Prépublication
· 2026 arXiv
EN
Despite recent advances, current AI systems remain highly susceptible to domain shifts, particularly in biomedical imaging, where images are usually acquired under substantially different experimental conditions. Although recent domain adaptation methods have...
Sonja Topf, Ana Sanchez-Fernandez et al.
#cs.LG
Prépublication
· 2026 arXiv
EN
Reinforcement Learning with Human Feedback (RLHF) has become a central paradigm for aligning Large Language Models with human values. However, the reliance on sensitive preference data necessitates rigorous differential privacy (DP) guarantees to prevent user...
Meng Ding, Mingxi Lei et al.
#cs.LG
Prépublication
· 2026 arXiv
EN
TS2Vec is one of the strongest self-supervised methods for time series classification, introduced in 2022. It is designed to be trained anew on every dataset: self-supervised pre-training followed by linear probing. Since then, the field has shifted towards fo...
Vasilii Feofanov, Zhenghan Tai et al.
#cs.LG
Prépublication
· 2026 arXiv
EN
Generative models for precipitation nowcasting are trained and evaluated predominantly on wet-biased datasets, which over-represent precipitation events to emphasize rare extremes. Selecting test cases based on target observations is known to favor forecasts t...
Christoph Metzl, Stefan Kapsreiter et al.
#cs.LG
Prépublication
· 2026 arXiv
EN
Long-horizon agents must learn heterogeneous capabilities from interleaved trajectories. Updating shared parameters to learn new capabilities can degrade previously acquired ones, resulting in catastrophic forgetting. As a trajectory unfolds, different stages...
Rui Shi, Xunjian Yin et al.
#cs.LG
Prépublication
· 2026 arXiv
EN
We propose KronLSTM, a linear attention architecture based on the Kronecker Delta Rule, a novel update rule for associative matrix memories. KronLSTM extends the xLSTM family with a memory-revision mechanism that corrects targeted associations while modifying...
Anamaria-Roberta Hartl, Levente Zólyomi et al.
#cs.LG
Prépublication
· 2026 arXiv
EN
Mixture-of-experts (MoE) models have become an important approach for scaling model parameters. Modern MoE architectures increasingly combine two design choices: fine-grained expert segmentation and shared experts. The former increases expressiveness by enabli...
Bingcong Li, Hao Ma et al.
#cs.LG
Prépublication
· 2026 arXiv
EN
Weather prediction is undergoing an important shift, with data-driven AI models outperforming leading numerical weather prediction systems on average at a fraction of the computational cost. Yet, whether this success extends to extreme events remains contested...
Nathan Chalumeau, Xavier Renard et al.
#cs.LG
Prépublication
· 2026 arXiv
EN
Scaling up transformers has produced models with broad capabilities, deployed across heterogeneous hardware and fluctuating workloads. Yet, model families offer only a few fixed sizes (e.g., S, B, L), forcing users to commit to a model based on hardware and la...
Walter Simoncini, Dheeraj Varghese et al.
#cs.LG
Prépublication
· 2026 arXiv
EN
We introduce Continuum Attention (CA), a causal Transformer attention operator that replaces discrete key and value lookup with integration over a continuous, piecewise linear memory curve. Each query induces an exponential relevance density along the curve. I...
Afshin Khadangi
#cs.LG
Prépublication
· 2026 arXiv
EN
Post-training binds the competence of an LLM agent to the interface it was trained on. Semantics-preserving perturbations of that interface, such as renaming an action or changing the notation, leave the underlying task unchanged yet make the agent worse at it...
Artin Tajdini, Manpreet Kaur et al.
#cs.LG
Prépublication
· 2026 arXiv
EN
On-policy distillation (OPD) trains a student model on its own rollouts with token-level supervision from a teacher, assuming that the teacher can reach a correct answer from any prefix the student writes. We call this property the recoverability of the teache...
Kaixiang Zhao, Tianrun Yu et al.
#cs.LG