Tootfinder

SecInfer: Preventing Prompt Injection via Inference-time Scaling
Yupei Liu, Yanting Wang, Yuqi Jia, Jinyuan Jia, Neil Zhenqiang Gong
https://arxiv.org/abs/2509.24967 https://

SecInfer: Preventing Prompt Injection via Inference-time Scaling
Prompt injection attacks pose a pervasive threat to the security of Large Language Models (LLMs). State-of-the-art prevention-based defenses typically rely on fine-tuning an LLM to enhance its security, but they achieve limited effectiveness against strong attacks. In this work, we propose \emph{SecInfer}, a novel defense against prompt injection attacks built on \emph{inference-time scaling}, an emerging paradigm that boosts LLM capability by allocating more compute resources for reasoning dur…

Markov Decision Processing Networks
Sanidhay Bhambay, Thirupathaiah Vasantam, Neil Walton
https://arxiv.org/abs/2509.24541 https://arxiv.org/pdf/2509.24541…

Markov Decision Processing Networks
We introduce Markov Decision Processing Networks (MDPNs) as a multiclass queueing network model where service is a controlled, finite-state Markov process. The model exhibits a decision-dependent service process where actions taken influence future service availability. Viewed as a two-sided queueing model, this captures settings such as assemble-to-order systems, ride-hailing platforms, cross-skilled call centers, and quantum switches. We first characterize the capacity region of MDPNs. Unli…

Multihead Finite-State Dimension
Xiang Huang, Xiaoyuan Li, Jack H. Lutz, Neil Lutz
https://arxiv.org/abs/2509.22912 https://arxiv.org/pdf/2509.22912…

Multihead Finite-State Dimension
We introduce multihead finite-state dimension, a generalization of finite-state dimension in which a group of finite-state agents (the heads) with oblivious, one-way movement rules, each reporting only one symbol at a time, enable their leader to bet on subsequent symbols in an infinite data stream. In aggregate, such a scheme constitutes an $h$-head finite state gambler whose maximum achievable growth rate of capital in this task, quantified using betting strategies called gales, determines th…

Spectral-temporal processing using integrated recursive electro-optic circuit
Xudong Li, Yaowen Hu, Tong Ge, Andrea Cordaro, Yunxiang Song, Xinrui Zhu, Shengyuan Lu, Keith Powell, Let\'icia Magalh\~aes, Urban Senica, Neil Sinclair, Marko Lon\v{c}ar
https://arxiv.org/abs/2509.25102

Spectral-temporal processing using integrated recursive electro-optic circuit
Advances in integrated photonics have enabled unprecedented level of control of light, powering a wide range of photonic technologies from communications and computing to precision metrology and quantum information. However, the conventional on-chip optical signal processing approaches based on optical waveguides and cavities suffer from their large physical footprint and narrow operating bandwidth, respectively. To address this, we propose and experimentally demonstrate, using the thin film li…

Comprehensive X-ray Observations of the Exceptional Ultra-long X-ray and Gamma-ray Transient GRB 250702B with Swift, NuSTAR, and Chandra: Insights from the X-ray Afterglow Properties
Brendan O'Connor, Ramandeep Gill, James DeLaunay, Jeremy Hare, Dheeraj Pasham, Eric R. Coughlin, Ananya Bandopadhyay, Akash Anumarlapudi, Paz Beniamini, Jonathan Granot, Igor Andreoni, Jonathan Carney, Michael J. Moss, Ersin G\"o\u{g}\"u\c{s}, Jamie A. Kennea, Malte Busmann, Simone Dichiara, …

Comprehensive X-ray Observations of the Exceptional Ultra-long X-ray and Gamma-ray Transient GRB 250702B with Swift, NuSTAR, and Chandra: Insights from the X-ray Afterglow Properties
GRB 250702B is an exceptional transient that produced multiple episodes of luminous gamma-ray radiation lasting for $>25$ ks, placing it among the class of ultra-long gamma-ray bursts (GRBs). However, unlike any known GRB, a soft X-ray precursor was discovered by the Einstein Probe up to 24 hours before the gamma-ray triggers. We present comprehensive X-ray observations of the transient's afterglow obtained with the Neil Gehrels Swift Observatory, the Nuclear Spectroscopic Telescope Array, and …

