J. Zico Kolter

Carnegie Mellon University — United States

Computer Science · Physical Sciences

55h-index18.2kcitations259works1.32yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Adversarial Robustness in Machine Learning(67), Anomaly Detection Techniques and Applications(29), Machine Learning and Algorithms(28), Topic Modeling(22), Domain Adaptation and Few-Shot Learning(22)

Publications259 total

Comparing AI Agents to Cybersecurity Professionals in Real-World Penetration Testing
arXiv (Cornell University)·2025Open Access
Joint Distillation for Fast Likelihood Evaluation and Sampling in Flow-based Models
arXiv (Cornell University)·2025Open Access
Improved Mean Flows: On the Challenges of Fastforward Generative Models
arXiv (Cornell University)·2025Open Access
D-REX: A Benchmark for Detecting Deceptive Reasoning in Large Language Models
arXiv (Cornell University)·2025Open Access
OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents
arXiv (Cornell University)·2025· 1 citedOpen Access
OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics
arXiv (Cornell University)·2025Open Access
Adversarial Attacks on Robotic Vision Language Action Models
arXiv (Cornell University)·2025Open Access
Existing Large Language Model Unlearning Evaluations Are Inconclusive
arXiv (Cornell University)·2025Open Access
Mean Flows for One-step Generative Modeling
arXiv (Cornell University)·2025· 2 citedOpen Access
Contextures: Representations from Contexts
arXiv (Cornell University)·2025Open Access
Antidistillation Sampling
arXiv (Cornell University)·2025Open Access
Looking beyond the next token
arXiv (Cornell University)·2025Open Access
Weight Ensembling Improves Reasoning in Language Models
arXiv (Cornell University)·2025Open Access
Unnatural Languages Are Not Bugs but Features for LLMs
arXiv (Cornell University)·2025Open Access
A Vision for Computational Decarbonization of Societal Infrastructure
IEEE Internet Computing·2025· 3 cited
Training a Generally Curious Agent
arXiv (Cornell University)·2025Open Access
Idiosyncrasies in Large Language Models
arXiv (Cornell University)·2025· 1 citedOpen Access
Neural Network Verification with Branch-and-Bound for General Nonlinearities
Lecture notes in computer science·2025· 4 citedOpen Access
HyperCLIP: Adapting Vision-Language models with Hypernetworks
arXiv (Cornell University)·2024Open Access
Blind Inverse Problem Solving Made Easy by Text-to-Image Latent Diffusion
arXiv (Cornell University)·2024Open Access
page 1 of 13Next →

Frequent Co-authors

Eric Wong(7), Andrew Y. Ng(7), Brandon Amos(7), Marcus A. Maloof(5), Shaojie Bai(4), Frank R. Schmidt(4), Vladlen Koltun(3), Priya L. Donti(3), Leslie Rice(2), Filipe de Avila Belbute-Peres(2), Jan Hendrik Metzen(2), Andy Zou(2), Jacob Sacks(2), Byron Boots(2), Vaishnavh Nagarajan(2), Jesse Levinson(1), Jake Askeland(1), Jan Becker(1), Jennifer Dolson(1), David Held(1)