---
title: "Jimmy Lei Ba — all works — Elamur Research"
description: "All 75 works of Jimmy Lei Ba 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/jimmy-lei-ba/works/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/jimmy-lei-ba/works/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Jimmy Lei Ba](https://md.research.elamur.ai/free/en/authors/jimmy-lei-ba/) / all works

# Jimmy Lei Ba — all works

75 works · [← Jimmy Lei Ba](https://md.research.elamur.ai/free/en/authors/jimmy-lei-ba/)

1. [**Adam: A Method for Stochastic Optimization arXiv:1412.6980**Diederik P. Kingma, Jimmy Ba*2014 · 90,277 citations*](https://md.research.elamur.ai/free/en/papers/kingma-2014-adam-method-stochastic-optimization/)
2. [**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/)
3. [**Layer Normalization arXiv:1607.06450**Jimmy Lei Ba, Jamie Ryan Kiros, Geoffrey E. Hinton*2016 · 1,819 citations*](https://md.research.elamur.ai/free/en/papers/ba-2016-layer-normalization/)
4. **[Do Deep Nets Really Need to be Deep? ↗](https://arxiv.org/abs/1312.6184) arXiv (Cornell University) · no summary yet**Jimmy Lei Ba, Rich Caruana*2013 · 1,496 citations*
5. [**Large Language Models Are Human-Level Prompt Engineers arXiv:2211.01910**Yongchao Zhou, Andrei Ioan Muresanu, Ziwen Han, et al.*2022 · 701 citations*](https://md.research.elamur.ai/free/en/papers/zhou-2022-large-language-models-human-level/)
6. **[Multiple Object Recognition with Visual Attention ↗](https://arxiv.org/abs/1412.7755) arXiv (Cornell University) · no summary yet**Jimmy Lei Ba, Volodymyr Mnih, Koray Kavukcuoglu*2014 · 698 citations*
7. **[AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback](https://md.research.elamur.ai/free/en/papers/dubois-2023-alpacafarm-simulation-framework-methods-that/) [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/)**Yann Dubois, Xuechen Li, Rohan Taori, et al.*2023 · 456 citations*
8. **[Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation ↗](https://arxiv.org/abs/1708.05144) arXiv (Cornell University) · no summary yet**Yuhuai Wu et al.*2017 · 450 citations*
9. **[Classifying and segmenting microscopy images with deep multiple instance learning ↗](https://doi.org/10.1093/bioinformatics/btw252) Bioinformatics · no summary yet**Oren Z. Kraus, Jimmy Lei Ba, Brendan J. Frey*2016 · 416 citations*
10. **[Lookahead Optimizer: k steps forward, 1 step back ↗](https://arxiv.org/abs/1907.08610) arXiv (Cornell University) · no summary yet**Michael R. Zhang et al.*2019 · 380 citations*
11. **[Predicting Deep Zero-Shot Convolutional Neural Networks Using Textual Descriptions ↗](https://doi.org/10.1109/iccv.2015.483) IEEE International Conference on Computer Vision (ICCV) · no summary yet**Jimmy Lei Ba et al.*2015 · 361 citations*
12. **[Adaptive dropout for training deep neural networks ↗](https://openalex.org/W2136836265) neural information processing systems · no summary yet**Jimmy Lei Ba, Brendan J. Frey*2013 · 272 citations*
13. **[Dream to Control: Learning Behaviors by Latent Imagination ↗](https://arxiv.org/abs/1912.01603) arXiv:1912.01603 · no summary yet**Danijar Hafner et al.*2019 · 228 citations*
14. **[Benchmarking Model-Based Reinforcement Learning ↗](https://arxiv.org/abs/1907.02057) arXiv (Cornell University) · no summary yet**Tingwu Wang et al.*2019 · 223 citations*
15. **[Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning ↗](https://arxiv.org/abs/1511.06342) arXiv (Cornell University) · no summary yet**Emilio Parisotto, Jimmy Lei Ba, Ruslan Salakhutdinov*2015 · 217 citations*
16. **[Mastering diverse control tasks through world models ↗](https://doi.org/10.1038/s41586-025-08744-2) Nature · no summary yet**Danijar Hafner et al.*2025 · 200 citations*
17. **[Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches ↗](https://arxiv.org/abs/1803.04386) arXiv:1803.04386 · no summary yet**Yeming Wen et al.*2018 · 189 citations*
