ICML 2023 Conference Submissions

Quantifying the Knowledge in GNNs for Reliable Distillation into MLPs
Lirong Wu, Haitao Lin, Yufei Huang, Stan Z. Li
- Published: 24 Apr 2023, Last Modified: 15 Jun 2023
- ICML 2023 Poster
- Readers: Everyone
Composer: Creative and Controllable Image Synthesis with Composable Conditions
Lianghua Huang, Di Chen, Yu Liu, Yujun Shen, Deli Zhao, Jingren Zhou
- Published: 24 Apr 2023, Last Modified: 15 Jun 2023
- ICML 2023 Poster
- Readers: Everyone
Sketching Meets Differential Privacy: Fast Algorithm for Dynamic Kronecker Projection Maintenance
Zhao Song, Xin Yang, Yuanyuan Yang, Lichen Zhang
- Published: 24 Apr 2023, Last Modified: 21 Jun 2023
- ICML 2023 Poster
- Readers: Everyone
Robust Perception through Equivariance
Chengzhi Mao, Lingyu Zhang, Abhishek Vaibhav Joshi, Junfeng Yang, Hao Wang, Carl Vondrick
- Published: 24 Apr 2023, Last Modified: 21 Jun 2023
- ICML 2023 Poster
- Readers: Everyone
Understanding and Defending Patched-based Adversarial Attacks for Vision Transformer
Liang Liu, Yanan Guo, Youtao Zhang, Jun Yang
- Published: 24 Apr 2023, Last Modified: 21 Jun 2023
- ICML 2023 Poster
- Readers: Everyone
Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights?
Ruisi Cai, Zhenyu Zhang, Zhangyang Wang
- Published: 24 Apr 2023, Last Modified: 21 Jun 2023
- ICML 2023 Poster
- Readers: Everyone
Estimating Heterogeneous Treatment Effects: Mutual Information Bounds and Learning Algorithms
Xingzhuo Guo, Yuchen Zhang, Jianmin Wang, Mingsheng Long
- Published: 24 Apr 2023, Last Modified: 15 Jun 2023
- ICML 2023 Poster
- Readers: Everyone
On the Optimality of Misspecified Kernel Ridge Regression
Haobo Zhang, Yicheng Li, Weihao Lu, Qian Lin
- Published: 24 Apr 2023, Last Modified: 21 Jun 2023
- ICML 2023 Poster
- Readers: Everyone
Multi-View Masked World Models for Visual Robotic Manipulation
Younggyo Seo, Junsu Kim, Stephen James, Kimin Lee, Jinwoo Shin, Pieter Abbeel
- Published: 24 Apr 2023, Last Modified: 15 Jun 2023
- ICML 2023 Poster
- Readers: Everyone
Performative Recommendation: Diversifying Content via Strategic Incentives
Itay Eilat, Nir Rosenfeld
- Published: 24 Apr 2023, Last Modified: 15 Jun 2023
- ICML 2023 Poster
- Readers: Everyone
How Does Information Bottleneck Help Deep Learning?
Kenji Kawaguchi, Zhun Deng, Xu Ji, Jiaoyang Huang
- Published: 24 Apr 2023, Last Modified: 15 Jun 2023
- ICML 2023 Poster
- Readers: Everyone
Momentum Ensures Convergence of SIGNSGD under Weaker Assumptions
Tao Sun, Qingsong Wang, Dongsheng Li, Bao Wang
- Published: 24 Apr 2023, Last Modified: 21 Jun 2023
- ICML 2023 Poster
- Readers: Everyone
Lowering the Pre-training Tax for Gradient-based Subset Training: A Lightweight Distributed Pre-Training Toolkit
Yeonju Ro, Zhangyang Wang, Vijay Chidambaram, Aditya Akella
- Published: 24 Apr 2023, Last Modified: 21 Jun 2023
- ICML 2023 Poster
- Readers: Everyone
Eliminating Adversarial Noise via Information Discard and Robust Representation Restoration
Dawei Zhou, Yukun Chen, Nannan Wang, Decheng Liu, Xinbo Gao, Tongliang Liu
- Published: 24 Apr 2023, Last Modified: 15 Jun 2023
- ICML 2023 Poster
- Readers: Everyone
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
Junnan Li, Dongxu Li, Silvio Savarese, Steven Hoi
- Published: 24 Apr 2023, Last Modified: 21 Jun 2023
- ICML 2023 Poster
- Readers: Everyone
Gradient Descent Finds the Global Optima of Two-Layer Physics-Informed Neural Networks
Yihang Gao, Yiqi Gu, Michael Ng
- Published: 24 Apr 2023, Last Modified: 21 Jun 2023
- ICML 2023 Poster
- Readers: Everyone
A Nearly-Optimal Bound for Fast Regression with $\ell_\infty$ Guarantee
Zhao Song, Mingquan Ye, Junze Yin, Lichen Zhang
- Published: 24 Apr 2023, Last Modified: 21 Jun 2023
- ICML 2023 Poster
- Readers: Everyone
Transcendental Idealism of Planner: Evaluating Perception from Planning Perspective for Autonomous Driving
Weixin Li, Xiaodong Yang
- Published: 24 Apr 2023, Last Modified: 21 Jun 2023
- ICML 2023 Poster
- Readers: Everyone
Attribute-Efficient PAC Learning of Low-Degree Polynomial Threshold Functions with Nasty Noise
Shiwei Zeng, Jie Shen
- Published: 24 Apr 2023, Last Modified: 21 Jun 2023
- ICML 2023 Poster
- Readers: Everyone
Consistency of Multiple Kernel Clustering
Weixuan Liang, Xinwang Liu, Yong Liu, Chuan Ma, Yunping Zhao, Zhe Liu, En Zhu
- Published: 24 Apr 2023, Last Modified: 21 Jun 2023
- ICML 2023 Poster
- Readers: Everyone
Towards Controlled Data Augmentations for Active Learning
Jianan Yang, Haobo Wang, Sai Wu, Gang Chen, Junbo Zhao
- Published: 24 Apr 2023, Last Modified: 15 Jun 2023
- ICML 2023 Poster
- Readers: Everyone
Bi-directional Masks for Efficient N:M Sparse Training
Yuxin Zhang, Yiting Luo, Mingbao Lin, Yunshan Zhong, JingJing Xie, Fei Chao, Rongrong Ji
- Published: 24 Apr 2023, Last Modified: 15 Jun 2023
- ICML 2023 Poster
- Readers: Everyone
The Virtues of Laziness in Model-based RL: A Unified Objective and Algorithms
Anirudh Vemula, Yuda Song, Aarti Singh, Drew Bagnell, Sanjiban Choudhury
- Published: 24 Apr 2023, Last Modified: 21 Jun 2023
- ICML 2023 Poster
- Readers: Everyone
Fair and Robust Estimation of Heterogeneous Treatment Effects for Policy Learning
Kwangho Kim, Jose R Zubizarreta
- Published: 24 Apr 2023, Last Modified: 21 Jun 2023
- ICML 2023 Poster
- Readers: Everyone
Controlled Text Generation with Natural Language Instructions
Wangchunshu Zhou, Yuchen Eleanor Jiang, Ethan Wilcox, Ryan Cotterell, Mrinmaya Sachan
- Published: 24 Apr 2023, Last Modified: 15 Jun 2023
- ICML 2023 Poster
- Readers: Everyone