ICLR 2025 Conference Submissions

UNAST: Unified framework for Neural Architecture Search for Transformers
Ilia Markov, Chenhan D. Yu, Hongxu Yin, Saurav Muralidharan, Greg Heinrich, Jan Kautz, Dan Alistarh, Pavlo Molchanov
- 26 Sept 2024 (modified: 25 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Towards Self-Supervised Covariance Estimation in Deep Heteroscedastic Regression
Megh Shukla, Aziz Shameem, Mathieu Salzmann, Alexandre Alahi
- Published: 22 Jan 2025, Last Modified: 14 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Unifying Disentangled Representation Learning with Compositional Bias
Whie Jung, Dong Hoon Lee, Seunghoon Hong
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model
Jiahui Gao, Renjie Pi, Jipeng Zhang, Jiacheng Ye, Wanjun Zhong, Yufei Wang, Lanqing HONG, Jianhua Han, Hang Xu, Zhenguo Li, Lingpeng Kong
- Published: 22 Jan 2025, Last Modified: 28 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Complementary Label Learning with Positive Label Guessing and Negative Label Enhancement
Yuhang Li, Zhuying Li, Yuheng Jia
- Published: 22 Jan 2025, Last Modified: 23 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Automatic Jailbreaking of Text-to-Image Generative AI Systems for Copyright Infringement
Minseon Kim, Hyomin Lee, Boqing Gong, Huishuai Zhang, Sung Ju Hwang
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Provable Convergence of Single-Timescale Neural Actor-Critic in Continuous Spaces
Xuyang Chen, Fengzhuo Zhang, Guojian Wang, Lin Zhao
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Linearly Controlled Language Generation with Performative Guarantees
Emily Cheng, Marco Baroni, Carmen Amo Alonso
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Can Model Randomization Offer Robustness Against Query-Based Black-Box Attacks?
Quoc Viet Vo, Bao Gia Doan, Ehsan Abbasnejad, Damith Ranasinghe
- 26 Sept 2024 (modified: 23 Feb 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
EIBench: Assessing the Emotion Interpretation ability of Vision Large Language Models
Yuxiang Lin, Jue Wang, Haomin Liang, Zebang Cheng, Jun-Yan He, Zhi-Qi Cheng, Xiaojiang Peng, Xian-Sheng Hua
- 26 Sept 2024 (modified: 26 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Calibrated Physics-Informed Uncertainty Quantification
Vignesh Gopakumar, Ander Gray, Daniel Giles, Lorenzo Zanisi, Stanislas Pamela, Matt Kusner, Marc Peter Deisenroth
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
The Buffer Mechanism for Multi-Step Information Reasoning in Language Models
Zhiwei Wang, Yunji Wang, Zhongwang Zhang, Zhangchen Zhou, Hui Jin, Tianyang Hu, Jiacheng Sun, Zhenguo Li, Yaoyu Zhang, Zhi-Qin John Xu
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Emergence of a High-Dimensional Abstraction Phase in Language Transformers
Emily Cheng, Diego Doimo, Corentin Kervadec, Iuri Macocco, Lei Yu, Alessandro Laio, Marco Baroni
- Published: 22 Jan 2025, Last Modified: 30 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
Domain-specific Benchmarking of Vision-Language Models: A Task Augmentation Framework Using Metadata
Tim Rädsch, Leon Mayer, Simon Pavicic, Ali Emre Kavur, Marcel Knopp, Barış Öztürk, Klaus Maier-Hein, Paul F Jaeger, Fabian Isensee, Annika Reinke, Lena Maier-hein
- 26 Sept 2024 (modified: 15 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Embedding Learning for Approximating Person-specific Cognitive Similarity
Yujin Cha
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
KidSat: satellite imagery to map childhood poverty
Makkunda Sharma, Fan Yang, Duy-Nhat Vo, Jack Gidney, Matthew Sutcliffe, Mengyan Zhang, Esra Suel, H Juliette T Unwin, Swapnil Mishra, Samir Bhatt, Oliver Fiala, William Rudgard, Seth Flaxman
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
DiffStroke: High-Quality Mask-free Image Manipulation with Partial Sketches
Tengjie Li, Shikui Tu, Lei Xu
- 26 Sept 2024 (modified: 14 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Self-Supervised Grid Cells Without Path Integration
Vemund Sigmundson Schøyen, Markus Pettersen, Anders Malthe-Sorenssen, Mattis Dalsætra Østby, Mikkel Elle Lepperød
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Collaborative Discrete-Continuous Black-Box Prompt Learning for Language Models
Hualin Zhang, Haozhen Zhang, Zhekai Liu, Bin Gu, Yi Chang
- Published: 22 Jan 2025, Last Modified: 28 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Singular Value Adaptation for Parameter-Efficient Fine Tuning
Susmit Agrawal, Krishn Vishwas Kher, Swarnim Maheshwari, Rishabh Lalla, Vineeth N. Balasubramanian
- 26 Sept 2024 (modified: 25 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Effective and Efficient Adversarial Detection for Vision-Language Models via A Single Vector
Youcheng Huang, Fengbin ZHU, Jingkun Tang, Pan Zhou, Wenqiang Lei, Tat-Seng Chua
- 26 Sept 2024 (modified: 14 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Training-Free Retrieval-Augmented Generation for Knowledge-Intensive Visual Question Answering
Shan Ning, Longtian Qiu, Jiaxuan Sun, Xuming He
- 26 Sept 2024 (modified: 15 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Relation-Aware Diffusion for Heterogeneous Graphs with Partially Observed Features
Daeho Um, Yoonji Lee, Jiwoong Park, Seulki Park, Yuneil Yeo, Seong Jin Ahn
- Published: 22 Jan 2025, Last Modified: 23 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Towards Lightweight Deep Watermarking Framework
Yupeng Qiu, Han Fang, Ee-Chien Chang
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Debiasing Vison-Language Models with Text-Only Training
Yunfan Yang, Chaoquan Jiang, Zhiyu Lin, Jinlin Xiao, Jiaming Zhang, Jitao Sang
- 26 Sept 2024 (modified: 13 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone