🧑‍🔬 Jimmy Lei Ba

🏛️ Affiliations

🎓University of TorontoToronto · Canada2013–2025 · 50 papers🔬Vector InstituteToronto · Canada2023–2024 · 3 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

2010s

📄 Papers

The most cited first (OpenAlex and our library).

1. Adam: A Method for Stochastic Optimization (2014 · 90,277 citations)
   Training large models on noisy, minibatch-based objectives needs a first-order optimizer that is cheap, light on memory, and robust to gradient scale, sparse gradients and objectives that drift over time.
2. Show, Attend and Tell: Neural Image Caption Generation with Visual Attention (2015 · 7,670 citations)
   The paper tackles automatic image captioning: producing a natural-language sentence that describes a photo.
3. Layer Normalization (2016 · 1,819 citations)
   Batch normalization speeds up training of deep networks, but it estimates its statistics from the mini-batch.
4. Large Language Models Are Human-Level Prompt Engineers (2022 · 701 citations)
   How well a large language model does a task depends heavily on the wording of its instruction, and good prompts are usually written by hand through trial and error.
5. AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback (2023 · 456 citations)
   Training instruction-following LLMs with human feedback is costly and slow to iterate on. It is also hard to evaluate reliably, and commercial vendors document it poorly. AlpacaFarm is a sandbox for cheaply studying learning from pairwise feedback (LPF). It has three parts:
6. OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text (2023 · 132 citations)
   Large language models get noticeably better at quantitative reasoning when trained on math-heavy text. Minerva showed this, but its web corpus was never released. Existing open web datasets also mangle mathematical notation during HTML-to-text conversion, so open researchers had no comparable resource. The authors…

All works

76 works of theirs in our library, the most cited first; 6 with a page here, the others link their original until we summarise them.

1. Adam: A Method for Stochastic OptimizationarXiv:1412.6980Diederik P. Kingma, Jimmy Ba2014 · 90,277 citations
2. Show, Attend and Tell: Neural Image Caption Generation with Visual AttentionarXiv:1502.03044Kelvin Xu, Jimmy Ba, Ryan Kiros, et al.2015 · 7,670 citations
3. Layer NormalizationarXiv:1607.06450Jimmy Lei Ba, Jamie Ryan Kiros, Geoffrey E. Hinton2016 · 1,819 citations
4. Do Deep Nets Really Need to be Deep? ↗arXiv (Cornell University) · no summary yetJimmy Lei Ba, Rich Caruana2013 · 1,496 citations
5. Large Language Models Are Human-Level Prompt EngineersarXiv:2211.01910Yongchao Zhou, Andrei Ioan Muresanu, Ziwen Han, et al.2022 · 701 citations
6. Multiple Object Recognition with Visual Attention ↗arXiv (Cornell University) · no summary yetJimmy Lei Ba, Volodymyr Mnih, Koray Kavukcuoglu2014 · 698 citations
7. AlpacaFarm: A Simulation Framework for Methods that Learn from Human FeedbackConference on Neural Information Processing Systems (NeurIPS)Yann Dubois, Xuechen Li, Rohan Taori, et al.2023 · 456 citations
8. Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation ↗arXiv (Cornell University) · no summary yetYuhuai Wu et al.2017 · 450 citations
9. Classifying and segmenting microscopy images with deep multiple instance learning ↗Bioinformatics · no summary yetOren Z. Kraus, Jimmy Lei Ba, Brendan J. Frey2016 · 416 citations
10. Lookahead Optimizer: k steps forward, 1 step back ↗arXiv (Cornell University) · no summary yetMichael R. Zhang et al.2019 · 380 citations
11. Predicting Deep Zero-Shot Convolutional Neural Networks Using Textual Descriptions ↗IEEE International Conference on Computer Vision (ICCV) · no summary yetJimmy Lei Ba et al.2015 · 361 citations
12. Adaptive dropout for training deep neural networks ↗neural information processing systems · no summary yetJimmy Lei Ba, Brendan J. Frey2013 · 272 citations
13. Dream to Control: Learning Behaviors by Latent Imagination ↗arXiv:1912.01603 · no summary yetDanijar Hafner et al.2019 · 228 citations
14. Benchmarking Model-Based Reinforcement Learning ↗arXiv (Cornell University) · no summary yetTingwu Wang et al.2019 · 223 citations
15. Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning ↗arXiv (Cornell University) · no summary yetEmilio Parisotto, Jimmy Lei Ba, Ruslan Salakhutdinov2015 · 217 citations
16. Mastering diverse control tasks through world models ↗Nature · no summary yetDanijar Hafner et al.2025 · 200 citations
17. Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches ↗arXiv:1803.04386 · no summary yetYeming Wen et al.2018 · 189 citations
18. Mastering Diverse Domains through World Models ↗arXiv:2301.04104 · no summary yetDanijar Hafner et al.2023 · 182 citations
19. Using Fast Weights to Attend to the Recent Past ↗arXiv (Cornell University) · no summary yetJimmy Lei Ba et al.2016 · 168 citations
20. NerveNet: Learning Structured Policy with Graph Neural Networks ↗International Conference on Learning Representations · no summary yetTingwu Wang et al.2018 · 148 citations
21. OpenWebMath: An Open Dataset of High-Quality Mathematical Web TextarXiv:2310.06786Keiran Paster, Marco Dos Santos, Zhangir Azerbayev, et al.2023 · 132 citations
22. The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning ↗arXiv:2403.03218 · no summary yetNathaniel Li et al.2024 · 127 citations
23. BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning ↗arXiv (Cornell University) · no summary yetYeming Wen, Dustin Tran, Jimmy Lei Ba2020 · 108 citations
24. Identifying the Risks of LM Agents with an LM-Emulated Sandbox ↗arXiv:2309.15817 · no summary yetYangjun Ruan et al.2023 · 96 citations
25. Mastering Atari with Discrete World Models ↗arXiv:2010.02193 · no summary yetDanijar Hafner et al.2020 · 92 citations

See all 76 works by Jimmy Lei Ba →

🤝 Co-authors here

12 of 20 co-authors with a page, the most papers together first.

• Keiran Paster ×2
• Aaron Courville
• Carlos Guestrin
• Diederik P. Kingma
• Geoffrey E. Hinton
• Ishaan Gulrajani
• Jamie Kiros
• Kelvin Xu
• Kyunghyun Cho
• Marco Dos Santos
• Percy Liang
• Richard S. Zemel

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• International Conference on Learning Representations ×4
• neural information processing systems ×4
• Conference on Neural Information Processing Systems (NeurIPS): NeurIPS 2023
• Bioinformatics
• Communications in computer and information science
• Findings of the Association for Computational Linguistics: ACL 2023
• IEEE International Conference on Computer Vision (ICCV)
• International Conference on Artificial Intelligence and Statistics
• International Conference on Machine Learning
• Nature
• Uncertainty in Artificial Intelligence

🔗 Cited by

Papers of our library cite their works 15,364 times (of the 149,439 papers whose bibliographies we read); 1,475 citing papers with a page here →.

Updated 30 October 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/jimmy-lei-ba/