arXiv:2601.09693v2 Announce Type: replace-cross Abstract: Structure-based and ligand-based computational drug design have traditionally relied on disjoint data sources and modeling assumptions, limiting their joint use at scale. In this work, we introduce Contrastive Geometric Learning for Unified Computational Drug Design (ConGLUDe), a single contrastive geometric model that unifies structure- and ligand-based training. ConGLUDe couples a geometric protein encoder that produces whole-protein representations and implicit embeddings of predicted binding sites with a fast ligand encoder, removing the need for […]

Ver mais

arXiv:2603.22348v1 Announce Type: new Abstract: Online learning algorithms often faces a fundamental trilemma: balancing regret guarantees between adversarial and stochastic settings and providing baseline safety against a fixed comparator. While existing methods excel in one or two of these regimes, they typically fail to unify all three without sacrificing optimal rates or requiring oracle access to problem-dependent parameters. In this work, we bridge this gap by introducing COMPASS-Hedge. Our algorithm is the first full-information method to simultaneously achieve: […]

Ver mais

:::info Astounding Stories of Super-Science May 2001, by Astounding Stories is part of HackerNoon’s Book Blog Post series. You can jump to any chapter in this book here. A ROOM WITH A VIEW – Chapter XX – The End of the Middle Ages Astounding Stories of Super-Science May 2001: A ROOM WITH A VIEW – Chapter XX – The End of the Middle Ages By E. M. Forster ::: The Miss Alans did go to Greece, but they went […]

Ver mais

arXiv:2607.02576v1 Announce Type: new Abstract: Parameter-Efficient Fine-Tuning (PEFT) commonly adapts pretrained weights through low-rank updates, and recent methods further exploit the singular value decomposition (SVD) of the base weight for initialization or subspace selection. However, these methods do not explicitly preserve the coupled geometry between the pretrained left and right singular bases. Motivated by recent minimum-perturbation theory, which shows that stable finetuning follows a coherent SVD rotation in which a single orthogonal $Q$ acts on both the left […]

Ver mais

Soft Q-learning has emerged as a versatile model-free method for entropy-regularised reinforcement learning, optimising for returns augmented with a penalty on the divergence from a reference policy. Despite its success, the multi-step extensions of soft Q-learning remain relatively unexplored and limited to on-policy action sampling under the Boltzmann policy. In this brief research note, we first present a formal $n$-step formulation for soft Q-learning and then extend this framework to the fully off-policy case by introducing a novel […]

Ver mais

arXiv:2602.11170v1 Announce Type: new Abstract: Large language models have demonstrated remarkable capabilities across diverse reasoning tasks, yet their performance on algorithmic reasoning remains limited. To handle this limitation, we propose PRIME (Policy-Reinforced Iterative Multi-agent Execution), a framework comprising three specialized agents, an executor for step-by-step reasoning, a verifier for constraint checking, and a coordinator for backtracking control, optimized through group relative policy optimization. For comprehensive evaluation, we introduce PRIME-Bench, the largest algorithmic reasoning benchmark to date, comprising 86 […]

Ver mais

Every enterprise revenue team has seen the demonstration at some point. The AI suggests a price, routes an approval, and flags a risk with apparent confidence, and the room is impressed by the fluency of it. What happens six months after go-live tends to be a different conversation, where the team is managing exceptions, investigating outputs that conflict with internal policy, and reconciling AI-generated recommendations against business rules the system had no reliable way to access in the […]

Ver mais