Latest AI/ML News
435 articles · 🧠 Research
arXiv:2607.07003v3 Announce Type: replace Abstract: Large Language Models (LLMs) frequently exhibit sycophancy, agreeing with a user's statement even…
arXiv:2606.29248v3 Announce Type: replace Abstract: Vegetable prices in Sri Lanka are highly volatile because the market is largely import-isolated, s…
arXiv:2606.23587v2 Announce Type: replace Abstract: Previous work has found a gap between the scale of neural networks that reliably learn Conway's Ga…
arXiv:2606.17035v2 Announce Type: replace Abstract: Prior research suggests that differential privacy (DP) inherently enhances the robustness of feder…
arXiv:2606.07627v3 Announce Type: replace Abstract: A representation transfers if it stays usable once the task has changed. Standard evaluations repo…
arXiv:2606.05327v2 Announce Type: replace Abstract: Flow matching (FM) has emerged as a powerful framework for learning dynamic transport maps between…
arXiv:2605.30556v2 Announce Type: replace Abstract: CORRECTION (August 2026): the central finding of this paper is not supported. An evaluation-mode d…
arXiv:2605.25194v2 Announce Type: replace Abstract: Adversarial images pose a severe security threat to multimodal large language models through promp…
arXiv:2605.23391v3 Announce Type: replace Abstract: Physics-informed neural networks (PINNs) offer a mesh-free route to solving coupled multiphysics s…
arXiv:2605.22401v2 Announce Type: replace Abstract: CORRECTION (August 2026): an evaluation-mode defect in the shared feature-extraction pipeline affe…
arXiv:2605.08832v3 Announce Type: replace Abstract: Neural surrogate models for computational fluid dynamics (CFD) are typically trained as forward op…
arXiv:2604.18194v2 Announce Type: replace Abstract: Single-step generators promise high-fidelity synthesis at a fraction of the inference and training…
arXiv:2604.16875v3 Announce Type: replace Abstract: CORRECTION (August 2026): an evaluation-mode defect affected the predictive-coding and STDP condit…
arXiv:2604.13672v2 Announce Type: replace Abstract: The spotoptim package implements surrogate-model-based optimization of expensive black-box functio…
arXiv:2603.11799v2 Announce Type: replace Abstract: Membership inference attacks (MIAs) are becoming standard tools for auditing the privacy of machin…
arXiv:2603.09868v2 Announce Type: replace Abstract: Accurately quantifying terrestrial carbon exchange is essential for climate policy and carbon acco…
arXiv:2603.01959v2 Announce Type: replace Abstract: State-Space Models (SSMs) have recently been shown to achieve strong empirical performance on a va…
arXiv:2602.23459v2 Announce Type: replace Abstract: Psychiatric questionnaires are highly context sensitive and often only weakly predict subsequent s…
arXiv:2602.15572v3 Announce Type: replace Abstract: Agent-based modelling (ABM) is a widespread approach to simulate complex systems. Advancements in…
arXiv:2512.14338v4 Announce Type: replace Abstract: Many learning problems are organized by group symmetries. While invariance is often imposed throug…