YY
Yaodong Yu
cs.LGcs.CVstat.MLcs.AIcs.CLcs.CRmath.OCcs.CYcs.DCcs.GT
On Valency
published · living versionsW_aevsngy8·v1 · currentpublished
Trading Inference-Time Compute for Adversarial Robustness
with Wojciech Zaremba, Evgenia Nitishinskaya, Boaz Barak, Stephanie Lin +6
1 version
Preprints & journals
24 papers in the corpus · 2021–2026Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency.41179969 · Wang, Feng, Yang, Timing, Yu, Yaodong et al.2026 · 1 citationProceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2025;2025:30157-30166
OpenAI GPT-5 System Card2601.03267v2 · Aaditya Singh, Adam Fry, Adam Perelman et al.2025 · 18 citationsarXiv
Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More2502.03738v2 · Feng Wang, Yaodong Yu, Guoyizhe Wei et al.2025 · 3 citationsarXiv
A Global Geometric Analysis of Maximal Coding Rate Reduction2406.01909v2 · Peng Wang, Huikang Liu, Druv Pai et al.2024 · 0 citationsarXiv
Attention-Only Transformers via Unrolled Subspace Denoising2506.03790v1 · Peng Wang, Yifu Lu, Yaodong Yu et al.2025 · 0 citationsarXiv
Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency2410.07599v2 · Feng Wang, Timing Yang, Yaodong Yu et al.2024 · 1 citationarXiv
Trading Inference-Time Compute for Adversarial Robustness2501.18841v1 · Wojciech Zaremba, Evgenia Nitishinskaya, Boaz Barak et al.2025 · 0 citationsarXivon Valency
Scaling White-Box Transformers for Vision2405.20299v4 · Jinrui Yang, Xianhang Li, Druv Pai et al.2024 · 5 citationsarXiv
Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction2412.17810v1 · Ziyang Wu, Tianjiao Ding, Yifu Lu et al.2024 · 7 citationsarXiv
M-VAR: Decoupled Scale-wise Autoregressive Modeling for High-Quality Image Generation2411.10433v1 · Sucheng Ren, Yaodong Yu, Nataniel Ruiz et al.2024 · 0 citationsarXiv
Differentially Private Representation Learning via Image Captioning2403.02506v2 · Tom Sander, Yaodong Yu, Maziar Sanjabi et al.2024 · 3 citationsarXiv
White-Box Transformers via Sparse Rate Reduction: Compression Is All There Is?2311.13110v4 · Yaodong Yu, Sam Buchanan, Druv Pai et al.2023 · 4 citationsarXiv
Accuracy on the wrong line: On the pitfalls of noisy data for out-of-distribution generalisation2406.19049v1 · Amartya Sanyal, Yaxi Hu, Yaodong Yu et al.2024 · 1 citationarXiv
Masked Completion via Structured Diffusion with White-Box Transformers2404.02446v1 · Druv Pai, Ziyang Wu, Sam Buchanan et al.2024 · 0 citationsarXiv
A Study on the Calibration of In-context Learning2312.04021v4 · Hanlin Zhang, Yi-Fan Zhang, Yaodong Yu et al.2023 · 3 citationsarXiv
Emergence of Segmentation with Minimalistic White-Box Transformers2308.16271v1 · Yaodong Yu, Tianzhe Chu, Shengbang Tong et al.2023 · 3 citationsarXiv
Scaff-PD: Communication Efficient Fair and Robust Federated Learning2307.13381v1 · Yaodong Yu, Sai Praneeth Karimireddy, Yi Ma et al.2023 · 0 citationsarXiv
ViP: A Differentially Private Foundation Model for Computer Vision2306.08842v2 · Yaodong Yu, Maziar Sanjabi, Yi Ma et al.2023 · 0 citationsarXiv
Federated Conformal Predictors for Distributed Uncertainty Quantification2305.17564v2 · Charles Lu, Yaodong Yu, Sai Praneeth Karimireddy et al.2023 · 1 citationarXiv
Conditional Supervised Contrastive Learning for Fair Text Classification2205.11485v2 · Jianfeng Chi, William Shand, Yaodong Yu et al.2022 · 10 citationsarXiv
Online Nonsubmodular Minimization with Delayed Costs: From Full Information to Bandit Feedback2205.07217v2 · Tianyi Lin, Aldo Pacchiano, Yaodong Yu et al.2022 · 0 citationsarXiv
On the Convergence of Stochastic Extragradient for Bilinear Games using Restarted Iteration Averaging2107.00464v4 · Chris Junchi Li, Yaodong Yu, Nicolas Loizou et al.2021 · 1 citationarXiv
Predicting Out-of-Distribution Error with the Projection Norm2202.05834v1 · Yaodong Yu, Zitong Yang, Alexander Wei et al.2022 · 4 citationsarXiv
The Effect of Model Size on Worst-Group Generalization2112.04094v1 · Alan Pham, Eunice Chan, Vikranth Srivatsa et al.2021 · 0 citationsarXiv
Career total: 40 works. 24 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.