J. Zico Kolter

Venues

Frequent coauthors

Papers

1. Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws
   ICLR 2025 ·

   Yiding Jiang

   DBLP profile ↗ORCID search ↗
2. AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
   ICLR 2025 ·

   Maksym Andriushchenko

   DBLP profile ↗ORCID search ↗
3. Antidistillation Sampling
   NeurIPS 2025 ·

   Yash Savani

   DBLP profile ↗ORCID search ↗
4. Compute-Optimal LLMs Provably Generalize Better with Scale
   ICLR 2025 ·

   Marc Anton Finzi

   DBLP profile ↗ORCID search ↗
5. Consistency Models Made Easy
   ICLR 2025 ·

   Zhengyang Geng

   DBLP profile ↗ORCID search ↗
6. Context-Parametric Inversion: Why Instruction Finetuning May Not Actually Improve Context Reliance
   ICLR 2025 ·

   Sachin Goyal

   DBLP profile ↗ORCID search ↗
7. Contextures: Representations from Contexts
   ICML 2025 ·

   Runtian Zhai

   DBLP profile ↗ORCID search ↗
8. Idiosyncrasies in Large Language Models
   ICML 2025 ·

   Mingjie Sun

   DBLP profile ↗ORCID search ↗
9. Inference Optimal VLMs Need Fewer Visual Tokens and More Parameters
   ICLR 2025 ·

   Kevin Y. Li

   DBLP profile ↗ORCID search ↗
10. Mean Flows for One-step Generative Modeling
    NeurIPS 2025 ·

    Zhengyang Geng

    DBLP profile ↗ORCID search ↗
11. OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents
    NeurIPS 2025 ·

    Thomas Kuntz

    DBLP profile ↗ORCID search ↗
12. OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics
    NeurIPS 2025 ·

    Vineeth Dorna

    DBLP profile ↗ORCID search ↗
13. Predicting the Performance of Black-box Language Models with Follow-up Queries
    NeurIPS 2025 ·

    Dylan Sam

    DBLP profile ↗ORCID search ↗
14. Safety Pretraining: Toward the Next Generation of Safe AI
    NeurIPS 2025 ·

    Pratyush Maini

    DBLP profile ↗ORCID search ↗
15. Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition
    NeurIPS 2025 ·

    Andy Zou

    DBLP profile ↗ORCID search ↗
16. Theory of Agreement-on-the-Line in Linear Models and Gaussian Data
    AISTATS 2025 ·

    Christina Baek

    DBLP profile ↗ORCID search ↗
17. Thirty-Ninth AAAI Conference on Artificial Intelligence, Thirty-Seventh Conference on Innovative Applications of Artificial Intelligence, Fifteenth Symposium on Educational Advances in Artificial Intelligence, AAAI 2025, Philadelphia, PA, USA, February 25 - March 4, 2025
    AAAI 2025 ·

    Toby Walsh

    DBLP profile ↗ORCID search ↗
18. Training a Generally Curious Agent
    ICML 2025 ·

    Fahim Tajwar

    DBLP profile ↗ORCID search ↗
19. Understanding Optimization in Deep Learning with Central Flows
    ICLR 2025 ·

    Jeremy Cohen

    DBLP profile ↗ORCID search ↗
20. Unnatural Languages Are Not Bugs but Features for LLMs
    ICML 2025 ·

    Keyu Duan

    DBLP profile ↗ORCID search ↗
21. A Simple and Effective Pruning Approach for Large Language Models
    ICLR 2024 ·

    Mingjie Sun

    DBLP profile ↗ORCID search ↗
22. Computing Low-Entropy Couplings for Large-Support Distributions
    UAI 2024 ·

    Samuel Sokota

    DBLP profile ↗ORCID search ↗
23. DART: Implicit Doppler Tomography for Radar Novel View Synthesis
    CVPR 2024 ·

    Tianshu Huang

    DBLP profile ↗ORCID search ↗
24. Diffusing Differentiable Representations
    NeurIPS 2024 ·

    Yash Savani

    DBLP profile ↗ORCID search ↗
25. Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024
    ICML 2024 ·

    Ruslan Salakhutdinov

    DBLP profile ↗ORCID search ↗
26. From Variance to Veracity: Unbundling and Mitigating Gradient Variance in Differentiable Bundle Adjustment Layers
    CVPR 2024 ·

    Swaminathan Gurumurthy

    DBLP profile ↗ORCID search ↗
27. Improving Alignment and Robustness with Circuit Breakers
    NeurIPS 2024 ·

    Andy Zou

    DBLP profile ↗ORCID search ↗
28. Manifold Preserving Guided Diffusion
    ICLR 2024 ·

    Yutong He

    DBLP profile ↗ORCID search ↗
29. On the Joint Interaction of Models, Data, and Features
    ICLR 2024 ·

    Yiding Jiang

    DBLP profile ↗ORCID search ↗
30. One-Step Diffusion Distillation through Score Implicit Matching
    NeurIPS 2024 ·

    Weijian Luo

    DBLP profile ↗ORCID search ↗
31. Predicting the Performance of Foundation Models via Agreement-on-the-Line
    NeurIPS 2024 ·

    Rahul Saxena

    DBLP profile ↗ORCID search ↗
32. Rethinking LLM Memorization through the Lens of Adversarial Compression
    NeurIPS 2024 ·

    Avi Schwarzschild

    DBLP profile ↗ORCID search ↗
33. Scaling Laws for Data Filtering - Data Curation Cannot be Compute Agnostic
    CVPR 2024 ·

    Sachin Goyal

    DBLP profile ↗ORCID search ↗
34. T-MARS: Improving Visual Representations by Circumventing Text Feature Learning
    ICLR 2024 ·

    Pratyush Maini

    DBLP profile ↗ORCID search ↗
35. Test-Time Adaptation Induces Stronger Accuracy and Agreement-on-the-Line
    NeurIPS 2024 ·

    Eungyeup Kim

    DBLP profile ↗ORCID search ↗
36. The Update-Equivalence Framework for Decision-Time Planning
    ICLR 2024 ·

    Samuel Sokota

    DBLP profile ↗ORCID search ↗
37. Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models
    NeurIPS 2024 ·

    Aviv Bick

    DBLP profile ↗ORCID search ↗
38. Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression
    ICLR 2024 ·

    Runtian Zhai

    DBLP profile ↗ORCID search ↗
39. Understanding Hallucinations in Diffusion Models through Mode Interpolation
    NeurIPS 2024 ·

    Sumukh K. Aithal

    DBLP profile ↗ORCID search ↗
40. Understanding prompt engineering may not require rethinking generalization
    ICLR 2024 ·

    Victor Akinwande

    DBLP profile ↗ORCID search ↗
41. Why is SAM Robust to Label Noise?
    ICLR 2024 ·

    Christina Baek

    DBLP profile ↗ORCID search ↗