18. **[Mastering Diverse Domains through World Models ↗](https://arxiv.org/abs/2301.04104) arXiv:2301.04104 · no summary yet**Danijar Hafner et al.*2023 · 182 citations*
19. **[Using Fast Weights to Attend to the Recent Past ↗](https://arxiv.org/abs/1610.06258) arXiv (Cornell University) · no summary yet**Jimmy Lei Ba et al.*2016 · 168 citations*
20. **[NerveNet: Learning Structured Policy with Graph Neural Networks ↗](https://openalex.org/W2785948534) International Conference on Learning Representations · no summary yet**Tingwu Wang et al.*2018 · 148 citations*
21. [**OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text arXiv:2310.06786**Keiran Paster, Marco Dos Santos, Zhangir Azerbayev, et al.*2023 · 132 citations*](https://md.research.elamur.ai/free/en/papers/paster-2023-openwebmath-open-dataset-high-quality/)
22. **[BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning ↗](https://arxiv.org/abs/2002.06715) arXiv (Cornell University) · no summary yet**Yeming Wen, Dustin Tran, Jimmy Lei Ba*2020 · 108 citations*
23. [**Identifying the Risks of LM Agents with an LM-Emulated Sandbox arXiv:2309.15817**Yangjun Ruan, Honghua Dong, Andrew Wang, et al.*2023 · 96 citations*](https://md.research.elamur.ai/free/en/papers/ruan-2023-identifying-risks-lm-agents-lm/)
24. **[Mastering Atari with Discrete World Models ↗](https://arxiv.org/abs/2010.02193) arXiv:2010.02193 · no summary yet**Danijar Hafner et al.*2020 · 92 citations*
25. **[Clinical Camel: An Open Expert-Level Medical Language Model with Dialogue-Based Knowledge Encoding ↗](https://arxiv.org/abs/2305.12031) arXiv:2305.12031 · no summary yet**Augustin Toma et al.*2023 · 91 citations*
26. **[Exploring Model-based Planning with Policy Networks ↗](https://arxiv.org/abs/1906.08649) arXiv (Cornell University) · no summary yet**Tingwu Wang, Jimmy Lei Ba*2019 · 88 citations*
27. **[Generating Images from Captions with Attention ↗](https://arxiv.org/abs/1511.02793) arXiv (Cornell University) · no summary yet**Elman Mansimov et al.*2015 · 88 citations*
28. **[Distributed Second-Order Optimization using Kronecker-Factored Approximations ↗](https://openalex.org/W2750933313) International Conference on Learning Representations · no summary yet**Jimmy Lei Ba, Roger Grosse, James Martens*2017 · 73 citations*
29. **[Improving Transformer Optimization Through Better Initialization ↗](https://openalex.org/W3035618017) International Conference on Machine Learning · no summary yet**Xiao Shi Huang et al.*2020 · 67 citations*
30. **[Graph Normalizing Flows ↗](https://arxiv.org/abs/1905.13177) arXiv (Cornell University) · no summary yet**Liu, Jenny et al.*2019 · 64 citations*
31. **[On the Convergence and Robustness of Training GANs with Regularized Optimal Transport ↗](https://arxiv.org/abs/1802.08249) arXiv (Cornell University) · no summary yet**Maziar Sanjabi et al.*2018 · 57 citations*
32. **[On Solving Minimax Optimization Locally: A Follow-the-Ridge Approach ↗](https://arxiv.org/abs/1910.07512) arXiv (Cornell University) · no summary yet**Yuanhao Wang, Guodong Zhang, Jimmy Lei Ba*2019 · 54 citations*
33. **[Kronecker-factored Curvature Approximations for Recurrent Neural Networks ↗](https://openalex.org/W2786263712) International Conference on Learning Representations · no summary yet**James Martens, Jimmy Lei Ba, Matt R. Johnson*2018 · 51 citations*
34. **[Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learning ↗](https://arxiv.org/abs/2007.02832) arXiv (Cornell University) · no summary yet**Silviu Pitis et al.*2020 · 45 citations*
35. **[Residual Prompt Tuning: improving prompt tuning with residual reparameterization ↗](https://aclanthology.org/2023.findings-acl.421/) Findings of the Association for Computational Linguistics: ACL 2023 · no summary yet**Anastasiia Razdaibiedina et al.*2023 · 42 citations*
36. **[INT: An Inequality Benchmark for Evaluating Generalization in Theorem Proving ↗](https://arxiv.org/abs/2007.02924) arXiv:2007.02924 · no summary yet**Yuhuai Wu et al.*2020 · 41 citations*
