ICLR 2024 Conference Submissions

Lipsum-FT: Robust Fine-Tuning of Zero-Shot Models Using Random Text Guidance
Giung Nam, Byeongho Heo, Juho Lee
- Published: 16 Jan 2024, Last Modified: 20 Mar 2024
- ICLR 2024 poster
- Readers: Everyone
Evade ChatGPT Detectors via A Single Space
Shuyang Cai, Wanyun Cui
- 23 Sept 2023 (modified: 25 Mar 2024)
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
The Closeness of In-Context Learning and Weight Shifting for Softmax Regression
Shuai Li, Zhao Song, Yu Xia, Tong Yu, Tianyi Zhou
- 23 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
CoSDA: Continual Source-Free Domain Adaptation
Haozhe Feng, Zhaorui Yang, Hesun Chen, Tianyu Pang, Chao Du, Minfeng Zhu, Wei Chen, Shuicheng YAN
- 23 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies
Xiangyu Liu, Chenghao Deng, Yanchao Sun, Yongyuan Liang, Furong Huang
- Published: 16 Jan 2024, Last Modified: 09 Apr 2024
- ICLR 2024 spotlight
- Readers: Everyone
Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEs
Ilan Naiman, N. Benjamin Erichson, Pu Ren, Michael W. Mahoney, Omri Azencot
- Published: 16 Jan 2024, Last Modified: 10 Mar 2024
- ICLR 2024 poster
- Readers: Everyone
Complex Logical Reasoning over Knowledge Graphs using Large Language Models
Nurendra Choudhary, Chandan K. Reddy
- 23 Sept 2023 (modified: 25 Mar 2024)
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
Generating Pragmatic Examples to Train Neural Program Synthesizers
Saujas Vaduguru, Daniel Fried, Yewen Pu
- Published: 16 Jan 2024, Last Modified: 11 Apr 2024
- ICLR 2024 poster
- Readers: Everyone
Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness
Bohang Zhang, Jingchu Gai, Yiheng Du, Qiwei Ye, Di He, Liwei Wang
- Published: 16 Jan 2024, Last Modified: 15 Mar 2024
- ICLR 2024 oral
- Readers: Everyone
Fairness Feedback Loops: Training on Synthetic Data Amplifies Bias
Sierra Calanda Wyllie, Ilia Shumailov, Nicolas Papernot
- 23 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Making RL with Preference-based Feedback Efficient via Randomization
Runzhe Wu, Wen Sun
- Published: 16 Jan 2024, Last Modified: 12 Mar 2024
- ICLR 2024 poster
- Readers: Everyone
On the Possibilities of AI-Generated Text Detection: A Sample Complexity Analysis
Souradip Chakraborty, Amrit Bedi, Sicheng Zhu, Bang An, Dinesh Manocha, Furong Huang
- 23 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Reflective Policy Optimization
Yaozhong Gan, Renye Yan, Zhe Wu, Junliang Xing
- 23 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
GPT-Fathom: Benchmarking Large Language Models to Decipher the Evolutionary Path towards GPT-4 and Beyond
Shen Zheng, Yuyu Zhang, Yijie Zhu, Chenguang Xi, Pengyang Gao, zhou Xun, Kevin Chang
- 23 Sept 2023 (modified: 25 Mar 2024)
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
User Inference Attacks on Large Language Models
Nikhil Kandpal, Krishna Pillutla, Alina Oprea, Peter Kairouz, Christopher A. Choquette-Choo, Zheng Xu
- 23 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
CLIP as Multi-Task Multi-Kernel Learning
Tianjun Ke, Yucong Lin, Xingpeng Xia, Jiaheng Yin, Jiaxing Xu, Tianxi Cai, Junwei Lu
- 23 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy
Pingzhi Li, Zhenyu Zhang, Prateek Yadav, Yi-Lin Sung, Yu Cheng, Mohit Bansal, Tianlong Chen
- Published: 16 Jan 2024, Last Modified: 07 Mar 2024
- ICLR 2024 spotlight
- Readers: Everyone
RoboGPT : An intelligent agent of making embodied long-term decisions for daily instruction tasks
Yaran Chen, Wenbo Cui, Yuanwen Chen, Mining Tan, Xinyao Zhang, Dongbin Zhao, He Wang
- 23 Sept 2023 (modified: 25 Mar 2024)
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
Adaptive Regret for Bandits Made Possible: Two Queries Suffice
Zhou Lu, Qiuyi Zhang, Xinyi Chen, Fred Zhang, David Woodruff, Elad Hazan
- Published: 16 Jan 2024, Last Modified: 16 Apr 2024
- ICLR 2024 poster
- Readers: Everyone
Universal Off-Policy Selection for Human-Centric Systems via Participant Sub-grouping
Ge Gao, Xi Yang, Qitong Gao, Song Ju, Miroslav Pajic, Min Chi
- 23 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Delayed Local-SGD for Distributed Learning with Linear Speedup
Xiaolu Wang, Zijian Li, Jun Zhang
- 23 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
AudoFormer: An Efficient Transformer with Consistent Auxiliary Domain for Source-free Domain Adaptation
Renrong Shao, Wei Zhang, Kangyang Luo, Qin Li, Jun Wang
- 23 Sept 2023 (modified: 25 Mar 2024)
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
Generalized Activation via Multivariate Projection
Jiayun Li, Yuxiao Cheng, Zhuofan Xia, Yilin Mo, Gao Huang
- 23 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Conformal Prediction for Deep Classifier via Label Ranking
Jianguo Huang, HuaJun Xi, Linjun Zhang, Huaxiu Yao, Yue Qiu, Hongxin Wei
- 23 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Symmetrized Schrödinger Bridge Matching
Dong-Sig Han, Jaein Kim, HEE BIN YOO, Byoung-Tak Zhang
- 23 Sept 2023 (modified: 25 Mar 2024)
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone