Prépublication
· 2026 arXiv
EN
Deep-learning models increasingly rival numerical simulation in Earth-system forecasting, yet forecast error alone cannot determine whether their learned input-output dependencies are physically consistent. Here we introduce sensitivity fidelity as an addition...
Qi Chen, Peng Zhan et al.
#cs.LG
Prépublication
· 2026 arXiv
EN
While deep learning models for tabular data have recently received significant research attention, the choice of objective functions for regression tasks remains an understudied degree of freedom. Several lines of research offer alternatives to the standard Me...
Danil Rudenko, Georgii Bulgakov et al.
#cs.LG
Prépublication
· 2026 arXiv
EN
The intermittent and variable nature of precipitation makes its accurate estimation over extended domains difficult, yet its spatiotemporal structure suggests that a low-rank representation may be possible. This work represents daily precipitation over the con...
Ryan Solgi, Rohan Shankar et al.
#cs.LG
Prépublication
· 2026 arXiv
EN
Bifurcations are ubiquitous in physical systems, from structural buckling to fluid and climate dynamics, yet they remain largely unexplored in deep learning. At a symmetry-breaking bifurcation, a single input admits multiple equally valid solutions, violating...
Anna Zimmel, Fleur Hendriks et al.
#cs.LG
Prépublication
· 2026 arXiv
EN
Recent incidents have highlighted the challenge of monitoring LLM agents and the danger of models deceiving people. We show that white-box deception detection via probes can be scaled up to frontier monitoring settings by collecting the largest deception datas...
Oskar J. Hollinsworth, Alex F. Spies et al.
#cs.LG
Prépublication
· 2026 arXiv
EN
We introduce EC-EarthFlow, a generative flow matching model that emulates simulations from the physical climate model EC-Earth3. The model is trained on transient simulations from EC-Earth3 (1950-2166, SSP2-4.5) to predict the day ahead temperature field from...
Kirien Whan, Nikolaj T. Mücke et al.
#cs.LG
Prépublication
· 2026 arXiv
EN
Deep learning has revolutionised weather forecasting in recent years, especially through atmospheric foundation models, which offer competitive skill for a fraction of the computational costs of classic physics-based models. However, most existing foundation m...
Eliot Walt, Miltiadis Kofinas et al.
#cs.LG
Prépublication
· 2026 arXiv
EN
Despite substantial progress in short-to-medium-range weather forecasting, predicting high-impact events such as flash droughts remains a key challenge for both early warning operations and physically-based subseasonal-to-seasonal (S2S) prediction systems. Her...
Noelia Otero, Atahan Özer et al.
#cs.LG
Prépublication
· 2026 arXiv
EN
Modern language models undergo reinforcement learning with verifiable rewards (RLVR) on top of already-trained checkpoints. A key promise of RLVR is the discovery of new reasoning strategies. In principle, a model can sample novel ideas absent from its prior t...
Saif Punjwani, Micah Goldblum
#cs.LG
Prépublication
· 2026 arXiv
EN
Multi-teacher on-policy distillation (MOPD) is used in two settings. In common-domain composition, several teachers score each student rollout from one prompt domain and their signals form a single target; in routed-domain distillation, prompts from different...
Hejian Sang, Zhengze Zhou et al.
#cs.LG
Prépublication
· 2026 arXiv
EN
Reinforcement Learning (RL) from outcome rewards suffers from sparse supervision, particularly on difficult, long-horizon tasks where successful trajectories are rare and costly to generate. On-Policy Distillation (OPD) offers an attractive alternative by prov...
Randy Ardywibowo, Arnav Dalal et al.
#cs.LG
Prépublication
· 2026 arXiv
EN
Flow policies capture rich and diverse action distributions, and fine-tuning them with off-policy RL to improve beyond the demonstrations has drawn growing interest. However, fine-tuning a flow policy against a learned value function is not trivial, because th...
Yonghoon Dong, Minsung Yoon et al.
#cs.LG