ICLR 2025 Conference Submissions

WASH: Train your Ensemble with Communication-Efficient Weight Shuffling, then Average
Louis Fournier, Adel Nabli, Masih Aminbeidokhti, Marco Pedersoli, Eugene Belilovsky, Edouard Oyallon
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
FRAPPE: Fast RAG-Inspired Prompt Evaporator
Arnab Chakraborty, William McCormack, Zachary semenov, J. Jeffrey Brown, Mohammadreza Soltani
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
The Challenging Growth: Evaluating the Scalability of Causal Models
Nicholas Tagliapietra, Juergen Luettin, Lavdim Halilaj, Moritz Willig, Tim Pychynski, Kristian Kersting
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
HOGT: High-Order Graph Transformers
Xueqi Ma, Xingjun Ma, Chuang Liu, Sarah Monazam Erfani, James Bailey
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Can Data be Myopic? Outlier Detection in High-Dimensional Tabular Data via Subspaces
Jose Cribeiro-Ramallo, Vadim Arzamasov, Federico Matteucci, Denis Wambold, Klemens Böhm
- 26 Sept 2024 (modified: 28 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
SLoPe: Double-Pruned Sparse Plus Lazy Low-Rank Adapter Pretraining of LLMs
Mohammad Mozaffari, Amir Yazdanbakhsh, Zhao Zhang, Maryam Mehri Dehnavi
- Published: 22 Jan 2025, Last Modified: 27 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?
Liqiang Jing, Zhehui Huang, Xiaoyang Wang, Wenlin Yao, Wenhao Yu, Kaixin Ma, Hongming Zhang, Xinya Du, Dong Yu
- Published: 22 Jan 2025, Last Modified: 21 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Bringing NeRFs to the Latent Space: Inverse Graphics Autoencoder
Antoine Schnepf, Karim Kassab, Jean-Yves Franceschi, Laurent Caraffa, Flavian Vasile, Jeremie Mary, Andrew I. Comport, Valerie Gouet-Brunet
- Published: 22 Jan 2025, Last Modified: 24 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
KnowData: Knowledge-Enabled Data Generation for Improving Multimodal Models
YiPeng Chen, Chulin Xie, Zinan Lin, Dawn Song, Bo Li
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
What Are Good Positional Encodings for Directed Graphs?
Yinan Huang, Haoyu Peter Wang, Pan Li
- Published: 22 Jan 2025, Last Modified: 28 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
ASTrA: Adversarial Self-supervised Training with Adaptive-Attacks
Prakash Chandra Chhipa, Gautam Vashishtha, Settur Jithamanyu, Rajkumar Saini, Mubarak Shah, Marcus Liwicki
- Published: 22 Jan 2025, Last Modified: 01 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
GUI-World: A Video Benchmark and Dataset for Multimodal GUI-oriented Understanding
Dongping Chen, Yue Huang, Siyuan Wu, Jingyu Tang, Huichi Zhou, Qihui Zhang, Zhigang He, Yilin Bai, Chujie Gao, Liuyi Chen, Yiqiang Li, Chenlong Wang, Yue Yu, Tianshuo Zhou, Zhen Li, Yi Gui, Yao Wan, Pan Zhou, Jianfeng Gao, Lichao Sun
- Published: 22 Jan 2025, Last Modified: 03 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
A Pontryagin Perspective on Reinforcement Learning
Onno Eberhard, Claire Vernade, Michael Muehlebach
- 26 Sept 2024 (modified: 18 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Out of Many, One: Designing and Scaffolding Proteins at the Scale of the Structural Universe with Genie 2
Yeqing Lin, Minji Lee, Zhao Zhang, Mohammed AlQuraishi
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Understanding When and Why Graph Attention Mechanisms Work via Node Classification
Zhongtian Ma, Qiaosheng Zhang, Bocheng Zhou, Yexin Zhang, Shuyue Hu, Zhen Wang
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Beyond the Lazy versus Rich Dichotomy: Geometry Insights in Feature Learning from Task-Relevant Manifold Untangling
Chi-Ning Chou, Hang Le, Yichen Wang, SueYeon Chung
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Integrating State Space Model and Transformer for Global-Local Processing in Super-Resolution Networks
Yukai Sun, Zheng Chen, Yulun Zhang, Jinjin Gu
- 26 Sept 2024 (modified: 12 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Mycroft: Towards Effective and Efficient External Data Augmentation
Zain Sarwar, Van Tran, Arjun Nitin Bhagoji, Nick Feamster, Ben Y. Zhao, Supriyo Chakraborty
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Learning grid cells by predictive coding
Mufeng Tang, Helen C Barron, Rafal Bogacz
- 26 Sept 2024 (modified: 24 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
How does Your RL Agent Explore? An Optimal Transport Analysis of Occupancy Measure Trajectories
Reabetswe M. Nkhumise, Debabrota Basu, Tony J. Prescott, Aditya Gilra
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Retrieval-based Zero-shot Crowd Counting
Don Yasiru Lakshan Ranasinghe, Vishal M. Patel
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Can Large Language Models Effectively Modify Graphs?
Cazamere Comrie, Jon Kleinberg
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
ESQA: Event Sequences Question Answering
Irina Abdullaeva, Andrei Filatov, Mikhail Orlov, Ivan Karpukhin, Viacheslav Vasilev, Denis Dimitrov, Andrey Kuznetsov, Ivan A Kireev, Andrey Savchenko
- 26 Sept 2024 (modified: 27 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
LLM4Solver: Large Language Model for Efficient Algorithm Design of Combinatorial Optimization Solver
Yuyan Zhou, Jie Wang, Yufei Kuang, Xijun Li, Weilin Luo, Jianye HAO, Feng Wu
- 26 Sept 2024 (modified: 25 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Link Prediction on Text Attributed Graphs: A New Benchmark and Efficient LM-nested GNN Design
Chen Shao, Ruirui Wang, Kai Yuan, German Mikhelson, Constantin Sanders, Michael Färber, Tobias Käfer
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone