Følg
Dingli Yu
Dingli Yu
Microsoft Research
Verifisert e-postadresse på microsoft.com - Startside
Tittel
Sitert av
Sitert av
År
Harnessing the power of infinitely wide deep nets on small-data tasks
S Arora, SS Du, Z Li, R Salakhutdinov, R Wang, D Yu
arXiv preprint arXiv:1910.01663, 2019
1962019
Enhanced convolutional neural tangent kernels
Z Li, R Wang, D Yu, SS Du, W Hu, R Salakhutdinov, S Arora
arXiv preprint arXiv:1911.00809, 2019
1402019
Simple and effective regularization methods for training on noisily labeled data with generalization guarantee
W Hu, Z Li, D Yu
arXiv preprint arXiv:1905.11368, 2019
912019
A kernel-based view of language model fine-tuning
S Malladi, A Wettig, D Yu, D Chen, S Arora
International Conference on Machine Learning, 23610-23641, 2023
682023
Tensor programs vi: Feature learning in infinite-depth neural networks
G Yang, D Yu, C Zhu, S Hayou
arXiv preprint arXiv:2310.02244, 2023
39*2023
A partisan districting protocol with provably nonpartisan outcomes
W Pegden, AD Procaccia, D Yu
arXiv preprint arXiv:1710.08781, 2017
382017
Skill-Mix: A flexible and expandable family of evaluations for AI models
D Yu, S Kaur, A Gupta, J Brown-Cohen, A Goyal, S Arora
arXiv preprint arXiv:2310.17567, 2023
252023
Characterization of group-strategyproof mechanisms for facility location in strictly convex space
P Tang, D Yu, S Zhao
Proceedings of the 21st ACM Conference on Economics and Computation, 133-157, 2020
232020
Keeping llms aligned after fine-tuning: The crucial role of prompt templates
K Lyu, H Zhao, X Gu, D Yu, A Goyal, S Arora
arXiv preprint arXiv:2402.18540, 2024
222024
Fast mixing of stochastic gradient descent with normalization and weight decay
Z Li, T Wang, D Yu
Advances in Neural Information Processing Systems 35, 9233-9248, 2022
212022
Fair rent division on a budget
A Procaccia, R Velez, D Yu
Proceedings of the AAAI Conference on Artificial Intelligence 32 (1), 2018
182018
Conceptmix: A compositional image generation benchmark with controllable difficulty
X Wu, D Yu, Y Huang, O Russakovsky, S Arora
arXiv preprint arXiv:2408.14339, 2024
82024
Phi-4 technical report
M Abdin, J Aneja, H Behl, S Bubeck, R Eldan, S Gunasekar, M Harrison, ...
arXiv preprint arXiv:2412.08905, 2024
72024
New definitions and evaluations for saliency methods: Staying intrinsic, complete and sound
A Gupta, N Saunshi, D Yu, K Lyu, S Arora
Advances in Neural Information Processing Systems 35, 33120-33133, 2022
72022
Ai-assisted generation of difficult math questions
V Shah, D Yu, K Lyu, S Park, J Yu, Y He, NR Ke, M Mozer, Y Bengio, ...
arXiv preprint arXiv:2407.21009, 2024
52024
Can Models Learn Skill Composition from Examples?
H Zhao, S Kaur, D Yu, A Goyal, S Arora
arXiv preprint arXiv:2409.19808, 2024
12024
Balanced Outcomes in Wage Bargaining.
P Tang, D Yu
AAMAS, 2091-2093, 2018
12018
Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?
S Park, A Panigrahi, Y Cheng, D Yu, A Goyal, S Arora
arXiv preprint arXiv:2501.02669, 2025
2025
Efficient Scaling of Large Models: Principles in Optimization and Data Aspects
D Yu
Princeton University, 2024
2024
Systemet kan ikke utføre handlingen. Prøv på nytt senere.
Artikler 1–19