Author

Tianle Cai

Observed name: Cai, Tianle

Institutions: Princeton University, Peking University, ByteDance (China)

Observed institutions: Princeton University, Peking University, ByteDance (China)

ORCID: 0009-0008-8644-3895

Observed ORCID: 0009-0008-8644-3895

OpenAlex ID: A5083555133

Do Transformers Really Perform Badly for Graph Representation

2021 · Chengxuan Ying, Tianle Cai, et al. · neural information processing systems · 489

Do Transformers Really Perform Bad for Graph Representation?

2021 · Ying, Chengxuan, Cai, Tianle, et al. · arXiv (Cornell University) · 146

GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training

2020 · Cai, Tianle, Luo, Shengjie, et al. · arXiv (Cornell University) · 103

Adversarially Robust Generalization Just Requires More Unlabeled Data

2019 · Zhai, Runtian, Cai, Tianle, et al. · arXiv (Cornell University) · 79

SnapKV: LLM Knows What You are Looking for Before Generation

2024 · Yuhong Li, Yingbing Huang, et al. · neural information processing systems · 71

Convergence of Adversarial Training in Overparametrized Neural Networks

2019 · Gao, Ruiqi, Cai, Tianle, et al. · arXiv (Cornell University) · 59

DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models

2024 · Muyang Li, Tianle Cai, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 46

Towards a Theoretical Framework of Out-of-Distribution Generalization

2021 · Ye, Haotian, Xie, Chuanlong, et al. · arXiv (Cornell University) · 46

REST: Retrieval-Based Speculative Decoding

2024 · Zhenyu He, Zexuan Zhong, et al. · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · 34

Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot

2020 · Su, Jingtong, Chen, Yihang, et al. · arXiv (Cornell University) · 30

Large Language Models as Tool Makers

2023 · Cai, Tianle, Wang, Xuezhi, et al. · arXiv (Cornell University) · 28

Gram-Gauss-Newton Method: Learning Overparameterized Neural Networks for Regression Problems

2019 · Cai, Tianle, Gao, Ruiqi, et al. · arXiv (Cornell University) · 28

Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads

2024 · Cai, Tianle, Li, Yuhong, et al. · arXiv (Cornell University) · 27

What Makes Convolutional Models Great on Long Sequence Modeling?

2022 · Li, Yuhong, Cai, Tianle, et al. · arXiv (Cornell University) · 24

Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding

2021 · Luo, Shengjie, Li, Shanda, et al. · arXiv (Cornell University) · 16

A Theory of Label Propagation for Subpopulation Shift

2021 · Cai, Tianle, Gao, Ruiqi, et al. · arXiv (Cornell University) · 16

RANDOM MASK: Towards Robust Convolutional Neural Networks

2020 · Luo, Tiange, Cai, Tianle, et al. · arXiv (Cornell University) · 16

Locally Differentially Private (Contextual) Bandits Learning

2020 · Zheng, Kai, Cai, Tianle, et al. · arXiv (Cornell University) · 16

Towards Certifying L-infinity Robustness using Neural Networks with L-inf-dist Neurons

2021 · Zhang, Bohang, Cai, Tianle, et al. · arXiv (Cornell University) · 12

Is Vertical Logistic Regression Privacy-Preserving? A Comprehensive Privacy Analysis and Beyond

2022 · Hu, Yuzheng, Cai, Tianle, et al. · arXiv (Cornell University) · 8

FlexAttention for Efficient High-Resolution Vision-Language Models

2024 · Junyan Li, Delin Chen, et al. · Lecture notes in computer science · 7

BitDelta: Your Fine-Tune May Only Be Worth One Bit

2024 · James Liu, Guangxuan Xiao, et al. · neural information processing systems · 5

Training-Free Activation Sparsity in Large Language Models

2024 · Liu, James, Ponnusamy, Pragaash, et al. · arXiv (Cornell University) · 4

JetMoE: Reaching Llama2 Performance with 0.1M Dollars

2024 · Shen, Yikang, Guo, Zhen, et al. · arXiv (Cornell University) · 4

First Place Solution of KDD Cup 2021 & OGB Large-Scale Challenge Graph Prediction Track

2021 · Ying, Chengxuan, Yang, Mingqi, et al. · arXiv (Cornell University) · 4

Works count: 53

Citation count: 1,338

H-index: 16

I10-index: 19