arXiv:2408.13406v2 Announce Type: replace Abstract: Large Language Model (LLM)-based multi-agent systems are increasingly applied to automate computational workflows in science and engineering. However, how inter-agent dynamics influence reasoning quality and verification reliability remains unclear. We study these mechanisms using an AutoGen-based multi-agent framework for linear-elastic Finite Element Analysis (FEA), evaluating seven role configurations across four […]
OMPILOT: Harnessing Transformer Models for Auto Parallelization to Shared Memory Computing Paradigms
arXiv:2511.03866v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have significantly accelerated progress in code translation, enabling more accurate and efficient transformation across programming languages. While originally developed for natural language processing, LLMs have shown strong capabilities in modeling programming language syntax and semantics, outperforming traditional rule-based systems in both accuracy and […]
KnowThyself: An Agentic Assistant for LLM Interpretability
arXiv:2511.03878v1 Announce Type: new Abstract: We develop KnowThyself, an agentic assistant that advances large language model (LLM) interpretability. Existing tools provide useful insights but remain fragmented and code-intensive. KnowThyself consolidates these capabilities into a chat-based interface, where users can upload models, pose natural language questions, and obtain interactive visualizations with guided explanations. At its core, […]
SnappyMeal: Design and Longitudinal Evaluation of a Multimodal AI Food Logging Application
arXiv:2511.03907v1 Announce Type: cross Abstract: Food logging, both self-directed and prescribed, plays a critical role in uncovering correlations between diet, medical, fitness, and health outcomes. Through conversations with nutritional experts and individuals who practice dietary tracking, we find current logging methods, such as handwritten and app-based journaling, are inflexible and result in low adherence and […]
BOTS: A Unified Framework for Bayesian Online Task Selection in LLM Reinforcement Finetuning
arXiv:2510.26374v2 Announce Type: replace Abstract: Reinforcement finetuning (RFT) is a key technique for aligning Large Language Models (LLMs) with human preferences and enhancing reasoning, yet its effectiveness is highly sensitive to which tasks are explored during training. Uniform task sampling is inefficient, wasting computation on tasks that are either trivial or unsolvable, while existing task […]
NVIDIA Nemotron Nano V2 VL
arXiv:2511.03929v1 Announce Type: cross Abstract: We introduce Nemotron Nano V2 VL, the latest model of the Nemotron vision-language series designed for strong real-world document understanding, long video comprehension, and reasoning tasks. Nemotron Nano V2 VL delivers significant improvements over our previous model, Llama-3.1-Nemotron-Nano-VL-8B, across all vision and text domains through major enhancements in model architecture, […]
Simulating the impact of perception bias on social contact surveys for infectious disease modelling
arXiv:2511.03897v1 Announce Type: new Abstract: Social contact patterns are a key input to many infectious disease models. Contact surveys, where participants are asked to provide information on their recent close and casual contacts with others, are one of the standard methods to measure contact patterns in a population. Surveys that require detailed sociodemographic descriptions of […]
Improving Multi-View Reconstruction via Texture-Guided Gaussian-Mesh Joint Optimization
arXiv:2511.03950v1 Announce Type: cross Abstract: Reconstructing real-world objects from multi-view images is essential for applications in 3D editing, AR/VR, and digital content creation. Existing methods typically prioritize either geometric accuracy (Multi-View Stereo) or photorealistic rendering (Novel View Synthesis), often decoupling geometry and appearance optimization, which hinders downstream editing tasks. This paper advocates an unified treatment […]
GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs
arXiv:2411.14133v3 Announce Type: replace-cross Abstract: LLMs have shown impressive capabilities across various natural language processing tasks, yet remain vulnerable to input prompts, known as jailbreak attacks, carefully designed to bypass safety guardrails and elicit harmful responses. Traditional methods rely on manual heuristics but suffer from limited generalizability. Despite being automatic, optimization-based attacks often produce unnatural […]
Multiscale Astrocyte Network Calcium Dynamics for Biologically Plausible Intelligence in Anomaly Detection
arXiv:2511.03993v1 Announce Type: cross Abstract: Network anomaly detection systems encounter several challenges with traditional detectors trained offline. They become susceptible to concept drift and new threats such as zero-day or polymorphic attacks. To address this limitation, we propose a Ca$^2+$-modulated learning framework that draws inspiration from astrocytic Ca$^2+$ signaling in the brain, where rapid, context-sensitive […]