duckworth, Daniel et al.*2019 · 20 citations*
27. **[Generalization on the Unseen, Logic Reasoning and Degree Curriculum ↗](https://arxiv.org/abs/2301.13105) arXiv:2301.13105 · no summary yet**Emmanuel Abbe et al.*2023 · 17 citations*
28. **[Using Web Co-occurrence Statistics for Improving Image Categorization ↗](https://arxiv.org/abs/1312.5697) arXiv (Cornell University) · no summary yet**Samy Bengio et al.*2013 · 17 citations*
29. **[Area Attention ↗](https://arxiv.org/abs/1810.10126) arXiv (Cornell University) · no summary yet**Yang Li et al.*2018 · 2 citations*
30. **[Show and Tell:2015MSCOCO画像キャプション攻撃から学んだ教訓【Powered by NICT】 ↗](https://openalex.org/W2746153907) IEEE Transactions on Pattern Analysis and Machine Intelligence · no summary yet**Oriol Vinyals et al.*2017*
31. **[Y.: Using web co-occurrence statistics for improving image categorization. arXiv preprint arXiv:1312.5697 ↗](https://openalex.org/W7098658056) no summary yet**Samy Bengio et al.*2013*