arXiv:2603.19294v1 Announce Type: new Abstract: While post-training has successfully improved large language models (LLMs) across a variety of domains, these gains heavily rely on human-labeled data or external verifiers. Existing data has already been exploited, and new high-quality data is…
arXiv:2603.19687v1 Announce Type: cross Abstract: Modern generative modelling systems are increasingly improved by expanding model capacity, training data, and computational resources. While empirical studies have documented such scaling behaviour across architectures including generative adversarial networks, variational autoencoders, transformer-based models, and…
arXiv:2603.19307v1 Announce Type: new Abstract: Modeling the complex interactions among functional subnetworks is crucial for the diagnosis of mental disorders and the identification of functional pathways. However, learning the interactions of the underlying subnetworks remains a significant challenge for existing…
arXiv:2603.19874v1 Announce Type: cross Abstract: Loss functions play a central role in supervised classification. Cross-entropy (CE) is widely used, whereas the mean absolute error (MAE) loss can offer robustness but is difficult to optimize. Interpolating between the CE and MAE…
arXiv:2603.19308v1 Announce Type: new Abstract: In autonomous driving, multi-agent collaborative perception enhances sensing capabilities by enabling agents to share perceptual data. A key challenge lies in handling {em heterogeneous} features from agents equipped with different sensing modalities or model architectures,…
arXiv:2603.20179v1 Announce Type: cross Abstract: Large language model-based AI agents are now able to autonomously execute substantial portions of a high energy physics (HEP) analysis pipeline with minimal expert-curated input. Given access to a HEP dataset, an execution framework, and…
arXiv:2603.19310v1 Announce Type: new Abstract: Training large language models (LLMs) for complex reasoning via reinforcement learning requires reward labels that specify whether the generated rollouts are correct. However, obtaining reward labels at scale often requires expensive human labeling or time-consuming…
arXiv:2510.11283v2 Announce Type: replace Abstract: This paper presents Gym-TORAX, a Python package enabling the implementation of Reinforcement Learning (RL) environments for simulating plasma dynamics and control in tokamaks. Users define succinctly a set of control actions and observations, and a…
arXiv:2603.19312v1 Announce Type: new Abstract: Joint Embedding Predictive Architectures (JEPAs) offer a compelling framework for learning world models in compact latent spaces, yet existing methods remain fragile, relying on complex multi-term losses, exponential moving averages, pre-trained encoders, or auxiliary supervision…
arXiv:2602.02500v3 Announce Type: replace Abstract: The Newton-Schulz (NS) iteration has become a key technique for orthogonalization in optimizers such as Muon and for optimization on the Stiefel manifold. Despite its effectiveness, the conventional NS iteration incurs significant computational overhead due…
