arXiv:2601.12415v5 Announce Type: replace Abstract: We propose Orthogonalized Policy Optimization (OPO), a principled framework for large language model alignment derived from optimization in the Hilbert function space L2(pi_k). Lifting policy updates from the probability simplex into L2(pi_k) transforms the nonlinear…
arXiv:2602.21340v1 Announce Type: new Abstract: Representing the past in a compressed, efficient, and informative manner is a central problem for systems trained on sequential data. The HiPPO framework, originally proposed by Gu & Dao et al., provides a principled approach…
arXiv:2602.20714v2 Announce Type: replace Abstract: Reliable prediction of hydraulic performance is challenging for Piano Key Weir (PKW) design because discharge capacity depends on three-dimensional geometry and operating conditions. Surrogate models can accelerate hydraulic-structure design, but progress is limited by scarce…
arXiv:2602.21342v1 Announce Type: new Abstract: Representation learning has been essential for graph machine learning tasks such as link prediction, community detection, and network visualization. Despite recent advances in achieving high performance on these downstream tasks, little progress has been made…
arXiv:2503.01927v2 Announce Type: replace-cross Abstract: The biomedical field is beginning to explore the use of quantum machine learning (QML) for tasks traditionally handled by classical machine learning, especially in predicting ADME (absorption, distribution, metabolism, and excretion) properties, which are essential…
arXiv:2602.21368v1 Announce Type: new Abstract: Given a black-box AI system and a task, at what confidence level can a practitioner trust the system’s output? We answer with a reliability level — a single number per system-task pair, derived from self-consistency…
arXiv:2509.11791v2 Announce Type: replace-cross Abstract: This paper investigates how the performance of visual navigation policies trained in simulation compares to policies trained with real-world data. Performance degradation of simulator-trained policies is often significant when they are evaluated in the real…
arXiv:2602.21371v1 Announce Type: new Abstract: Multi-Head Attention (MHA) is the core computational primitive underlying modern Large Language Models (LLMs). However, MHA suffers from a fundamental linear scaling limitation: $H$ attention heads produce exactly $H$ independent attention matrices, with no communication…
By leveraging idle computing time, researchers can double the speed of model training while preserving accuracy.
MIT researchers uncovered the physics behind bubble-removing membranes that could improve bioreactors, chemical production, and more.
