Tootfinder

new dining table!

Please join me on July 7th for next month's MediaEd Club webinar for the Media Education Lab: "Privacy, Power, and Platforms"
https://mediaeducationlab.com/index.php/events/privacy-power-and-platforms
If you missed today's / this month…

Katzenpärchen in der Nachbarschaft - am nach Farbe schreiendes Fenster 😊 ❤️
#Fensterfreitag
#DietmarSchneider #Fotogalerie

Sources: Meta is prioritizing an ultralight Horizon OS headset with a compute puck, instead of a traditional Quest 4, to ship in 2026 (David Heaney/UploadVR)
https://www.uploadvr.com/meta-prioritizing-puffin-for-2026-pushing-out-quest-4-to-2…

Meta Prioritizing Ultra-Light Headset With Puck Over Traditional Quest 4
Meta is prioritizing shipping an ultralight Horizon OS headset with a tethered compute puck in 2026, and might not ship a new traditional form factor Quest until 2027.

#Ukraine #Budanov

Und heute noch die #Kartenspiel-Version von #Siedler für zwei. Hat auch viel Spaß gemacht. :blobcatjustright: :blobcatcoffee:

This https://arxiv.org/abs/2505.01651 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

Human-AI Governance (HAIG): A Trust-Utility Approach
This paper introduces the HAIG framework for analysing trust dynamics across evolving human-AI relationships. Current categorical frameworks (e.g., "human-in-the-loop" models) inadequately capture how AI systems evolve from tools to partners, particularly as foundation models demonstrate emergent capabilities and multi-agent systems exhibit autonomous goal-setting behaviours. As systems advance, agency redistributes in complex patterns that are better represented as positions along continua rat…

Is Extending Modality The Right Path Towards Omni-Modality?
Tinghui Zhu, Kai Zhang, Muhao Chen, Yu Su
https://arxiv.org/abs/2506.01872 https://

Is Extending Modality The Right Path Towards Omni-Modality?
Omni-modal language models (OLMs) aim to integrate and reason over diverse input modalities--such as text, images, video, and audio--while maintaining strong language capabilities. Despite recent advancements, existing models, especially open-source ones, remain far from true omni-modality, struggling to generalize beyond the specific modality pairs they are trained on or to achieve strong performance when processing multi-modal inputs. We study the effect of extending modality, the dominant te…

RealDrive: Retrieval-Augmented Driving with Diffusion Models
Wenhao Ding, Sushant Veer, Yuxiao Chen, Yulong Cao, Chaowei Xiao, Marco Pavone
https://arxiv.org/abs/2505.24808

RealDrive: Retrieval-Augmented Driving with Diffusion Models
Learning-based planners generate natural human-like driving behaviors by learning to reason about nuanced interactions from data, overcoming the rigid behaviors that arise from rule-based planners. Nonetheless, data-driven approaches often struggle with rare, safety-critical scenarios and offer limited controllability over the generated trajectories. To address these challenges, we propose RealDrive, a Retrieval-Augmented Generation (RAG) framework that initializes a diffusion-based planning po…

This https://arxiv.org/abs/2405.02696 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

DiffuseTrace: A Transparent and Flexible Watermarking Scheme for Latent Diffusion Model
Latent Diffusion Models (LDMs) enable a wide range of applications but raise ethical concerns regarding illegal utilization. Adding watermarks to generative model outputs is a vital technique employed for copyright tracking and mitigating potential risks associated with Artificial Intelligence (AI)-generated contents. However, post-processed watermarking methods are unable to withstand generative watermark attacks and there exists a trade-off between image fidelity and watermark strength. There…