37. **[LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning ↗](https://arxiv.org/abs/2101.06223) arXiv:2101.06223 · no summary yet**Yuhuai Wu et al.*2021 · 39 citations*
38. **[Boosted Prompt Ensembles for Large Language Models ↗](https://arxiv.org/abs/2304.05970) arXiv (Cornell University) · no summary yet**Silviu Pitis et al.*2023 · 38 citations*
39. **[Neural Graph Evolution: Towards Efficient Automatic Robot Design ↗](https://arxiv.org/abs/1906.05370) arXiv (Cornell University) · no summary yet**Tingwu Wang et al.*2019 · 32 citations*
40. **[Generalization of Two-layer Neural Networks: An Asymptotic Viewpoint ↗](https://openalex.org/W2996067004) International Conference on Learning Representations · no summary yet**Jimmy Lei Ba et al.*2020 · 30 citations*
41. **[Reversible Recurrent Neural Networks ↗](https://arxiv.org/abs/1810.10999) arXiv (Cornell University) · no summary yet**Matthew Mackay et al.*2018 · 30 citations*
42. **[Learning Wake-Sleep Recurrent Attention Models ↗](https://arxiv.org/abs/1509.06812) arXiv (Cornell University) · no summary yet**Jimmy Lei Ba et al.*2015 · 29 citations*
43. **[The Scattering Compositional Learner: Discovering Objects, Attributes, Relationships in Analogical Reasoning ↗](https://arxiv.org/abs/2007.04212) arXiv (Cornell University) · no summary yet**Yuhuai Wu et al.*2020 · 27 citations*
44. **[Action and Perception as Divergence Minimization ↗](https://arxiv.org/abs/2009.01791) arXiv (Cornell University) · no summary yet**Danijar Hafner et al.*2020 · 25 citations*
45. **[ACTRCE: Augmenting Experience via Teacher's Advice For Multi-Goal Reinforcement Learning ↗](https://arxiv.org/abs/1902.04546) arXiv (Cornell University) · no summary yet**Harris Chan et al.*2019 · 25 citations*
46. **[DOM-Q-NET: Grounded RL on Structured Language ↗](https://arxiv.org/abs/1902.07257) arXiv (Cornell University) · no summary yet**Sheng Jia, Jamie Kiros, Jimmy Lei Ba*2019 · 19 citations*
47. **[Using Large Language Models for Hyperparameter Optimization ↗](https://arxiv.org/abs/2312.04528) arXiv (Cornell University) · no summary yet**Michael R. Zhang et al.*2023 · 18 citations*
48. **[Exploring Low Rank Training of Deep Neural Networks ↗](https://arxiv.org/abs/2209.13569) arXiv (Cornell University) · no summary yet**Siddhartha Rao Kamalakara et al.*2022 · 18 citations*
49. **[You Can’t Count on Luck: Why Decision Transformers and RvS Fail in Stochastic Environments ↗](https://doi.org/10.52202/068431-2824) neural information processing systems · no summary yet**Keiran Paster, Sheila A. McIlraith, Jimmy Lei Ba*2022 · 15 citations*
50. **[Clockwork Variational Autoencoders ↗](https://arxiv.org/abs/2102.09532) arXiv (Cornell University) · no summary yet**Vaibhav Saxena, Jimmy Lei Ba, Danijar Hafner*2021 · 13 citations*
51. **[Interplay Between Optimization and Generalization of Stochastic Gradient Descent with Covariance Noise. ↗](https://arxiv.org/abs/1902.08234) arXiv (Cornell University) · no summary yet**Yeming Wen et al.*2019 · 13 citations*
52. **[High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation ↗](https://arxiv.org/abs/2205.01445) arXiv (Cornell University) · no summary yet**Jimmy Lei Ba et al.*2022 · 12 citations*
53. **[A Study of Gradient Variance in Deep Learning ↗](https://arxiv.org/abs/2007.04532) arXiv (Cornell University) · no summary yet**Fartash Faghri et al.*2020 · 12 citations*
54. **[When Does Preconditioning Help or Hurt Generalization? ↗](https://arxiv.org/abs/2006.10732) arXiv (Cornell University) · no summary yet**Шун-ичи Амари et al.*2020 · 11 citations*
55. **[Training on Thin Air: Improve Image Classification with Generated Data ↗](https://arxiv.org/abs/2305.15316) arXiv (Cornell University) · no summary yet**Yongchao Zhou, Hshmat Sahak, Jimmy Lei Ba*2023 · 10 citations*
