ICLR 2025 Conference Submissions

Physics-Informed Autoencoder for Enhancing Data Quality to Improve the Forecasting Reliability of Carbon Dioxide Emissions from Agricultural Fields
Corentin Houpert, Muhammad Saad Zia, Ashiq Anjum, Noel Clancy, Jörg Kaduk, Heiko Balzter
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
An Efficient Quantum Classifier Based on Hamiltonian Representations
Federico Tiblias, Anna Schroeder, Yue Zhang, Mariami Gachechiladze, Iryna Gurevych
- 26 Sept 2024 (modified: 16 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
CompassDock: Comprehensive Accurate Assessment Approach for Deep Learning-Based Molecular Docking in Inference and Fine-Tuning
Ahmet Sarigun, Vedran Franke, Bora Uyar, Altuna Akalin
- 26 Sept 2024 (modified: 28 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Evaluating Gender Bias Transfer between Pre-trained and Prompt-Adapted Language Models
Nivedha Sivakumar, Natalie Mackraz, Samira Khorshidi, Krishna Patel, Barry-John Theobald, Luca Zappella, Nicholas Apostoloff
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Can We Talk Models Into Seeing the World Differently?
Paul Gavrikov, Jovita Lukasik, Steffen Jung, Robert Geirhos, Muhammad Jehanzeb Mirza, Margret Keuper, Janis Keuper
- Published: 22 Jan 2025, Last Modified: 22 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Vision CNNs trained to estimate spatial latents learned similar ventral-stream-aligned representations
Yudi Xie, Weichen Huang, Esther Alter, Jeremy Schwartz, Joshua B. Tenenbaum, James J. DiCarlo
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Temporal Graph Rewiring with Expander Graphs
Katarina Petrović, Shenyang Huang, Farimah Poursafaei, Petar Veličković
- 26 Sept 2024 (modified: 03 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Discretization of continuous input spaces in the hippocampal autoencoder
Adrian F. Amil, Ismael T. Freire, Paul FMJ Verschure
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Representation Confusion: Towards Representation Backdoor on CLIP via Concept Activation
Lijie Hu, Junchi Liao, Weimin Lyu, Shaopeng Fu, Tianhao Huang, Shu Yang, Guimin Hu, Di Wang
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
When and how are modular networks better?
Shreyas Malakarjun Patil, Cameron Ethan Taylor, Constantine Dovrolis
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Enhancing Multi-Modal Reasoning Over Time-Series and Natural Language Data
Paul Quinlan, Qingguo Li, Xiaodan Zhu
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
HAINAN: Fast and Accurate Transducer for Hybrid-Autoregressive ASR
Hainan Xu, Travis M. Bartley, Vladimir Bataev, Boris Ginsburg
- Published: 22 Jan 2025, Last Modified: 05 May 2025
- ICLR 2025 Poster
- Readers: Everyone
Theory of LLM sampling: part descriptive and part prescriptive
Sarath Sivaprasad, Pramod Kaushik, Sahar Abdelnabi, Mario Fritz
- 26 Sept 2024 (modified: 15 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Efficient Distributed Principal Component Analysis with Parallel Deflation
Fangshuo Liao, Wenyi Su, Anastasios Kyrillidis
- 26 Sept 2024 (modified: 26 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
On Information-Theoretic Measures of Predictive Uncertainty
Kajetan Schweighofer, Lukas Aichberger, Mykyta Ielanskyi, Sepp Hochreiter
- 26 Sept 2024 (modified: 22 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Model Developmental Safety: A Safety-Centric Method and Applications in Vision-Language Models
Gang Li, Wendi Yu, Yao Yao, Wei Tong, Yingbin Liang, Qihang Lin, Tianbao Yang
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Inference Optimal VLMs Need Fewer Visual Tokens and More Parameters
Kevin Li, Sachin Goyal, João D. Semedo, J Zico Kolter
- Published: 22 Jan 2025, Last Modified: 01 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
Lijie Yang, Zhihao Zhang, Zhuofu Chen, Zikun Li, Zhihao Jia
- Published: 22 Jan 2025, Last Modified: 01 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Adaptive Inference: Theoretical Limits and Opportunities for Efficient AI
Soheil Hor, Ying Qian, Mert Pilanci, Amin Arbabian
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Differentiable Polygon Modeling for Object Instance Segmentation
Thomas Paniagua, Ryan Grainger, Tianfu Wu
- 26 Sept 2024 (modified: 25 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Guided Stream of Search: Learning to Better Search with Language Models via Optimal Path Guidance
Seungyong Moon, Bumsoo Park, Hyun Oh Song
- 26 Sept 2024 (modified: 02 Jan 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting
Chen Huang, Skyler Seto, Hadi Pouransari, Mehrdad Farajtabar, Raviteja Vemulapalli, Fartash Faghri, Oncel Tuzel, Barry-John Theobald, Joshua M. Susskind
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
COMiX: Compositional explanations using prototypes
Sarath Sivaprasad, Dmitry Kangin, Plamen P Angelov, Mario Fritz
- 26 Sept 2024 (modified: 10 Jan 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
MediConfusion: Can you trust your AI radiologist? Probing the reliability of multimodal medical foundation models
Mohammad Shahab Sepehri, Zalan Fabian, Maryam Soltanolkotabi, Mahdi Soltanolkotabi
- Published: 22 Jan 2025, Last Modified: 01 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Revisiting and Expanding Targeted Universal Adversarial Perturbations
Thomas Paniagua, Ryan Grainger, Tianfu Wu
- 26 Sept 2024 (modified: 15 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone