ICLR 2025 Conference Submissions

Be More Diverse than the Most Diverse: Optimal Mixtures of Generative Models via Mixture-UCB Bandit Algorithms
Parham Rezaei, Farzan Farnia, Cheuk Ting Li
- Published: 22 Jan 2025, Last Modified: 03 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
TabReD: Analyzing Pitfalls and Filling the Gaps in Tabular Deep Learning Benchmarks
Ivan Rubachev, Nikolay Kartashev, Yury Gorishniy, Artem Babenko
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Spotlight
- Readers: Everyone
Linear-Time Sequence Modeling with MLPs
Chenwei Cui, Zehao Yan, Gedeon Muhawenayo, Hannah Kerner
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
SaTran: An efficient Transformer exploiting Spatiotemporal Redundancies for Satellite Image Time Series Representation Learning
Arshveer Kaur, Poonam Goyal, C Niranjan, Navneet Goyal
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Convergence of Adafactor under Non-Convex Smooth Stochastic Optimization
Yusu Hong, Junhong Lin
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Arithmetic Transformers Can Length-Generalize in Both Operand Length and Count
Hanseul Cho, Jaeyoung Cha, Srinadh Bhojanapalli, Chulhee Yun
- Published: 22 Jan 2025, Last Modified: 02 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
Training-Like Data Reconstruction
Pirzada Suhail, Amit Sethi
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Stealthy Shield Defense: A Conditional Mutual Information-Based Approach against Black-Box Model Inversion Attacks
Tianqu Zhuang, Hongyao Yu, Yixiang Qiu, Hao Fang, Bin Chen, Shu-Tao Xia
- Published: 22 Jan 2025, Last Modified: 18 May 2025
- ICLR 2025 Poster
- Readers: Everyone
A Computation and Communication Efficient Projection-free Algorithm for Decentralized Constrained Optimization
Tong He, Hao Di, Haishan Ye, Xiangyu Chang, Guang Dai, Ivor Tsang
- 28 Sept 2024 (modified: 04 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Democratizing online marketing with novel text-augmenting technologies: leveraging NLP in marketing with AMCN2
Neel Sirivara
- 28 Sept 2024 (modified: 09 Oct 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
LION: A bidirectional framework that trains like a Transformer and infers like an RNN
Arshia Afzal, Elias Abad Rocamora, Leyla Naz Candogan, Pol Puigdemont, Francesco Tonin, Yongtao Wu, Mahsa Shoaran, Volkan Cevher
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Relation Augmented Preferential Bayesian Optimization via Preference Propagation
Xiang Xia, Xiang Shu, Shuo Liu, Xingyu Lu, JUN ZHOU, Hong Qian
- 28 Sept 2024 (modified: 24 Jan 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Sparse Watermarking in LLMs with Enhanced Text Quality
Duy Cao Hoang, Thanh Quoc Hung Le, Rui Chu, Ping Li, Weijie Zhao, Yingjie Lao, Khoa D Doan
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Plasticity from Structured Sparsity: Mastering Continual Reinforcement Learning through Fine-grained Network Allocation and Dormant Neuron Exploration
Chengqi Zheng, Jianda Chen, Wen zheng terence Ng, Ivor Tsang, Haiyan Yin
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
NovelQA: Benchmarking Question Answering on Documents Exceeding 200K Tokens
Cunxiang Wang, Ruoxi Ning, Boqi Pan, Tonghui Wu, Qipeng Guo, Cheng Deng, Guangsheng Bao, Xiangkun Hu, Zheng Zhang, Qian Wang, Yue Zhang
- Published: 22 Jan 2025, Last Modified: 31 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Highlight Diffusion: Training-Free Attention Guided Acceleration for Text-to-Image Models
Kyuseok Nam, Yulhwa Kim, Jeongwoo Park
- 28 Sept 2024 (modified: 28 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Graphical-TS: An Interactive AI Pipeline for Multivariate Time Series with Ground-truth Graphical Modeling
Haixin Li, Yanke Li, Diego Paez-Granados
- 28 Sept 2024 (modified: 22 Jan 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Detecting and Approximating Redundant Computational Blocks in Neural Networks
Irene Cannistraci, Emanuele Rodolà, Bastian Rieck
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Look Before You Leap: Universal Emergent Mechanism for Retrieval in Language Models
Alexandre Variengien, Eric Winsor
- Published: 22 Jan 2025, Last Modified: 07 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Screener: Learning Conditional Distribution of Dense Self-supervised Representations for Unsupervised Pathology Segmentation in 3D Medical Images
Mikhail Goncharov, Eugenia Soboleva, Mariia Donskova, Ivan Oseledets, Marina Munkhoeva, Maxim Panov
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
A Multi-Power Law for Loss Curve Prediction Across Learning Rate Schedules
Kairong Luo, Haodong Wen, Shengding Hu, Zhenbo Sun, Zhiyuan Liu, Maosong Sun, Kaifeng Lyu, Wenguang Chen
- Published: 22 Jan 2025, Last Modified: 09 May 2025
- ICLR 2025 Poster
- Readers: Everyone
LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token
Shaolei Zhang, Qingkai Fang, Zhe Yang, Yang Feng
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
URLOST: Unsupervised Representation Learning without Stationarity or Topology
Zeyu Yun, Juexiao Zhang, Yann LeCun, Yubei Chen
- Published: 22 Jan 2025, Last Modified: 21 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
One-for-All Few-Shot Anomaly Detection via Instance-Induced Prompt Learning
Wenxi Lv, Qinliang Su, Wenchao Xu
- Published: 22 Jan 2025, Last Modified: 15 May 2025
- ICLR 2025 Poster
- Readers: Everyone
Synthesizing Physical Backdoor Datasets: An Automated Framework Leveraging Deep Generative Models
Sze Jue Yang, Chinh Duc La, Nguyen Hung-Quang, Eugene Bagdasarian, Kok-Seng Wong, Anh Tuan Tran, Chee Seng Chan, Khoa D Doan
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone