ICLR 2025 Conference Submissions

Synthetic continued pretraining
Zitong Yang, Neil Band, Shuangping Li, Emmanuel Candes, Tatsunori Hashimoto
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Oral
- Readers: Everyone
Tensor Attention Training: Provably Efficient Learning of Higher-order Transformers
Yingyu Liang, Zhenmei Shi, Zhao Song, Yufa Zhou
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Hierarchical Graph Learners for Cardinality Estimation
Zixuan Yi, Sami Abu-El-Haija, Yawen Wang, Yannis Chronis, Yu Gan, Michael Burrows, Carsten Binnig, Bryan Perozzi, Fatma Ozcan
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Combating Dual Noise Effect in Spatial-temporal Forecasting via Information Bottleneck Principle
Min Chen, Guansong Pang, Wenjun Wang, Cheng Yan
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
A Solver-Aided Hierarchical Language For LLM-Driven CAD Design
Benjamin Tod Jones, Zihan Zhang, Felix Hähnlein, Maaz Bin Safeer Ahmad, Vladimir Kim, Adriana Schulz
- 26 Sept 2024 (modified: 04 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
EM-GANSim: Real-time and Accurate EM Simulation Using Conditional GANs for 3D Indoor Scenes
Ruichen Wang, Dinesh Manocha
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Indirect Gradient Matching for Adversarial Robust Distillation
Hongsin Lee, Seungju Cho, Changick Kim
- Published: 22 Jan 2025, Last Modified: 24 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models
Yanwei Li, Yuechen Zhang, Chengyao Wang, Zhisheng Zhong, Yixin Chen, Ruihang Chu, Shaoteng Liu, Jiaya Jia
- 26 Sept 2024 (modified: 17 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Efficient Visual Transformer by Information Bottleneck Inspired Token Merging
Yancheng Wang, Yingzhen Yang
- 26 Sept 2024 (modified: 22 Jan 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Towards Generalization Bounds of GCNs for Adversarially Robust Node Classification
Wen Wen, Han Li, Tieliang Gong, Hong Chen
- Published: 22 Jan 2025, Last Modified: 14 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Learn while Unlearn: An Iterative Unlearning Framework for Generative Language Models
Haoyu Tang, Ye Liu, Xukai Liu, Kai Zhang, Yanghai Zhang, Qi Liu, Enhong Chen
- 26 Sept 2024 (modified: 01 Feb 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Domain Shift Tuning over Knowledge Gap
Noriaki Kawamae
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
An efficient algorithm for entropic optimal transport under martingale-type constraints
Xun Tang, Michael Shavlovsky, Holakou Rahmanian, Tesi Xiao, Lexing Ying
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
DiffMove: Human Trajectory Recovery via Conditional Diffusion Model
Kaijun Liu, Sijie Ruan, ZHANG LIANG, Cheng Long, Shuliang Wang, liang yu
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
EventFlow: Forecasting Continuous-Time Event Data with Flow Matching
Gavin Kerrigan, Kai Nelson, Padhraic Smyth
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Role of Momentum in Smoothing Objective Function and Generalizability of Deep Neural Networks
Naoki Sato, Hideaki Iiduka
- 26 Sept 2024 (modified: 04 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Compelling ReLU Networks to Exhibit Exponentially Many Linear Regions at Initialization and During Training
Max Milkert, David Hyde, Forrest John Laine
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
REvolve: Reward Evolution with Large Language Models using Human Feedback
RISHI HAZRA, Alkis Sygkounas, Andreas Persson, Amy Loutfi, Pedro Zuidberg Dos Martires
- Published: 22 Jan 2025, Last Modified: 17 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Task Descriptors Help Transformers Learn Linear Models In-Context
Ruomin Huang, Rong Ge
- Published: 22 Jan 2025, Last Modified: 26 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Diffusion Curriculum: Synthetic-to-Real Data Curriculum via Image-Guided Diffusion
Yijun Liang, Shweta Bhardwaj, Tianyi Zhou
- 26 Sept 2024 (modified: 15 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Beyond Trend and Periodicity: Guide Time Series Forecasting with Textual Cues
Zhijian Xu, Yuxuan Bian, Jianyuan Zhong, Xiangyu Wen, Qiang Xu
- 26 Sept 2024 (modified: 23 Jan 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
MallowsPO: Fine-Tune Your LLM with Preference Dispersions
Haoxian Chen, Hanyang Zhao, Henry Lam, David Yao, Wenpin Tang
- Published: 22 Jan 2025, Last Modified: 11 May 2025
- ICLR 2025 Poster
- Readers: Everyone
Distribution-Specific Agnostic Conditional Classification With Halfspaces
Jizhou Huang, Brendan Juba
- Published: 22 Jan 2025, Last Modified: 23 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Overcoming False Illusions in Real-World Face Restoration with Multi-Modal Guided Diffusion Model
Keda TAO, Jinjin Gu, Yulun Zhang, Xiucheng Wang, Nan Cheng
- Published: 22 Jan 2025, Last Modified: 29 Mar 2025
- ICLR 2025 Spotlight
- Readers: Everyone
A Causal Framework for Aligning Metrics of Image Quality and Deep Neural Network Robustness
Nathan Drenkow, Mathias Unberath
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone