Tootfinder

Live-Webinar: Was macOS 26, iOS 26 & Co. für das Apple Gerätemanagement bedeuten
Apples neue Systeme bringen viele Neuerungen für das Gerätemanagement. Erfahren Sie, wie Sie mit Ihnen die Effizienz und Sicherheit Ihres Unternehmens steigern.

Text as Any-Modality for Zero-Shot Classification by Consistent Prompt Tuning
Xiangyu Wu, Feng Yu, Yang Yang, Jianfeng Lu
https://arxiv.org/abs/2508.06382 https://

Text as Any-Modality for Zero-Shot Classification by Consistent Prompt Tuning
The integration of prompt tuning with multimodal learning has shown significant generalization abilities for various downstream tasks. Despite advancements, existing methods heavily depend on massive modality-specific labeled data (e.g., video, audio, and image), or are customized for a single modality. In this study, we present Text as Any-Modality by Consistent Prompt Tuning (TaAM-CPT), a scalable approach for constructing a general representation model toward unlimited modalities using solel…

X-Teaming Evolutionary M2S: Automated Discovery of Multi-turn to Single-turn Jailbreak Templates
Hyunjun Kim, Junwoo Ha, Sangyoon Yu, Haon Park
https://arxiv.org/abs/2509.08729 …

X-Teaming Evolutionary M2S: Automated Discovery of Multi-turn to Single-turn Jailbreak Templates
Multi-turn-to-single-turn (M2S) compresses iterative red-teaming into one structured prompt, but prior work relied on a handful of manually written templates. We present X-Teaming Evolutionary M2S, an automated framework that discovers and optimizes M2S templates through language-model-guided evolution. The system pairs smart sampling from 12 sources with an LLM-as-judge inspired by StrongREJECT and records fully auditable logs. Maintaining selection pressure by setting the success threshold …

DP-FedLoRA: Privacy-Enhanced Federated Fine-Tuning for On-Device Large Language Models
Honghui Xu, Shiva Shrestha, Wei Chen, Zhiyuan Li, Zhipeng Cai
https://arxiv.org/abs/2509.09097

DP-FedLoRA: Privacy-Enhanced Federated Fine-Tuning for On-Device Large Language Models
As on-device large language model (LLM) systems become increasingly prevalent, federated fine-tuning enables advanced language understanding and generation directly on edge devices; however, it also involves processing sensitive, user-specific data, raising significant privacy concerns within the federated learning framework. To address these challenges, we propose DP-FedLoRA, a privacy-enhanced federated fine-tuning framework that integrates LoRA-based adaptation with differential privacy in a…

Signature of polarized ultralight vector dark matter in pulsar timing arrays
Kimihiro Nomura, Hidetoshi Omiya, Takahiro Tanaka
https://arxiv.org/abs/2508.07358 https://

Signature of polarized ultralight vector dark matter in pulsar timing arrays
We investigate observational signatures of ultralight vector dark matter with masses $m \sim 10^{-24}$-$10^{-22}$ eV in pulsar timing arrays, taking into account general polarization states of the vector field. We find that vector dark matter induces pulsar timing residuals with nontrivial directional dependence, reflecting the anisotropic property and polarization structure specific to vector dark matter, unlike scalar dark matter. We also derive angular correlation curves of the timing residu…

On the Effect of Instruction Tuning Loss on Generalization
Anwoy Chatterjee, H S V N S Kowndinya Renduchintala, Sumit Bhatia, Tanmoy Chakraborty
https://arxiv.org/abs/2507.07817

On the Effect of Instruction Tuning Loss on Generalization
Instruction Tuning has emerged as a pivotal post-training paradigm that enables pre-trained language models to better follow user instructions. Despite its significance, little attention has been given to optimizing the loss function used. A fundamental, yet often overlooked, question is whether the conventional auto-regressive objective - where loss is computed only on response tokens, excluding prompt tokens - is truly optimal for instruction tuning. In this work, we systematically investigat…

Zweiteiliges Webinar: Apple-Gerätemanagement gemäß IT-Grundschutz des BSI
Optimieren Sie die Sicherheit und Compliance Ihrer Apple-Geräte. Zwei Webinare über Systemsicherheit sowie zur Umsetzung der IT-Grundschutz-Vorgaben des BSI.

PeftCD: Leveraging Vision Foundation Models with Parameter-Efficient Fine-Tuning for Remote Sensing Change Detection
Sijun Dong, Yuxuan Hu, LiBo Wang, Geng Chen, Xiaoliang Meng
https://arxiv.org/abs/2509.09572

PeftCD: Leveraging Vision Foundation Models with Parameter-Efficient Fine-Tuning for Remote Sensing Change Detection
To tackle the prevalence of pseudo changes, the scarcity of labeled samples, and the difficulty of cross-domain generalization in multi-temporal and multi-source remote sensing imagery, we propose PeftCD, a change detection framework built upon Vision Foundation Models (VFMs) with Parameter-Efficient Fine-Tuning (PEFT). At its core, PeftCD employs a weight-sharing Siamese encoder derived from a VFM, into which LoRA and Adapter modules are seamlessly integrated. This design enables highly effici…

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection
Ivan Zhang
https://arxiv.org/abs/2508.07139 https://arxiv.org/pdf/2508.07139

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection
Ensuring LLM alignment is critical to information security as AI models become increasingly widespread and integrated in society. Unfortunately, many defenses against adversarial attacks and jailbreaking on LLMs cannot adapt quickly to new attacks, degrade model responses to benign prompts, or introduce significant barriers to scalable implementation. To mitigate these challenges, we introduce a real-time, self-tuning (RTST) moderator framework to defend against adversarial attacks while mainta…

Low-Resource Fine-Tuning for Multi-Task Structured Information Extraction with a Billion-Parameter Instruction-Tuned Model
Yu Cheng Chih, Yong Hao Hou
https://arxiv.org/abs/2509.08381

Low-Resource Fine-Tuning for Multi-Task Structured Information Extraction with a Billion-Parameter Instruction-Tuned Model
Deploying large language models (LLMs) for structured data extraction in domains such as financial compliance reporting, legal document analytics, and multilingual knowledge base construction is often impractical for smaller teams due to the high cost of running large architectures and the difficulty of preparing large, high-quality datasets. Most recent instruction-tuning studies focus on seven-billion-parameter or larger models, leaving limited evidence on whether much smaller models can work…