NaviGait: Navigating Dynamically Feasible Gait Libraries using Deep Reinforcement Learning
Neil C. Janwani, Varun Madabushi, Maegan Tucker
https://arxiv.org/abs/2510.11542 https…

NaviGait: Navigating Dynamically Feasible Gait Libraries using Deep Reinforcement Learning
Reinforcement learning (RL) has emerged as a powerful method to learn robust control policies for bipedal locomotion. Yet, it can be difficult to tune desired robot behaviors due to unintuitive and complex reward design. In comparison, offline trajectory optimization methods, like Hybrid Zero Dynamics, offer more tuneable, interpretable, and mathematically grounded motion plans for high-dimensional legged systems. However, these methods often remain brittle to real-world disturbances like exter…

Exploiting ID-Text Complementarity via Ensembling for Sequential Recommendation
Liam Collins, Bhuvesh Kumar, Clark Mingxuan Ju, Tong Zhao, Donald Loveland, Leonardo Neves, Neil Shah
https://arxiv.org/abs/2512.17820 https://arxiv.org/pdf/2512.17820 https://arxiv.org/html/2512.17820
arXiv:2512.17820v1 Announce Type: new
Abstract: Modern Sequential Recommendation (SR) models commonly utilize modality features to represent items, motivated in large part by recent advancements in language and vision modeling. To do so, several works completely replace ID embeddings with modality embeddings, claiming that modality embeddings render ID embeddings unnecessary because they can match or even exceed ID embedding performance. On the other hand, many works jointly utilize ID and modality features, but posit that complex fusion strategies, such as multi-stage training and/or intricate alignment architectures, are necessary for this joint utilization. However, underlying both these lines of work is a lack of understanding of the complementarity of ID and modality features. In this work, we address this gap by studying the complementarity of ID- and text-based SR models. We show that these models do learn complementary signals, meaning that either should provide performance gain when used properly alongside the other. Motivated by this, we propose a new SR method that preserves ID-text complementarity through independent model training, then harnesses it through a simple ensembling strategy. Despite this method's simplicity, we show it outperforms several competitive SR baselines, implying that both ID and text features are necessary to achieve state-of-the-art SR performance but complex fusion architectures are not.
toXiv_bot_toot

Position: AI Will Transform Neuropsychology Through Mental Health Digital Twins for Dynamic Mental Health Care, Especially for ADHD
Neil Natarajan, Sruthi Viswanathan, Xavier Roberts-Gaal, Michelle Marie Martel
https://arxiv.org/abs/2510.07409

Position: AI Will Transform Neuropsychology Through Mental Health Digital Twins for Dynamic Mental Health Care, Especially for ADHD
Static solutions don't serve a dynamic mind. Thus, we advocate a shift from static mental health diagnostic assessments to continuous, artificial intelligence (AI)-driven assessment. Focusing on Attention-Deficit/Hyperactivity Disorder (ADHD) as a case study, we explore how generative AI has the potential to address current capacity constraints in neuropsychology, potentially enabling more personalized and longitudinal care pathways. In particular, AI can efficiently conduct frequent, low-level…

Numerical modeling of laser cooling in molecules: From simple diatomics to polyatomics and radioactive species
Felix Kogel, Tatsam Garg, Phillip Gro{\ss}, Lukas Leczek, Marian Rockenh\"auser, Neil Shah, Jakob Wei{\ss}, Andreas Schindewolf, Tim Langen
https://arxiv.org/abs/2510.16203

Replaced article(s) found for hep-ph. https://arxiv.org/list/hep-ph/new
[1/2]:
- Repurposing lattice QCD results for composite phenomenology
Thomas DeGrand, Ethan T. Neil