Tootfinder

AdaptiveGuard: Towards Adaptive Runtime Safety for LLM-Powered Software
Rui Yang, Michael Fu, Chakkrit Tantithamthavorn, Chetan Arora, Gunel Gulmammadova, Joey Chua
https://arxiv.org/abs/2509.16861

AdaptiveGuard: Towards Adaptive Runtime Safety for LLM-Powered Software
Guardrails are critical for the safe deployment of Large Language Models (LLMs)-powered software. Unlike traditional rule-based systems with limited, predefined input-output spaces that inherently constrain unsafe behavior, LLMs enable open-ended, intelligent interactions--opening the door to jailbreak attacks through user inputs. Guardrails serve as a protective layer, filtering unsafe prompts before they reach the LLM. However, prior research shows that jailbreak attacks can still succeed ove…

EASE: Embodied Active Event Perception via Self-Supervised Energy Minimization
Zhou Chen, Sanjoy Kundu, Harsimran S. Baweja, Sathyanarayanan N. Aakur
https://arxiv.org/abs/2506.17516

EASE: Embodied Active Event Perception via Self-Supervised Energy Minimization
Active event perception, the ability to dynamically detect, track, and summarize events in real time, is essential for embodied intelligence in tasks such as human-AI collaboration, assistive robotics, and autonomous navigation. However, existing approaches often depend on predefined action spaces, annotated datasets, and extrinsic rewards, limiting their adaptability and scalability in dynamic, real-world scenarios. Inspired by cognitive theories of event perception and predictive coding, we p…

Tenure Under Pressure: Simulating the Disruptive Effects of AI on Academic Publishing
Shan Jiang
https://arxiv.org/abs/2509.16925 https://arxiv.org/pdf/250…

Tenure Under Pressure: Simulating the Disruptive Effects of AI on Academic Publishing
Generative artificial intelligence (AI) has begun to reshape academic publishing by enabling the rapid production of submission-ready manuscripts. While such tools promise to enhance productivity, they also raise concerns about overwhelming journal systems that have fixed acceptance capacities. This paper uses simulation modeling to investigate how AI-driven surges in submissions may affect desk rejection rates, review cycles, and faculty publication portfolios, with a focus on business school …

Terrestrial Planet Formation from Two Source Reservoirs
David Nesvorny, Alessandro Morbidelli, William F. Bottke, Rogerio Deienno, Max Goldberg
https://arxiv.org/abs/2507.14814

Terrestrial Planet Formation from Two Source Reservoirs
This work describes new dynamical simulations of terrestrial planet formation. The simulations started at the protoplanetary disk stage, when planetesimals formed and accreted into protoplanets, and continued past the late stage of giant impacts. We explored the effect of different parameters, such as the initial radial distribution of planetesimals and Type-I migration of protoplanets, on the final results. In each case, a thousand simulations were completed to characterize the stochastic natu…

Political Leaning and Politicalness Classification of Texts
Matous Volf (DELTA High school of computer science and economics, Pardubice, Czechia), Jakub Simko (Kempelen Institute of Intelligent Technologies, Bratislava, Slovakia)
https://arxiv.org/abs/2507.13913

Political Leaning and Politicalness Classification of Texts
This paper addresses the challenge of automatically classifying text according to political leaning and politicalness using transformer models. We compose a comprehensive overview of existing datasets and models for these tasks, finding that current approaches create siloed solutions that perform poorly on out-of-distribution texts. To address this limitation, we compile a diverse dataset by combining 12 datasets for political leaning classification and creating a new dataset for politicalness …

Uncertainty-Informed Scheduling of Decision Points for Intelligent Mobile Health Interventions
Asim H. Gazi, Bhanu T. Gullapalli, Daiqi Gao, Benjamin M. Marlin, Vivek Shetty, Susan A. Murphy
https://arxiv.org/abs/2507.10798

Uncertainty-Informed Scheduling of Decision Points for Intelligent Mobile Health Interventions
Timely decision making is critical to the effectiveness of mobile health (mHealth) interventions. At predefined timepoints called "decision points," intelligent mHealth systems such as just-in-time adaptive interventions (JITAIs) estimate an individual's biobehavioral context from sensor or survey data and determine whether and how to intervene. For interventions targeting habitual behavior (e.g., oral hygiene), effectiveness often hinges on delivering support shortly before the target behavior…

AlphaAgents: Large Language Model based Multi-Agents for Equity Portfolio Constructions
Tianjiao Zhao, Jingrao Lyu, Stokes Jones, Harrison Garber, Stefano Pasquali, Dhagash Mehta
https://arxiv.org/abs/2508.11152

AlphaAgents: Large Language Model based Multi-Agents for Equity Portfolio Constructions
The field of artificial intelligence (AI) agents is evolving rapidly, driven by the capabilities of Large Language Models (LLMs) to autonomously perform and refine tasks with human-like efficiency and adaptability. In this context, multi-agent collaboration has emerged as a promising approach, enabling multiple AI agents to work together to solve complex challenges. This study investigates the application of role-based multi-agent systems to support stock selection in equity research and portfo…

Gradient-Based Inverse Optimization of Atom-Chip Wire Currents for BEC Transport
Naoki Shibuya
https://arxiv.org/abs/2508.11712 https://arxiv.org/pdf/2508.…

Gradient-Based Inverse Optimization of Atom-Chip Wire Currents for BEC Transport
Modulating wire currents to shift a magnetic trap along an atom chip enables smooth contact-free delivery of Bose-Einstein condensates but can deform the confinement profile causing parametric heating and atom loss. We introduce a fast simulation framework based on inverse optimization that, given an initial trap and a predefined trajectory over time, computes a wire current schedule that transports the atoms and restores the trap geometry upon arrival. We assess trap's minimum energy, lateral …

Data management software vendor Rubrik agrees to acquire Predibase, which helps with deploying AI models; source: Rubrik plans to pay between $100M and $500M (Jordan Novet/CNBC)
https://www.cnbc.com/2025/06/25/rubrik-agrees-to-bu…

Rubrik agrees to buy AI startup Predibase for over $100 million
Rubrik is seeking to bolster its artificial intelligence capabilities through acquisition.

A Lightweight Privacy-Preserving Smart Metering Billing Protocol with Dynamic Tariff Policy Adjustment
Farid Zaredar, Morteza Amini
https://arxiv.org/abs/2508.14815 https://

A Lightweight Privacy-Preserving Smart Metering Billing Protocol with Dynamic Tariff Policy Adjustment
The integration of information and communication technology (ICT) with traditional power grids has led to the emergence of smart grids. Advanced metering infrastructure (AMI) plays a crucial role in smart grids by facilitating two-way communication between smart meters and the utility provider. This bidirectional communication allows intelligent meters to report fine-grained consumption data at predefined intervals, enabling accurate billing, efficient grid monitoring and management, and rapid …