arXiv:2510.21315v1 Announce Type: cross Abstract: Biological circuits have evolved to incorporate multiple modules that perform similar functions. In the fly olfactory circuit, both lateral inhibition (LI) and neuronal spike frequency adaptation (SFA) are thought to enhance pattern separation for odor learning. However, it remains unclear whether these mechanisms play redundant or distinct roles in this […]
Patient-specific AI for generation of 3D dosimetry imaging from two 2D-planar measurements
arXiv:2510.21362v1 Announce Type: cross Abstract: In this work we explored the use of patient specific reinforced learning to generate 3D activity maps from two 2D planar images (anterior and posterior). The solution of this problem remains unachievable using conventional methodologies and is of particular interest for dosimetry in nuclear medicine where approaches for post-therapy distribution […]
Large Language Models Meet Text-Attributed Graphs: A Survey of Integration Frameworks and Applications
arXiv:2510.21131v1 Announce Type: cross Abstract: Large Language Models (LLMs) have achieved remarkable success in natural language processing through strong semantic understanding and generation. However, their black-box nature limits structured and multi-hop reasoning. In contrast, Text-Attributed Graphs (TAGs) provide explicit relational structures enriched with textual context, yet often lack semantic depth. Recent research shows that combining […]
Securing AI Agent Execution
arXiv:2510.21236v1 Announce Type: cross Abstract: Large Language Models (LLMs) have evolved into AI agents that interact with external tools and environments to perform complex tasks. The Model Context Protocol (MCP) has become the de facto standard for connecting agents with such resources, but security has lagged behind: thousands of MCP servers execute with unrestricted access […]
Causal Head Gating: A Framework for Interpreting Roles of Attention Heads in Transformers
arXiv:2505.13737v2 Announce Type: replace Abstract: We present causal head gating (CHG), a scalable method for interpreting the functional roles of attention heads in transformer models. CHG learns soft gates over heads and assigns them a causal taxonomy – facilitating, interfering, or irrelevant – based on their impact on task performance. Unlike prior approaches in mechanistic […]
CDrugRed: A Chinese Drug Recommendation Dataset for Discharge Medications in Metabolic Diseases
arXiv:2510.21084v1 Announce Type: cross Abstract: Intelligent drug recommendation based on Electronic Health Records (EHRs) is critical for improving for improving the quality and efficiency of clinical decision-making. By leveraging large-scale patient data, drug recommendation systems can assist physicians in selecting the most appropriate medications according to a patient’s medical history, diagnoses, laboratory results, and comorbidities. […]
Multi-stable oscillations in cortical networks with two classes of inhibition
arXiv:2510.20848v1 Announce Type: new Abstract: In the classic view of cortical rhythms, the interaction between excitatory pyramidal neurons (E) and inhibitory parvalbumin neurons (I) has been shown to be sufficient to generate gamma and beta band rhythms. However, it is now clear that there are multiple inhibitory interneuron subtypes and that they play important roles […]
Foundation Models in Dermatopathology: Skin Tissue Classification
arXiv:2510.21664v1 Announce Type: cross Abstract: The rapid generation of whole-slide images (WSIs) in dermatopathology necessitates automated methods for efficient processing and accurate classification. This study evaluates the performance of two foundation models, UNI and Virchow2, as feature extractors for classifying WSIs into three diagnostic categories: melanocytic, basaloid, and squamous lesions. Patch-level embeddings were aggregated into […]
DP-LLM: Runtime Model Adaptation with Dynamic Layer-wise Precision Assignment
arXiv:2508.06041v2 Announce Type: replace-cross Abstract: How can we effectively handle queries for on-device large language models (LLMs) with varying runtime constraints, such as latency and accuracy? Multi-scale quantization addresses this challenge by enabling memory-efficient runtime model adaptation of LLMs through the overlaying of multiple model variants quantized to different bitwidths. Meanwhile, an important question still […]
Collective Communication for 100k+ GPUs
arXiv:2510.20171v2 Announce Type: replace-cross Abstract: The increasing scale of large language models (LLMs) necessitates highly efficient collective communication frameworks, particularly as training workloads extend to hundreds of thousands of GPUs. Traditional communication methods face significant throughput and latency limitations at this scale, hindering both the development and deployment of state-of-the-art models. This paper presents the […]