Papers
Everything we have discussed, in the order we discussed it. Papers on the list but not yet scheduled are at the bottom.
-
Gradient-based learning applied to document recognition.
LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P.
Proceedings of the IEEE, 86(11), 2278-2234. (1998).
Convolutional Neural Networks (CNNs), particularly LeNet-5.
-
Attention is all you need.
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... & Polosukhin, I.
Advances in Neural Information Processing Systems, 30, 5998-6008. (2017).
The Transformer architecture.
-
Bert: Pre-training of deep bidirectional transformers for language understanding.
Devlin, J., Chang, M. W., Lee, K., & Toutanova, K.
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT), 4171-4186. (2019).
Bidirectional Encoder Representations from Transformers (BERT).
-
On the Power of Context-Enhanced Learning in LLMs.
Xingyu Zhu, Abhishek Panigrahi, Sanjeev Arora.
Proceedings of the 42nd International Conference on Machine Learning (ICML). (2025).
Analysis of context-enhanced learning in LLMs.
-
Improving language understanding by generative pre-training.
Radford, A., Narasimhan, K., Salimans, T., & Sutskever, I.
OpenAI Technical Report. (2018).
Generative Pre-trained Transformer (GPT-1).
-
Which Attention Heads Matter for In-Context Learning?
Kayo Yin, Jacob Steinhardt.
Proceedings of the 42nd International Conference on Machine Learning (ICML). (2025).
Analysis of attention head roles in in-context learning.
-
Generalized brain-state modeling with KenazLBM
Graham W. Johnson, Ghassan S. Makhoul, Derek J. Doss, Bruno Hidalgo Monroy Lerma, Leon Y. Cai, Emily Liao, Danika L. Paulo
bioRxiv 2025.08.10.669538, 2025
-
ChartGPT: Leveraging LLMs to Generate Charts From Abstract Natural Language
Yuan Tian, Weiwei Cui, Dazhen Deng, Xinjing Yi, Yurun Yang, Haidong Zhang
IEEE Transactions on Visualization and Computer Graphics 31.3 (2024): 1731-1745.
-
A Multimodal Automated Interpretability Agent
Tamar Rott Shaham, Sarah Schwettmann, Franklin Wang, Achyuta Rajaram, Evan Hernandez, Jacob Andreas, Antonio Torralba
Forty-first International Conference on Machine Learning. 2024.
-
Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation.
Danny Halawi, Alexander Wei, Eric Wallace, Tony T. Wang, Nika Haghtalab, Jacob Steinhardt.
Proceedings of the 41st International Conference on Machine Learning (ICML). (2024).
Analysis of malicious finetuning vulnerabilities in LLMs.
-
Conformal Prediction with Large Language Models for Multi-Choice Question Answering
Bhawesh Kumar, Charlie Lu, Gauri Gupta, Anil Palepu, David Bellamy, Ramesh Raskar, Andrew Beam
arXiv:2305.18404, 2023.
Conformal prediction sets for LLM answers on multiple-choice questions.
-
Attribute-Efficient PAC Learning of Sparse Halfspaces with Constant Malicious Noise Rate
Shiwei Zeng, Jie Shen
arXiv:2505.21430, 2025.
Attribute-efficient, noise-robust PAC learning of sparse halfspaces via hinge loss minimization.
-
Using Reinforcement Learning to Train Large Language Models to Explain Human Decisions
Jian-Qiao Zhu, Hanbo Xie, Dilip Arumugam, Robert C. Wilson, Thomas L. Griffiths
International Conference on Learning Representations (ICLR), 2026.
RL fine-tuning of LLMs to produce natural-language explanations of human decision making. Code: https://github.com/xhb120633/rl_human_behavior
-
A Finite-Time Analysis of Temporal Difference Learning With Linear Function Approximation
Jalaj Bhandari, Daniel Russo, Raghav Singal
31st Conference on Learning Theory (COLT), PMLR 75:1691–1692, 2018
-
Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates
Dong Yin, Yudong Chen, Ramchandran Kannan, Peter Bartlett
35th International Conference on Machine Learning (ICML), PMLR 80:5650–5659, 2018
-
CNN EXPLAINER: Learning Convolutional Neural Networks with Interactive Visualization.
