ICML 2025 Workshop MOSS Submissions

Dynamic Low-Rank Training with Spectral Regularization: Achieving Robustness in Compressed Representations
Steffen Schotthöfer, H. Lexie Yang, Stefan Schnake
- Published: 10 Jun 2025, Last Modified: 15 Jul 2025
- MOSS@ICML2025
- Readers: Everyone
Effective Reinforcement Learning for Reasoning in Language Models
Lianghuan Huang, Shuo Li, Sagnik Anupam, Insup Lee, Osbert Bastani
- Published: 10 Jun 2025, Last Modified: 15 Jul 2025
- MOSS@ICML2025
- Readers: Everyone
Koopman Autoencoders Learn Neural Representation Dynamics
Nishant Suresh Aswani, Saif Jabari
- Published: 10 Jun 2025, Last Modified: 15 Jul 2025
- MOSS@ICML2025
- Readers: Everyone
LiteByte: Efficient and Fast-Adapting MLPs for Online Byte-Level Prediction
Yu Mao, Yuyan Lin, Xue Liu, Chun Jason Xue
- Published: 10 Jun 2025, Last Modified: 15 Jul 2025
- MOSS@ICML2025
- Readers: Everyone
Mind the Gap: Removing the Discretization Gap in Differentiable Logic Gate Networks
Shakir Yousefi, Andreas Plesner, Till Aczel, Roger Wattenhofer
- Published: 10 Jun 2025, Last Modified: 15 Jul 2025
- MOSS@ICML2025
- Readers: Everyone
Quantitative Bounds for Length Generalization in Transformers
Zachary Izzo, Eshaan Nichani, Jason D. Lee
- Published: 10 Jun 2025, Last Modified: 15 Jul 2025
- MOSS@ICML2025
- Readers: Everyone
Emergence of Hebbian Dynamics in Regularized Non-Local Learners
David Aaron Koplow, Tomaso Poggio, Liu Ziyin
- Published: 10 Jun 2025, Last Modified: 15 Jul 2025
- MOSS@ICML2025
- Readers: Everyone
Is Visual Prompting the Right Setup for Knowledge Transfer in new Foundation Models?
Niclas Hergenröther, Antonio Orvieto
- Published: 10 Jun 2025, Last Modified: 15 Jul 2025
- MOSS@ICML2025
- Readers: Everyone
An Empirical Investigation of Initialization Strategies for Kolmogorov–Arnold Networks
Spyros Rigas, Dhruv Verma, Georgios Alexandridis, Yixuan Wang
- Published: 10 Jun 2025, Last Modified: 15 Jul 2025
- MOSS@ICML2025
- Readers: Everyone
Transformers Pretrained on Procedural Data Contain Modular Structures for Algorithmic Reasoning
Zachary Shinnick, Liangze Jiang, Hemanth Saratchandran, Anton van den Hengel, Damien Teney
- Published: 10 Jun 2025, Last Modified: 15 Jul 2025
- MOSS@ICML2025
- Readers: Everyone
ZeroTuning: Unlocking the Initial Token's Power to Enhance Large Language Models Without Training
Feijiang Han, Xiaodong Yu, Jianheng Tang, Qingyun Zeng, Licheng Guo, Lyle Ungar
- Published: 10 Jun 2025, Last Modified: 15 Jul 2025
- MOSS@ICML2025
- Readers: Everyone