Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws
Yiding Jiang*, Allan Zhou*, Zhili Feng, Sadhika Malladi, J. Zico Kolter
Arxiv, 2024  |  [code]

Improving Generalization on the ProcGen Benchmark with Simple Architectural Changes and Scale
Andrew Jesson, Yiding Jiang
Arxiv, 2024  |  [code]

Automated Black-box Prompt Engineering for Personalized Text-to-Image Generation
Yutong He, Alexander Robey, Naoki Murata, Yiding Jiang, Joshua Williams, George J. Pappas, Hamed Hassani, Yuki Mitsufuji, Ruslan Salakhutdinov, J. Zico Kolter
Arxiv, 2024

On the Joint Interaction of Models, Data, and Features
Yiding Jiang, Christina Baek, J. Zico Kolter
ICLR, 2024 (oral)

Understanding prompt engineering may not require rethinking generalization
Victor Akinwande, Yiding Jiang, Dylan Sam, J. Zico Kolter
ICLR, 2024
Sampling and Optimization in Discrete Space workshop, ICML 2023 (Outstanding Paper)

Language models are weak learners
Hariharan Manikandan, Yiding Jiang, J. Zico Kolter
NeurIPS, 2023

Neural Functional Transformers
Allan Zhou, Kaien Yang, Yiding Jiang, Kaylee Burns, Winnie Xu, Samuel Sokota, J. Zico Kolter, Chelsea Finn
NeurIPS, 2023

Permutation equivariant neural functionals
Allan Zhou, Kaien Yang, Kaylee Burns, Adriano Cardace, Yiding Jiang, Samuel Sokota, J. Zico Kolter, Chelsea Finn
NeurIPS, 2023

On the Importance of Exploration for Generalization in Reinforcement Learning
Yiding Jiang, J. Zico Kolter, Roberta Raileanu
NeurIPS, 2023  |  [code]

Learning Options via Compression
Yiding Jiang*, Evan Z. Liu*, Benjamin Eysenbach, J. Zico Kolter, Chelsea Finn
NeurIPS, 2022  |  [code]

Agreement-on-the-line: Predicting the Performance of Neural Networks under Distribution Shift
Christina Baek, Yiding Jiang, Aditi Raghunathan, J. Zico Kolter
NeurIPS, 2022 (oral)

Assessing Generalization of SGD via Disagreement
Yiding Jiang*, Vaishnavh Nagarajan*, Christina Baek, J. Zico Kolter
ICLR, 2022 (spotlight)  |  [blog post]

Methods and Analysis of The First Competition in Predicting Generalization of Deep Learning
Yiding Jiang, Parth Natekar*, Manik Sharma*, Sumukh K Aithal*, Dhruva Kashyap*,
Natarajan Subramanyam*, Carlos Lassance*, Daniel M. Roy, Gintare Karolina Dziugaite, Suriya Gunasekar,
Isabelle Guyon, Pierre Foret, Scott Yak, Hossein Mobahi, Behnam Neyshabur*, Samy Bengio
PMLR: NeurIPS 2020 Competition and Demonstration Track, 2020  |  [competition page] [Codalab] [competition dataset] [competition code]

Fantastic Generalization Measures and Where to Find Them
Yiding Jiang*, Behnam Neyshabur*, Hossein Mobahi, Dilip Krishnan, Samy Bengio
ICLR, 2020
"Science meets the Engineering of Deep Learning" workshop, NeurIPS 2019 (oral)

Observational Overfitting in Reinforcement Learning
Xingyou Song, Yiding Jiang, Stephen Tu, Yilun Du, Behnam Neyshabur
ICLR, 2020

Language as an Abstraction for Hierarchical Deep Reinforcement Learning
Yiding Jiang, Shixiang Gu, Kevin Murphy, Chelsea Finn
NeurIPS, 2019  |  [project page] [environment]

Adversarial Grasp Objects
David Wang*, David Tseng*, Pusong Li*, Yiding Jiang*, Menglong Guo, Michael Danielczuk, Jeffrey Mahler, Jeffrey Ichnowski, Ken Goldberg
CASE, 2019  |  IEEE Spectrum article

Predicting the Generalization Gap in Deep Networks with Margin Distributions
Yiding Jiang, Dilip Krishnan, Hossein Mobahi, Samy Bengio
ICLR, 2019  |  [blog post]

Ask & Explore: Grounded Question Answering for Curiosity-Driven Exploration
Jivat Neet Kaur, Yiding Jiang, Paul Pu Liang
Arxiv, 2021
Workshop on Embodied Multimodal Learning, ICLR 2021

CLEVR-Robot Environment

The CLEVR-Robot environment is a reinforcement learning environment that aims to provide a research platform for developing RL agents at the intersection of vision, language, and continuous/discrete control.

Deep Model Generalization Dataset (DEMOGEN)

The DEMOGEN dataset is a collection of 756 trained neural network models and supporting code. This is the same dataset used in our work “Predicting the Generalization Gap in Deep Networks with Margin Distributions”, and is, to our knowledge, the first dataset of models specifically for studying generalization.

City2City

City2City is a project that restyles Google Street View images of one city with another city’s aesthetic style.