Zijie J. Wang, Robert Turko, Omar Shaikh, Haekyu Park, Nilaksh Das, Fred Hohman, Minsuk Kahng, and Duen Horng (Polo) Chau.
IEEE Transactions on Visualization and Computer Graphics, 27(2), 1396-1406. (2021).
Interactive visualization tool for learning CNNs.
-
Estimating Divergence Functionals and the Likelihood Ratio by Convex Risk Minimization
XuanLong Nguyen, Martin J. Wainwright, Michael I. Jordan
IEEE Transactions on Information Theory, vol. 56, no. 11, pp. 5847–5861, 2010
-
Explaining Vulnerabilities to Adversarial Machine Learning through Visual Analytics.
Yuxin Ma, Tiankai Xie, Jundong Li, Ross Maciejewski.
IEEE Transactions on Visualization and Computer Graphics, 26(10), 3091-3101. (2020).
Visual analytics for explaining adversarial ML vulnerabilities.
-
Language models are unsupervised multitask learners.
Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., & Sutskever, I.
OpenAI Blog, 1(8). (2019).
GPT-2 and demonstrating zero-shot task learning.
-
Learning Safety Constraints for Large Language Models.
Xin Chen, Yarden As, Andreas Krause.
Proceedings of the 42nd International Conference on Machine Learning (ICML). (2025).
Method for learning safety constraints for LLMs.
-
Multiple Forecast Visualizations (MFVs): Trade-offs in Trust and Performance in Multiple COVID-19 Forecast Visualizations.
Lace Padilla, Racquel Fygenson, Spencer C. Castro, Enrico Bertini.
IEEE Transactions on Visualization and Computer Graphics, 29(1), 589-599. (2023).
Study on trust and performance in forecast visualizations.
-
Provably Learning a Multi-head Attention Layer.
Sitan Chen, Yuanzhi Li.
Proceedings of the 57th Annual ACM Symposium on Theory of Computing (STOC). (2025).
Theoretical analysis of learning multi-head attention.
-
Score-Based Generative Modeling Through Stochastic Differential Equations
Yang Song, Jascha Sohl-Dickstein, Diederik P. Kingma, Abhishek Kumar, Stefano Ermon, Ben Poole
International Conference on Learning Representations (ICLR), 2021
-
Score-Based Hypothesis Testing for Unnormalized Models
Suya Wu, Enmao Diao, Khalil Elkhalil, Jie Ding, Vahid Tarokh
IEEE Access
-
Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond.
Chongyu Fan, Jinghan Jia, Yihua Zhang, Anil Ramakrishna, Mingyi Hong, Sijia Liu.
Proceedings of the 42nd International Conference on Machine Learning (ICML). (2025).
Method for LLM unlearning resilient to attacks.
-
Uncertainty-Aware Multidimensional Scaling.
David Hagele, Tim Krake, and Daniel Weiskopf.
IEEE Transactions on Visualization and Computer Graphics, 29(9), 3740-3754. (2023).
Uncertainty-aware multidimensional scaling technique.
-
VATLD: A Visual Analytics System to Assess, Understand and Improve Traffic Light Detection.
Liang Gou, Lincan Zou, Nanxiang Li, Michael Hofmann, Arvind Kumar Shekar, Axel Wendt and Liu Ren.
IEEE Transactions on Visualization and Computer Graphics, 28(1), 328-338. (2021).
Visual analytics system for traffic light detection models.
-
VisEval: A Benchmark for Data Visualization in the Era of Large Language Models.
Nan Chen, Yuge Zhang, Jiahang Xu, Kan Ren, and Yuqing Yang.
IEEE Transactions on Visualization and Computer Graphics. (2025).
Benchmark for data visualization tasks for LLMs.