Tootfinder

Evasion Attacks Against Bayesian Predictive Models
Pablo G. Arce, Roi Naveiro, David R\'ios Insua
https://arxiv.org/abs/2506.09640 https://

Evasion Attacks Against Bayesian Predictive Models
There is an increasing interest in analyzing the behavior of machine learning systems against adversarial attacks. However, most of the research in adversarial machine learning has focused on studying weaknesses against evasion or poisoning attacks to predictive models in classical setups, with the susceptibility of Bayesian predictive models to attacks remaining underexplored. This paper introduces a general methodology for designing optimal evasion attacks against such models. We investigate …

Statt Urnengang Untergang gelesen.
Hm.
https://www.republik.ch/2025/06/12/srg-mutlosigkeit-als-programm?utm_medium=social&utm_source=mastodon&utm_campaign=cm&utm_content…

SRG: Mutlosigkeit als Programm
Die Halbierungs­initiative beschädigt die SRG schon jetzt stark: Am Programm wird gespart und die Belegschaft ist frustriert.

Resa: Transparent Reasoning Models via SAEs
Shangshang Wang, Julian Asilis, \"Omer Faruk Akg\"ul, Enes Burak Bilgin, Ollie Liu, Deqing Fu, Willie Neiswanger
https://arxiv.org/abs/2506.09967

Resa: Transparent Reasoning Models via SAEs
How cost-effectively can we elicit strong reasoning in language models by leveraging their underlying representations? We answer this question with Resa, a family of 1.5B reasoning models trained via a novel and efficient sparse autoencoder tuning (SAE-Tuning) procedure. This method first trains an SAE to capture reasoning abilities from a source model, and then uses the trained SAE to guide a standard supervised fine-tuning process to elicit such abilities in a target model, all using verified…

Apple announces the Foundation Models framework, giving developers direct access to its on-device AI models for the first time (Tim Hardwick/MacRumors)
https://www.macrumors.com/2025/06/09/foundation-models-framework/

Apple Announces Foundation Models Framework for Developers to Leverage AI
Apple at WWDC today announced Foundation Models Framework, a new API allowing third-party developers to leverage the large language models at the...

From Intention to Execution: Probing the Generalization Boundaries of Vision-Language-Action Models
Irving Fang, Juexiao Zhang, Shengbang Tong, Chen Feng
https://arxiv.org/abs/2506.09930

From Intention to Execution: Probing the Generalization Boundaries of Vision-Language-Action Models
One promise that Vision-Language-Action (VLA) models hold over traditional imitation learning for robotics is to leverage the broad generalization capabilities of large Vision-Language Models (VLMs) to produce versatile, "generalist" robot policies. However, current evaluations of VLAs remain insufficient. Traditional imitation learning benchmarks are unsuitable due to the lack of language instructions. Emerging benchmarks for VLAs that incorporate language often come with limited evaluation ta…

Large Language Models for Toxic Language Detection in Low-Resource Balkan Languages
Amel Muminovic, Amela Kadric Muminovic
https://arxiv.org/abs/2506.09992

Large Language Models for Toxic Language Detection in Low-Resource Balkan Languages
Online toxic language causes real harm, especially in regions with limited moderation tools. In this study, we evaluate how large language models handle toxic comments in Serbian, Croatian, and Bosnian, languages with limited labeled data. We built and manually labeled a dataset of 4,500 YouTube and TikTok comments drawn from videos across diverse categories, including music, politics, sports, modeling, influencer content, discussions of sexism, and general topics. Four models (GPT-3.5 Turbo, G…

Analytic Task Scheduler: Recursive Least Squares Based Method for Continual Learning in Embodied Foundation Models
Lipei Xie, Yingxin Li, Huiping Zhuang
https://arxiv.org/abs/2506.09623

Analytic Task Scheduler: Recursive Least Squares Based Method for Continual Learning in Embodied Foundation Models
Embodied foundation models are crucial for Artificial Intelligence (AI) interacting with the physical world by integrating multi-modal inputs, such as proprioception, vision and language, to understand human intentions and generate actions to control robots. While these models demonstrate strong generalization and few-shot learning capabilities, they face significant challenges in continually acquiring new skills without forgetting previously learned skills, a problem known as catastrophic forg…

Know What You Don't Know: Uncertainty Calibration of Process Reward Models
Young-Jin Park, Kristjan Greenewald, Kaveh Alim, Hao Wang, Navid Azizan
https://arxiv.org/abs/2506.09338

Know What You Don't Know: Uncertainty Calibration of Process Reward Models
Process reward models (PRMs) play a central role in guiding inference-time scaling algorithms for large language models (LLMs). However, we observe that even state-of-the-art PRMs can be poorly calibrated and often overestimate success probabilities. To address this, we present a calibration approach, performed via quantile regression, that adjusts PRM outputs to better align with true success probabilities. Leveraging these calibrated success estimates and their associated confidence bounds, w…

Mistral launches its first reasoning models: Magistral Small, on Hugging Face under an Apache 2.0 license, and Magistral Medium, in preview on Mistral's Le Chat (Kyle Wiggers/TechCrunch)
https://techcrunch.com/2025/06/10/mistral-releases-a-pai…

Mistral releases a pair of AI reasoning models | TechCrunch
Like other reasoning models, Magistral works through problems step-by-step for improved consistency and reliability across topics such as math and physics.

Integrating Quantized LLMs into Robotics Systems as Edge AI to Leverage their Natural Language Processing Capabilities
Miguel \'A. Gonz\'alez-Santamarta, Francisco J. Rodr\'iguez-Lera, David Sobr\'in-Hidalgo, \'Angel Manuel Guerrero-Higueras, Vicente Matell\'An-Olivera
https://arxiv.org/abs/2506.09581

Integrating Quantized LLMs into Robotics Systems as Edge AI to Leverage their Natural Language Processing Capabilities
Large Language Models (LLMs) have experienced great advancements in the last year resulting in an increase of these models in several fields to face natural language tasks. The integration of these models in robotics can also help to improve several aspects such as human-robot interaction, navigation, planning and decision-making. Therefore, this paper introduces llama\_ros, a tool designed to integrate quantized Large Language Models (LLMs) into robotic systems using ROS 2. Leveraging llama.cp…