Tootfinder

Always fun/challenging to read new AI (pre)papers like this. "Base models know how to reason, thinking models learn when".
#AI #Google #reasoning

VITA-VLA: Efficiently Teaching Vision-Language Models to Act via Action Expert Distillation
Shaoqi Dong, Chaoyou Fu, Haihan Gao, Yi-Fan Zhang, Chi Yan, Chu Wu, Xiaoyu Liu, Yunhang Shen, Jing Huo, Deqiang Jiang, Haoyu Cao, Yang Gao, Xing Sun, Ran He, Caifeng Shan
https://arxiv.org/abs/2510.09607

VITA-VLA: Efficiently Teaching Vision-Language Models to Act via Action Expert Distillation
Vision-Language Action (VLA) models significantly advance robotic manipulation by leveraging the strong perception capabilities of pretrained vision-language models (VLMs). By integrating action modules into these pretrained models, VLA methods exhibit improved generalization. However, training them from scratch is costly. In this work, we propose a simple yet effective distillation-based framework that equips VLMs with action-execution capability by transferring knowledge from pretrained small…

OpenAI says the cyber capabilities of its frontier AI models are accelerating and warns that upcoming models are likely to pose a "high" risk (Ina Fried/Axios)
https://www.axios.com/2025/12/10/openai-new-models-cybersecurity-risks

Exclusive: New OpenAI models likely pose "high" cybersecurity risk, company says
OpenAI says it's stepping up efforts to protect against attacks.

🇺🇦 #NowPlaying on KEXP's #MiddayShow
Midlake:
🎵 The Ghouls
#Midlake
https://midlakeband.bandcamp.com/track/the-ghouls
https://open.spotify.com/track/0a2fNplIiTrysKtAAv9ESf

New OpenAI models likely to pose "high" cybersecurity risk
OpenAI says the cyber capabilities of its frontier AI models are accelerating and warns Wednesday that upcoming models are likely to pose a "high" risk […]
😶‍🌫️ https://www.axios.com/2025/12/10/openai-ne

Exclusive: New OpenAI models likely pose "high" cybersecurity risk, company says
OpenAI says it's stepping up efforts to protect against attacks.

Einige der zuletzt hier besonders häufig geteilten #News:
Instagram-Datenleck: Daten von 6,2 Millionen Konten bei Have-I-Been-Pwned

Design Principles for Sequence Models via Coefficient Dynamics
Jerome Sieber, Antonio Orvieto, Melanie N. Zeilinger, Carmen Amo Alonso
https://arxiv.org/abs/2510.09389 https://

Design Principles for Sequence Models via Coefficient Dynamics
Deep sequence models, ranging from Transformers and State Space Models (SSMs) to more recent approaches such as gated linear RNNs, fundamentally compute outputs as linear combinations of past value vectors. To draw insights and systematically compare such architectures, we develop a unified framework that makes this output operation explicit, by casting the linear combination coefficients as the outputs of autonomous linear dynamical systems driven by impulse inputs. This viewpoint, in spirit s…

Researchers at OpenAI, Anthropic, and others are studying LLMs like living things, not just software, to uncover some of their secrets for the first time (Will Douglas Heaven/MIT Technology Review)
https://www.technologyreview.com/2026/01/1

Meet the new biologists treating LLMs like aliens
By studying large language models as if they were living things instead of computer programs, scientists are discovering some of their secrets for the first time.

Zero-shot image privacy classification with Vision-Language Models
Alina Elena Baia, Alessio Xompero, Andrea Cavallaro
https://arxiv.org/abs/2510.09253 https://

Zero-shot image privacy classification with Vision-Language Models
While specialized learning-based models have historically dominated image privacy prediction, the current literature increasingly favours adopting large Vision-Language Models (VLMs) designed for generic tasks. This trend risks overlooking the performance ceiling set by purpose-built models due to a lack of systematic evaluation. To address this problem, we establish a zero-shot benchmark for image privacy classification, enabling a fair comparison. We evaluate the top-3 open-source VLMs, accor…

🇺🇦 #NowPlaying on KEXP's #Early
Middle Kids:
🎵 Go to Sleep on Me
#MiddleKids
https://middlekids.bandcamp.com/track/go-to-sleep-on-me-triple-j-live-at-the-wireless
https://open.spotify.com/track/3bxWeF2kpCjPmjc1ewoqrC