ICLR 2025 Conference Submissions

COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinement
Yuxi Xie, Anirudh Goyal, Xiaobao Wu, Xunjian Yin, Xiao Xu, Min-Yen Kan, Liangming Pan, William Yang Wang
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Hierarchical Clustering for Conditional Diffusion in Image Generation
Jorge da Silva Gonçalves, Laura Manduchi, Moritz Vandenhirtz, Julia E Vogt
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
FedEx-LoRA: Exact Aggregation for Federated and Efficient Fine-Tuning of Foundation Models
Raghav Singhal, Kaustubh Ponkshe, Praneeth Vepakomma
- 27 Sept 2024 (modified: 15 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Soft Checksums to Flag Untrustworthy Machine Learning Surrogate Predictions and Application to Atomic Physics Simulations
Casey Lauer, Robert C. Blake III, Jonathan B Freund
- 27 Sept 2024 (modified: 20 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
MetaInv: Overcoming Iterative and Direct Method Limitations for Inverse Learning
Jingyi Yuan, Muhao Guo, Yang Weng
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search
Murong Yue, Wenlin Yao, Haitao Mi, Dian Yu, Ziyu Yao, Dong Yu
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Learning Diagrams: A Graphical Language for Compositional Training Regimes
Mason Lary, Richard Samuelson, Alexander Wilentz, Alina Zare, Matthew Klawonn, James Fairbanks
- Published: 22 Jan 2025, Last Modified: 01 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Differential learning kinetics govern the transition from memorization to generalization during in-context learning
Alex Nguyen, Gautam Reddy
- Published: 22 Jan 2025, Last Modified: 07 Apr 2025
- ICLR 2025 Spotlight
- Readers: Everyone
Joint Graph Rewiring and Feature Denoising via Spectral Resonance
Jonas Linkerhägner, Cheng Shi, Ivan Dokmanić
- Published: 22 Jan 2025, Last Modified: 08 May 2025
- ICLR 2025 Oral
- Readers: Everyone
The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
Eric Wallace, Kai Yuanqing Xiao, Reimar Heinrich Leike, Lilian Weng, Johannes Heidecke, Alex Beutel
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Strategic Filtering for Content Moderation: Free Speech or Free of Distortion?
Saba Ahmadi, Avrim Blum, Haifeng Xu, Fan Yao
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
SatDiffMoE: A Mixture of Estimation Method for Satellite Image Super-resolution with Latent Diffusion Models
Zhaoxu Luo, Bowen Song, Liyue Shen
- 27 Sept 2024 (modified: 04 Jan 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Review and Rebuttal: Zero-shot In-context Adversarial Learning for Improving Research Ideation
Sikun Guo, Amir Hassan Shariatmadari, Peng Wang, Albert Huang, Aidong Zhang
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Towards Efficient Confidence Estimation for Large Language Model Reasoning
Zhi Zhou, Tan Yuhao, Zenan Li, Yuan Yao, Lan-Zhe Guo, Xiaoxing Ma, Yu-Feng Li
- 27 Sept 2024 (modified: 20 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
”DOES YOUR MOBILE SUIT YOUR SKIN?”: ADDRESSING SKIN TONE DISPARITIES IN PRESENTATION ATTACK DETECTION FOR ENHANCED INCLUSIVITY OF SMARTPHONE SECURITY
Anudeep Vurity, Emanuela Marasco
- 27 Sept 2024 (modified: 25 Feb 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Context-Scaling versus Task-Scaling in In-Context Learning
Amirhesam Abedsoltan, Adityanarayanan Radhakrishnan, Jingfeng Wu, Mikhail Belkin
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Practical alignment requires more than learning from human feedback
Tu Trinh, Khanh Xuan Nguyen
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones
Mehrnaz Mofakhami, Reza Bayat, Ioannis Mitliagkas, Joao Monteiro, Valentina Zantedeschi
- 27 Sept 2024 (modified: 22 Jan 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Latent Feature Mining for Predictive Model Enhancement with Large Language Models
Bingxuan Li, Pengyi Shi, Amy R Ward
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Multi-session, multi-task neural decoding from distinct cell-types and brain regions
Mehdi Azabou, Krystal Xuejing Pan, Vinam Arora, Ian Jarratt Knight, Eva L Dyer, Blake Aaron Richards
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Spotlight
- Readers: Everyone
Toward Robust Real-World Audio Deepfake Detection: Closing the Explainability Gap
Georgia Channing, Juil Sock, Ronald Clark, Philip Torr, Christian Schroeder de Witt
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Reality Only Happens Once: Single-path Generalization Bounds for Transformers
Yannick Limmer, Anastasis Kratsios, Xuwei Yang, Raeid Saqur, Blanka Horvath
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
An Information Theory of Compute-Optimal Size Scaling, Emergence, and Plateaus in Language Models
Anuj K. Nayak, Lav R. Varshney
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
LNUCB-TA: Linear-nonlinear Hybrid Bandit Learning with Temporal Attention
Hamed Khosravi, Ahmed Shoyeb Raihan, Srinjoy Das, Imtiaz Ahmed
- 27 Sept 2024 (modified: 03 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Learning Continually by Spectral Regularization
Alex Lewandowski, Michał Bortkiewicz, Saurabh Kumar, András György, Dale Schuurmans, Mateusz Ostaszewski, Marlos C. Machado
- Published: 22 Jan 2025, Last Modified: 08 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone