arXiv:2512.23190v2 Announce Type: replace-cross Abstract: Online eXp-concave Optimization (OXO) is a fundamental problem in online learning, where the goal is to minimize regret when loss functions are exponentially concave. The standard algorithm, Online Newton Step (ONS), guarantees an optimal $O(d log T)$ regret, where $d$ is the dimension and $T$ is the time horizon. Despite its simplicity, ONS may face a computational bottleneck due to the Mahalanobis projection at each round. This step costs $Omega(d^omega)$ arithmetic operations for […]

Ver mais

We present THEIA, a modular neural architecture that learns complete Kleene three-valued logic (K3) end-to-end without any external symbolic solver, and investigate what architectural prior enables compositional generalization under uncertainty. THEIA processes four mathematical domains (arithmetic, order, set membership, propositional logic) through dedicated engines that converge in a final logic module. Trained on a 2M-sample dataset with input space ~3.4×10^13, it achieves 12/12 Kleene K3 rule coverage across 5 seeds in 9.2 +/- 3.5 minutes (5.6x faster than […]

Ver mais

Multi-task representation learning (MTRL) is an approach that learns shared latent representations across related tasks, facilitating collaborative learning that improves the overall learning efficiency. This paper studies MTRL for multi-task reinforcement learning (RL), where multiple tasks have the same state-action space and transition probabilities, but different rewards. We consider T linear Markov Decision Processes (MDPs) where the reward functions and transition dynamics admit linear feature embeddings of dimension d. The relatedness among the tasks is captured by a […]

Ver mais

In a world where ransomware strikes, attempts at data manipulation, and system-crippling intrusions against hospitals are on the rise, the healthcare sector has reached a breaking point. These are no longer attacks on mere data; they are on ventilators, on imaging machines, on diagnostic algorithms, and on the very systems that sustain patients’ lives. On a national level across the United States, even a single breach has the power to halt surgeries, divert ambulances, and put lives in […]

Ver mais

arXiv:2604.13121v1 Announce Type: new Abstract: Locating and intercepting a moving target from possibly delayed, intermittent sensory signals is a paradigmatic problem in decision-making under uncertainty, and a fundamental challenge for, e.g., animals seeking prey or mates and autonomous robotic systems. Odor signals are intermittent, strongly mixed by turbulent-like transport, and typically lag behind the true target position, thereby complicating localization. Here, we formulate olfactory pursuit as a partially observable Markov decision process in which an agent maintains a […]

Ver mais

When you go to the doctor, one thing you may have noticed is how trash is handled. Usually, there are multiple trash cans for regular waste and biohazard waste. While this is done to prevent contamination to other individuals, it is also very costly for medical providers if they fail to properly dispose of their waste. For every violation where a sharp object is thrown away improperly, there is a $13,653 fine per violation. This does not include […]

Ver mais

arXiv:2603.26668v1 Announce Type: new Abstract: As an important paradigm for enhancing the generation quality of Large Language Models (LLMs), retrieval-augmented generation (RAG) faces the two challenges regarding retrieval accuracy and computational efficiency. This paper presents a novel RAG framework called Bridge-RAG. To overcome the accuracy challenge, we introduce the concept of abstract to bridge query entities and document chunks, providing robust semantic understanding. We organize the abstracts into a tree structure and design a multi-level retrieval strategy to […]

Ver mais

A crucial consideration when developing and deploying Large Language Models (LLMs) is the human values to which these models are aligned. In the constitutional framework of alignment models are aligned to a set of principles (the constitution) specified in natural language. However, it is unclear how to fairly determine this constitution with widespread stakeholder input. In this work we propose Grounded Constitutional AI (GCAI), a unified framework for generating constitutions of principles that are representative of both users’ […]

Ver mais

arXiv:2601.03273v1 Announce Type: new Abstract: As large language models (LLMs) become deeply embedded in daily life, the urgent need for safer moderation systems, distinguishing between naive from harmful requests while upholding appropriate censorship boundaries, has never been greater. While existing LLMs can detect harmful or unsafe content, they often struggle with nuanced cases such as implicit offensiveness, subtle gender and racial biases, and jailbreak prompts, due to the subjective and context-dependent nature of these issues. Furthermore, their heavy […]

Ver mais

arXiv:2604.17008v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used to generate narrative content, including children’s stories, which play an important role in social and cultural learning. Despite growing interest in AI safety and alignment, most existing evaluations focus primarily on English, leaving the cross-lingual generalization of aligned behavior underexplored. In this work, we introduce BiasedTales-ML, a large-scale parallel corpus of approximately 350,000 children’s stories generated across eight typologically and culturally diverse languages using a full-permutation […]

Ver mais