← Authors

J Zico Kolter

44 papers · 2021–2025 · 5 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (14) 🌈 Renaissance Researcher (6) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (15) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (5) 🏠 Conference Loyalist (33) ⚑ Prolific Year (13) πŸ’Ž Century Club (44) ❓ The Questioner (2) πŸ”₯ Unstoppable (5)

Conferences

ICLR (33) ICML (7) L4DC (2) AISTATS (1) CORL (1)

Top co-authors

YiDing Jiang (5) Christina Baek (5) Samuel Sokota (5) Noam Brown (4) Aditi Raghunathan (4) Mingjie Sun (3) Swaminathan Gurumurthy (3) Zachary Manchester (3) Asher Trockman (3) David J Wu (3)

Keywords

sample efficiency (1) sim-to-real transfer (1) game theory (1) computer vision (1) policy gradient (1) neural network optimization (1) imperfect information (1) nash equilibrium (1) value function (1) continuous control (1) off-policy learning (1) zero-sum game (1) weight initialization (1) proximal policy optimization (1) on-policy learning (1) robotics task (1) model initialization (1) iterative learning control (1) vision task (1) regularized equilibrium (1)

Papers

DEQ-MPC : Deep Equilibrium Model Predictive Control CORL 2025
Theory of Agreement-on-the-Line in Linear Models and Gaussian Data AISTATS 2025
Contextures: Representations from Contexts ICML 2025
Training a Generally Curious Agent ICML 2025
Idiosyncrasies in Large Language Models ICML 2025
Unnatural Languages Are Not Bugs but Features for LLMs ICML 2025
Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws ICLR 2025
Understanding Optimization in Deep Learning with Central Flows ICLR 2025
AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents ICLR 2025
Inference Optimal VLMs Need Fewer Visual Tokens and More Parameters ICLR 2025
Consistency Models Made Easy ICLR 2025
Context-Parametric Inversion: Why Instruction Finetuning May Not Actually Improve Context Reliance ICLR 2025
Compute-Optimal LLMs Provably Generalize Better with Scale ICLR 2025
A Simple and Effective Pruning Approach for Large Language Models ICLR 2024
Why is SAM Robust to Label Noise? ICLR 2024
On the Joint Interaction of Models, Data, and Features ICLR 2024
Understanding prompt engineering may not require rethinking generalization ICLR 2024
T-MARS: Improving Visual Representations by Circumventing Text Feature Learning ICLR 2024
Manifold Preserving Guided Diffusion ICLR 2024
The Update-Equivalence Framework for Decision-Time Planning ICLR 2024
Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression ICLR 2024
Can Neural Network Memorization Be Localized? ICML 2023
Understanding the Covariance Structure of Convolutional Filters ICLR 2023
Simple initialization and parametrization of sinusoidal networks via their kernel bandwidth ICLR 2023
(Certified!!) Adversarial Robustness for Free! ICLR 2023
A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games ICLR 2023
Perfectly Secure Steganography Using Minimum Entropy Coupling ICLR 2023
Understanding Why Generalized Reweighting Does Not Improve Over ERM ICLR 2023
Mimetic Initialization of Self-Attention Layers ICML 2023
Practical Critic Gradient based Actor Critic for On-Policy Reinforcement Learning L4DC 2023
Deep Off-Policy Iterative Learning Control L4DC 2023
Abstracting Imperfect Information Away from Two-Player Zero-Sum Games ICML 2023
Certified Robustness for Deep Equilibrium Models via Interval Bound Propagation ICLR 2022
Neural Deep Equilibrium Solvers ICLR 2022
A Fine-Tuning Approach to Belief State Modeling ICLR 2022
Assessing Generalization of SGD via Disagreement ICLR 2022
Learning perturbation sets for robust machine learning ICLR 2021
Estimating Lipschitz constants of monotone deep equilibrium models ICLR 2021
Provably robust classification of adversarial examples with detection ICLR 2021
Multiplicative Filter Networks ICLR 2021
Orthogonalizing Convolutional Layers with the Cayley Transform ICLR 2021
Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability ICLR 2021
Enforcing robust control guarantees within neural network policies ICLR 2021
DC3: A learning method for optimization with hard constraints ICLR 2021