Druv Pai

According to our database, Druv Pai authored at least 15 papers between 2022 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2025

Attention-Only Transformers via Unrolled Subspace Denoising.

Peng Wang, Yifu Lu, Yaodong Yu, Druv Pai, Qing Qu, Yi Ma

CoRR, June, 2025

Simplifying DINO via Coding Rate Regularization.

Ziyang Wu, Jingyuan Zhang, Druv Pai, Xudong Wang, Chandan Singh, Jianwei Yang, Jianfeng Gao, Yi Ma

CoRR, February, 2025

Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction.

Ziyang Wu, Tianjiao Ding, Yifu Lu, Druv Pai, Jingyuan Zhang, Weida Wang, Yaodong Yu, Yi Ma, Benjamin David Haeffele

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

Representation Learning via Manifold Flattening and Reconstruction.

Michael Psenka, Druv Pai, Vishal Raman, Shankar Sastry, Yi Ma

J. Mach. Learn. Res., 2024

Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs.

Tianyu Guo, Druv Pai, Yu Bai, Jiantao Jiao, Michael I. Jordan, Song Mei

CoRR, 2024

Congestion Pricing for Efficiency and Equity: Theory and Applications to the San Francisco Bay Area.

Chinmay Maheshwari, Kshitij Kulkarni, Druv Pai, Jiarui Yang, Manxi Wu, Shankar Sastry

CoRR, 2024

Scaling White-Box Transformers for Vision.

Jinrui Yang, Xianhang Li, Druv Pai, Yuyin Zhou, Yi Ma, Yaodong Yu, Cihang Xie

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

A Global Geometric Analysis of Maximal Coding Rate Reduction.

Peng Wang, Huikang Liu, Druv Pai, Yaodong Yu, Zhihui Zhu, Qing Qu, Yi Ma

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Masked Completion via Structured Diffusion with White-Box Transformers.

Druv Pai, Sam Buchanan, Ziyang Wu, Yaodong Yu, Yi Ma

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Emergence of Segmentation with Minimalistic White-Box Transformers.

Yaodong Yu, Tianzhe Chu, Shengbang Tong, Ziyang Wu, Druv Pai, Sam Buchanan, Yi Ma

Proceedings of the Conference on Parsimony and Learning, 2024

Closed-Loop Transcription via Convolutional Sparse Coding.

Xili Dai, Ke Chen, Shengbang Tong, Jingyuan Zhang, Xingjian Gao, Mingyang Li, Druv Pai, Yuexiang Zhai, Xiaojun Yuan, Heung-Yeung Shum, Lionel M. Ni, Yi Ma

Proceedings of the Conference on Parsimony and Learning, 2024

2023

Pursuit of a discriminative representation for multiple subspaces via sequential games.

Druv Pai, Michael Psenka, Chih-Yuan Chiu, Manxi Wu, Edgar Dobriban, Yi Ma

J. Frankl. Inst., 2023

White-Box Transformers via Sparse Rate Reduction: Compression Is All There Is?

Yaodong Yu, Sam Buchanan, Druv Pai, Tianzhe Chu, Ziyang Wu, Shengbang Tong, Hao Bai, Yuexiang Zhai, Benjamin D. Haeffele, Yi Ma

CoRR, 2023

White-Box Transformers via Sparse Rate Reduction.

Yaodong Yu, Sam Buchanan, Druv Pai, Tianzhe Chu, Ziyang Wu, Shengbang Tong, Benjamin D. Haeffele, Yi Ma

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

Independent and Decentralized Learning in Markov Potential Games.

Chinmay Maheshwari, Manxi Wu, Druv Pai, Shankar Sastry

CoRR, 2022