arXiv:2603.25158v1 Announce Type: new Abstract: Equipping Large Language Model (LLM) agents with domain-specific skills is critical for tackling complex tasks. Yet, manual authoring creates a severe scalability bottleneck. Conversely, automated skill generation often yields fragile or fragmented results because it either relies on shallow parametric knowledge or sequentially overfits to non-generalizable trajectory-local lessons. To overcome […]
PIDP-Attack: Combining Prompt Injection with Database Poisoning Attacks on Retrieval-Augmented Generation Systems
arXiv:2603.25164v1 Announce Type: cross Abstract: Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of applications. However, their practical deployment is often hindered by issues such as outdated knowledge and the tendency to generate hallucinations. To address these limitations, Retrieval-Augmented Generation (RAG) systems have been introduced, enhancing LLMs with external, up-to-date knowledge […]
The Competence Shadow: Theory and Bounds of AI Assistance in Safety Engineering
arXiv:2603.25197v1 Announce Type: new Abstract: As AI assistants become integrated into safety engineering workflows for Physical AI systems, a critical question emerges: does AI assistance improve safety analysis quality, or introduce systematic blind spots that surface only through post-deployment incidents? This paper develops a formal framework for AI assistance in safety analysis. We first establish […]
The Landscape of AI in Science Education: What is Changing and How to Respond
arXiv:2602.18469v2 Announce Type: replace-cross Abstract: This introductory chapter explores the transformative role of artificial intelligence (AI) in reshaping the landscape of science education. Positioned at the intersection of tradition and innovation, AI is altering educational goals, procedures, learning materials, assessment practices, and desired outcomes. We highlight how AI-supported tools, such as intelligent tutoring systems, adaptive […]
Lingshu-Cell: A generative cellular world model for transcriptome modeling toward virtual cells
arXiv:2603.25240v1 Announce Type: new Abstract: Modeling cellular states and predicting their responses to perturbations are central challenges in computational biology and the development of virtual cells. Existing foundation models for single-cell transcriptomics provide powerful static representations, but they do not explicitly model the distribution of cellular states for generative simulation. Here, we introduce Lingshu-Cell, a […]
Vision Hopfield Memory Networks
arXiv:2603.25157v1 Announce Type: cross Abstract: Recent vision and multimodal foundation backbones, such as Transformer families and state-space models like Mamba, have achieved remarkable progress, enabling unified modeling across images, text, and beyond. Despite their empirical success, these architectures remain far from the computational principles of the human brain, often demanding enormous amounts of training data […]
Distribution and Clusters Approximations as Abstract Domains in Probabilistic Abstract Interpretation to Neural Network Analysis
arXiv:2603.25273v1 Announce Type: new Abstract: The probabilistic abstract interpretation framework of neural network analysis analyzes a neural network by analyzing its density distribution flow of all possible inputs. The grids approximation is one of abstract domains the framework uses which abstracts concrete space into grids. In this paper, we introduce two novel approximation methods: distribution […]
Monocular Normal Estimation via Shading Sequence Estimation
arXiv:2602.09929v5 Announce Type: replace-cross Abstract: Monocular normal estimation aims to estimate the normal map from a single RGB image of an object under arbitrary lights. Existing methods rely on deep models to directly predict normal maps. However, they often suffer from 3D misalignment: while the estimated normal maps may appear to have a correct appearance, […]
SliderQuant: Accurate Post-Training Quantization for LLMs
arXiv:2603.25284v1 Announce Type: new Abstract: In this paper, we address post-training quantization (PTQ) for large language models (LLMs) from an overlooked perspective: given a pre-trained high-precision LLM, the predominant sequential quantization framework treats different layers equally, but this may be not optimal in challenging bit-width settings. We empirically study the quantization impact of different layers […]
Photon: Speedup Volume Understanding with Efficient Multimodal Large Language Models
arXiv:2603.25155v1 Announce Type: cross Abstract: Multimodal large language models are promising for clinical visual question answering tasks, but scaling to 3D imaging is hindered by high computational costs. Prior methods often rely on 2D slices or fixed-length token compression, disrupting volumetric continuity and obscuring subtle findings. We present Photon, a framework that represents 3D medical […]
Evaluating Language Models for Harmful Manipulation
arXiv:2603.25326v1 Announce Type: new Abstract: Interest in the concept of AI-driven harmful manipulation is growing, yet current approaches to evaluating it are limited. This paper introduces a framework for evaluating harmful AI manipulation via context-specific human-AI interaction studies. We illustrate the utility of this framework by assessing an AI model with 10,101 participants spanning interactions […]
Temporal Sepsis Modeling: a Fully Interpretable Relational Way
arXiv:2601.21747v2 Announce Type: replace-cross Abstract: Sepsis remains one of the most complex and heterogeneous syndromes in intensive care, characterized by diverse physiological trajectories and variable responses to treatment. While deep learning models perform well in the early prediction of sepsis, they often lack interpretability and ignore latent patient sub-phenotypes. In this work, we propose a […]