Stay updated with the latest research and technology news
arXiv:2602.14844v1 Announce Type: new Abstract: AI alignment is growing in importance, yet current approaches suffer from a critical structural flaw that entangles the safety objectives...
arXiv:2602.14846v1 Announce Type: new Abstract: We propose a multi-dimensional persistent sheaf Laplacian (MPSL) framework on simplicial complexes for image analysis. The proposed method is motivated...
arXiv:2602.14849v1 Announce Type: new Abstract: LLM agents increasingly act on external systems, yet tool effects are immediate. Under failures, speculation, or contention, losing branches can...
arXiv:2602.14850v1 Announce Type: new Abstract: The problem of allocating indivisible resources to agents arises in a wide range of domains, including treatment distribution and social...
arXiv:2602.14853v1 Announce Type: new Abstract: The traditional limitations of neural networks in reliably generalizing beyond the convex hulls of their training data present a significant...
arXiv:2602.14854v1 Announce Type: new Abstract: In this paper, we propose a domain decomposition dynamical low-rank method to solve high-dimensional radiative transfer problems and similar kinetic...
arXiv:2602.14855v1 Announce Type: new Abstract: Clustering algorithms are an essential part of the unsupervised data science ecosystem, and extrinsic evaluation of clustering algorithms requires a...
arXiv:2602.14857v1 Announce Type: new Abstract: Large Language Models (LLMs) have recently shown strong reasoning and generalization capabilities, motivating their use as decision-making policies in complex...
arXiv:2602.14858v1 Announce Type: new Abstract: Strategic-form min-max game theory examines the existence, multiplicity, selection of equilibria, and the worst-case computational complexity under perfect rationality. However,...
arXiv:2602.14865v1 Announce Type: new Abstract: Most web agents operate at the human interface level, observing screenshots or raw DOM trees without application-level access, which limits...
arXiv:2602.14868v1 Announce Type: new Abstract: Reinforcement learning has emerged as a powerful paradigm for unlocking reasoning capabilities in large language models. However, relying on sparse...
arXiv:2602.14869v1 Announce Type: new Abstract: As large language models are increasingly trained and fine-tuned, practitioners need methods to identify which training data drive specific behaviors,...
arXiv:2602.14871v1 Announce Type: new Abstract: Self-Sovereign Identity (SSI) enables user-controlled, cryptographically verifiable credentials. As EU regulations mandate EUDI Wallet acceptance by 2027, SSI adoption becomes...
arXiv:2602.14872v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has been a main driver of recent breakthroughs in large reasoning models. Yet it...
arXiv:2602.14874v1 Announce Type: new Abstract: Traditional learning from demonstration (LfD) generally demands a cumbersome collection of physical demonstrations, which can be time-consuming and challenging to...
arXiv:2602.14878v1 Announce Type: new Abstract: The Model Context Protocol (MCP) standardizes how Foundation Model (FM)-based agents interact with external systems by invoking tools. However, to...
arXiv:2602.14879v1 Announce Type: new Abstract: Artificial intelligence (AI) can automatically delineate lesions on computed tomography (CT) and generate radiology report content, yet progress is limited...
arXiv:2602.14889v1 Announce Type: new Abstract: We introduce Web-Scale Multimodal Summarization, a lightweight framework for generating summaries by combining retrieved text and image data from web...
arXiv:2602.14890v1 Announce Type: new Abstract: Reconciling the tension between inductive learning and deductive reasoning in first-order relational domains is a longstanding challenge in AI. We...
arXiv:2602.14896v1 Announce Type: new Abstract: Large-scale deep learning models are well-suited for compression. Methods like pruning, quantization, and knowledge distillation have been used to achieve...
arXiv:2602.14901v1 Announce Type: new Abstract: Task-specialized models form the backbone of agentic healthcare systems, enabling the agents to answer clinical queries across tasks such as...
arXiv:2602.14903v1 Announce Type: new Abstract: Chain-of-thought (CoT) prompting is a de-facto standard technique to elicit reasoning-like responses from large language models (LLMs), allowing them to...
arXiv:2602.14904v1 Announce Type: new Abstract: Models of High-level Computation (MHCs) provide effective means to describe complex real-world computing systems because they offer formal foundations for...
arXiv:2602.14909v1 Announce Type: new Abstract: Classical controllability and observability characterise reachability and reconstructibility of the full system state and admit equivalent geometric and eigenvalue-based Popov-Belevitch-Hautus...