*: indicating equal contribution or alphabetic ordering.
Manuscripts
- AI-Assisted Generation of Difficult Math Questions
Vedant Shah, Dingli Yu, Kaifeng Lyu, Simon Park, Jiatong Yu, Yinghui He, Nan Rosemary Ke, Michael Mozer, Yoshua Bengio, Sanjeev Arora, Anirudh Goyal
Publications
- Weak-to-Strong Generalization Even in Random Feature Networks, Provably
Marko Medvedev*, Kaifeng Lyu*, Dingli Yu, Sanjeev Arora, Zhiyuan Li, Nathan Srebro
ICML 2025 - Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?
Simon Park*, Abhishek Panigrahi*, Yun Cheng*, Dingli Yu, Anirudh Goyal, Sanjeev Arora
ICML 2025 - ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty
Xindi Wu*, Dingli Yu*, Yangsibo Huang, Olga Russakovsky, Sanjeev Arora
NeurIPS 2024 Datasets and Benchmarks Track - Can Models Learn Skill Composition from Examples?
Haoyu Zhao, Simran Kaur, Dingli Yu, Anirudh Goyal, Sanjeev Arora
NeurIPS 2024 - Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates
Kaifeng Lyu*, Haoyu Zhao*, Xinran Gu*, Dingli Yu, Anirudh Goyal, Sanjeev Arora
NeurIPS 2024 - Skill-Mix: a Flexible and Expandable Family of Evaluations for AI models
Dingli Yu, Simran Kaur, Arushi Gupta, Jonah Brown-Cohen, Anirudh Goyal, Sanjeev Arora
ICLR 2024 - Tensor Programs VI: Feature Learning in Infinite-Depth Neural Networks
Greg Yang*, Dingli Yu*, Chen Zhu, Soufiane Hayou
ICLR 2024 - A Kernel-Based View of Language Model Fine-Tuning
Sadhika Malladi, Alexander Wettig, Dingli Yu, Danqi Chen, Sanjeev Arora.
ICML 2023 - Fast Mixing of Stochastic Gradient Descent with Normalization and Weight Decay
Zhiyuan Li*, Tianhao Wang*, Dingli Yu*.
NeurIPS 2022 - New Definitions and Evaluations for Saliency Methods: Staying Intrinsic, Complete and Sound
Arushi Gupta*, Nikunj Saunshi*, Dingli Yu*, Kaifeng Lyu, Sanjeev Arora.
NeurIPS 2022 (Oral) - Enhanced Convolutional Neural Tangent Kernels
Zhiyuan Li*, Ruosong Wang*, Dingli Yu*, Simon S. Du, Wei Hu, Ruslan Salakhutdinov, and Sanjeev Arora - Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks
Sanjeev Arora*, Simon S. Du*, Zhiyuan Li*, Ruslan Salakhutdinov*, Ruosong Wang*, and Dingli Yu*.
ICLR 2020 (Spotlight) - Simple and Effective Regularization Methods for Training on Noisily Labeled Data with Generalization Guarantee
Wei Hu*, Zhiyuan Li*, and Dingli Yu*.
ICLR 2020 - Characterization of group-strategyproof mechanisms for facility location in strictly convex space
Pingzhong Tang*, Dingli Yu*, and Shengyu Zhao*.
EC-20 - A Partisan Districting Protocol with Provably Nonpartisan Outcomes.
Wesley Pegden*, Ariel D. Procaccia*, and Dingli Yu*.
Press coverage: The Washington Post (op-ed), Slate, Pittsburgh Post-Gazette, New Scientist, Axios, WDET (radio), Wisconsin Public Radio - Balanced Outcomes in Wage Bargaining
Pingzhong Tang*, and Dingli Yu*.
AAMAS-18 - Fair Rent Division on a Budget.
Ariel D. Procaccia*, Rodrigo A. Velez*, and Dingli Yu*.
AAAI-18
Dingli Yu 