TL;DR: A new research from Apple, formalizes what “mid-training” should do before reinforcement learning RL post-training and introduces RA3 (Reasoning as Action Abstractions)—an EM-style procedure that learns temporally consistent latent actions from expert traces, then fine-tunes on those bootstrapped traces.…
arXiv:2509.04128v2 Announce Type: replace Abstract: Machine learning based predictions are increasingly used in sensitive decision-making applications that directly affect our lives. This has led to extensive research into ensuring the fairness of classifiers. Beyond just fair classification, emerging legislation now…
arXiv:2502.07218v2 Announce Type: replace Abstract: The ability to selectively remove knowledge from LLMs is highly desirable. However, existing methods often struggle with balancing unlearning efficacy and retain model utility, and lack controllability at inference time to emulate base model behavior…
arXiv:2505.22524v3 Announce Type: replace Abstract: Discrete diffusion models have become highly effective across various domains. However, real-world applications often require the generative process to adhere to certain constraints. To this end, we propose a Sequential Monte Carlo (SMC) framework that…
arXiv:2510.07175v1 Announce Type: cross Abstract: Recent studies apply psychometric questionnaires to Large Language Models (LLMs) to assess high-level psychological constructs such as values, personality, moral foundations, and dark traits. Although prior work has raised concerns about possible data contamination from…
arXiv:2408.11200v3 Announce Type: replace Abstract: Kolmogorov-Arnold Networks (KANs) have recently emerged as a powerful alternative to traditional multilayer perceptrons. However, their reliance on predefined, bounded grids restricts their ability to approximate functions on unbounded domains. To address this, we present…
arXiv:2505.18356v2 Announce Type: replace-cross Abstract: Large language models (LLMs) still struggle across tasks outside of high-resource languages. In this work, we investigate cross-lingual transfer to lower-resource languages where task-specific post-training data is scarce. Building on prior work, we first validate…
arXiv:2510.03993v3 Announce Type: replace-cross Abstract: Current long-tailed semi-supervised learning methods assume that labeled data exhibit a long-tailed distribution, and unlabeled data adhere to a typical predefined distribution (i.e., long-tailed, uniform, or inverse long-tailed). However, the distribution of the unlabeled data…
arXiv:2510.06349v1 Announce Type: new Abstract: Foundation models have rapidly advanced AI, raising the question of whether their decisions will ultimately surpass human strategies in real-world domains. The exponential, and possibly super-exponential, pace of AI development makes such analysis elusive. Nevertheless,…
arXiv:2510.06355v1 Announce Type: new Abstract: Unmanned aerial vehicle (UAV) communications demand accurate yet interpretable air-to-ground (A2G) channel models that can adapt to nonstationary propagation environments. While deterministic models offer interpretability and deep learning (DL) models provide accuracy, both approaches suffer…