56. **[Evaluating Agents without Rewards ↗](https://arxiv.org/abs/2012.11538) arXiv (Cornell University) · no summary yet**Brendon Matusch, Jimmy Lei Ba, Danijar Hafner*2020 · 8 citations*
57. **[Planning from Pixels using Inverse Dynamics Models ↗](https://arxiv.org/abs/2012.02419) arXiv (Cornell University) · no summary yet**Keiran Paster, Sheila A. McIlraith, Jimmy Lei Ba*2020 · 7 citations*
58. **[Learning Intrinsic Rewards as a Bi-Level Optimization Problem ↗](https://openalex.org/W3089723243) Uncertainty in Artificial Intelligence · no summary yet**Bradly C. Stadie, Lunjun Zhang, Jimmy Lei Ba*2020 · 7 citations*
59. **[An Empirical Study of Stochastic Gradient Descent with Structured Covariance Noise ↗](https://openalex.org/W3037273417) International Conference on Artificial Intelligence and Statistics · no summary yet**Yeming Wen et al.*2020 · 7 citations*
60. **[Second-order Optimization for Deep Reinforcement Learning using Kronecker-factored Approximation ↗](https://openalex.org/W2753431380) neural information processing systems · no summary yet**Yuhuai Wu et al.*2017 · 7 citations*
61. **[Efficient Statistical Tests: A Neural Tangent Kernel Approach ↗](https://openalex.org/W3168905660) no summary yet**Sheng Jia et al.*2021 · 6 citations*
62. **[Towards Characterizing the High-dimensional Bias of Kernel-based Particle Inference Algorithms ↗](https://openalex.org/W3007177133) no summary yet**Jimmy Lei Ba et al.*2019 · 5 citations*
63. **[Multi-Rate VAE: Train Once, Get the Full Rate-Distortion Curve ↗](https://arxiv.org/abs/2212.03905) arXiv (Cornell University) · no summary yet**Juhan Bae et al.*2022 · 4 citations*
64. **[An Inductive Bias for Distances: Neural Nets that Respect the Triangle Inequality ↗](https://arxiv.org/abs/2002.05825) arXiv (Cornell University) · no summary yet**Silviu Pitis et al.*2020 · 4 citations*
65. **[Decomposed Prompting to Answer Questions on a Course Discussion Board ↗](https://doi.org/10.1007/978-3-031-36336-8_33) Communications in computer and information science · no summary yet**Brandon Jaipersaud et al.*2023 · 3 citations*
66. **[Learning Domain Invariant Representations in Goal-conditioned Block MDPs ↗](https://arxiv.org/abs/2110.14248) arXiv (Cornell University) · no summary yet**Beining Han et al.*2021 · 3 citations*
67. **[EMA Policy Gradient: Taming Reinforcement Learning for LLMs with EMA Anchor and Top-k KL ↗](https://arxiv.org/abs/2602.04417) arXiv (Cornell University) · no summary yet**Lunjun Zhang, Jimmy Lei Ba*2026 · 1 citation*
68. **[Report Cards: Qualitative Evaluation of Language Models Using Natural Language Summaries ↗](https://arxiv.org/abs/2409.00844) arXiv (Cornell University) · no summary yet**Blair Yang et al.*2024 · 1 citation*
69. **[Learning in the Presence of Low-dimensional Structure: A Spiked Random Matrix Perspective ↗](https://doi.org/10.52202/075280-0765) neural information processing systems · no summary yet**Jimmy Lei Ba et al.*2023 · 1 citation*
70. **[Noisy Labels Can Induce Good Representations. ↗](https://arxiv.org/abs/2012.12896) arXiv (Cornell University) · no summary yet**Jingling Li et al.*2020 · 1 citation*
71. **[TR0N: Translator Networks for 0-Shot Plug-and-Play Conditional Generation ↗](https://arxiv.org/abs/2304.13742) arXiv (Cornell University) · no summary yet**Zhaoyan Liu et al.*2023*
72. **[Video Prediction with Variational Temporal Hierarchies ↗](https://openalex.org/W3130028346) no summary yet**Vaibhav Saxena, Jimmy Lei Ba, Danijar Hafner*2021*
73. **[A Non-asymptotic comparison of SVRG and SGD: tradeoffs between compute and speed ↗](https://openalex.org/W2997794460) no summary yet**Qingru Zhang et al.*2019*
74. **[Exploring Curvature Noise in Large-Batch Stochastic Optimization ↗](https://openalex.org/W2914399343) no summary yet**Yeming Wen et al.*2018*
75. **[ACTRCE: Augmenting Experience via Teacher’s Advice ↗](https://openalex.org/W2914548969) no summary yet**Yuhuai Wu et al.*2018*