🧑‍🔬 Zico Kolter

🏛️ Affiliations

🎓Carnegie Mellon UniversityPittsburgh · United States2013–2026 · 174 paperscurrent🏢Robert BoschFarmington Hills · United States2019–2025 · 34 papers🏢Robert BoschBengaluru · India2019–2025 · 23 papers🏢Robert BoschTaipei · Taiwan2019–2024 · 18 papers🎓Stanford UniversityStanford · United States2007–2011 · 12 papers🎓Massachusetts Institute of TechnologyCambridge · United States2010–2018 · 8 papers🏢Robert BoschStuttgart · Germany2019–2025 · 3 papers🎓Georgetown UniversityWashington · United States2004–2005 · 3 papers🔬MIT Computer Science and Artificial Intelligence LaboratoryCambridge · United States2011–2012 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

🧭 Fields, topics and concepts

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

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. Improving Alignment and Robustness with Circuit Breakers (2024 · 83 citations)
   Language models trained to refuse harmful requests can still be jailbroken. Adversarial training usually protects only against attacks seen during training, and it reduces capability. Zou et al. propose "circuit breakers," which change the model's internal representations instead of patching individual attack routes.…
2. Weight Ensembling Improves Reasoning in Language Models (2025 · 10 citations)
   When reasoning models are trained with supervised finetuning (SFT), the variety of their outputs shrinks. Pass@1 keeps rising, but Pass@k peaks early and then falls, which weakens test-time scaling methods such as majority voting or reranking with a reward model. The authors finetune Gemma-2-2B and Qwen-2.5-0.5B on…

All works

18 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

1. Using additive expert ensembles to cope with concept drift ↗International Conference on Machine Learning · no summary yetJ. Zico Kolter, Marcus A. Maloof2005 · 261 citations
2. Near-Bayesian exploration in polynomial time ↗International Conference on Machine Learning · no summary yetJ. Zico Kolter, Andrew Ng2009 · 232 citations
3. Regularization and feature selection in least-squares temporal difference learning ↗International Conference on Machine Learning · no summary yetJ. Zico Kolter, Andrew Ng2009 · 176 citations
4. Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Neural Network Robustness Verification ↗neural information processing systems · no summary yetShiqi Wang et al.2021 · 106 citations
5. Mean Flows for One-step Generative Modeling ↗neural information processing systems · no summary yetZhengyang Geng et al.2025 · 83 citations
6. Improving Alignment and Robustness with Circuit BreakersConference on Neural Information Processing Systems (NeurIPS)Andy Zou, Long Phan, Justin Wang, et al.2024 · 83 citations
7. Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability ↗arXiv (Cornell University) · no summary yetCohen, Jeremy M. et al.2021 · 36 citations
8. Improved Mean Flows: On the Challenges of Fastforward Generative Models ↗arXiv (Cornell University) · no summary yetZhengyang Geng et al.2025 · 12 citations
9. Training a Generally Curious Agent ↗arXiv (Cornell University) · no summary yetFahim Tajwar et al.2025 · 11 citations
10. Weight Ensembling Improves Reasoning in Language ModelsarXiv:2504.10478 · COLM 2025Xingyu Dang, Christina Baek, Kaiyue Wen, et al.2025 · 10 citations
11. Manifold Preserving Guided Diffusion ↗arXiv (Cornell University) · no summary yetHe, Yutong et al.2023 · 8 citations
12. Automated Black-box Prompt Engineering for Personalized Text-to-Image Generation ↗arXiv (Cornell University) · no summary yetHe, Yutong et al.2024 · 5 citations
13. Localized Text-to-Image Generation for Free via Cross Attention Control ↗arXiv (Cornell University) · no summary yetHe, Yutong, Ruslan Salakhutdinov, J. Zico Kolter2023 · 4 citations
14. On Proximal Policy Optimization's Heavy-tailed Gradients ↗arXiv (Cornell University) · no summary yetGarg, Saurabh et al.2021 · 3 citations
15. Comparing AI Agents to Cybersecurity Professionals in Real-World Penetration Testing ↗arXiv (Cornell University) · no summary yetJustin W. Lin et al.2025 · 1 citation
16. Joint Distillation for Fast Likelihood Evaluation and Sampling in Flow-based Models ↗arXiv (Cornell University) · no summary yetAi, Xinyue et al.2025 · 1 citation
17. Accelerating Diffusion Planners in Offline RL via Reward-Aware Consistency Trajectory Distillation ↗arXiv (Cornell University) · no summary yetDuan, Xintong et al.2025
18. Blind Inverse Problem Solving Made Easy by Text-to-Image Latent Diffusion ↗arXiv (Cornell University) · no summary yetMichail Dontas et al.2024

🤝 Co-authors here

8 co-authors with a page, the most papers together first.

• Aditi Raghunathan
• Andy Zou
• Dan Hendrycks
• Kaiyue Wen
• Long Phan
• Maksym Andriushchenko
• Matt Fredrikson
• Xingyu Dang

Venues

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

• Conference on Neural Information Processing Systems (NeurIPS) ×3: NeurIPS 2024
• International Conference on Machine Learning ×3
• neural information processing systems ×2
• Annual Meeting of the Association for Computational Linguistics (ACL)

🔗 Cited by

Papers of our library cite their works 1,787 times (of the 149,439 papers whose bibliographies we read); 428 citing papers with a page here →.

Updated 3 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/zico-kolter/