Tootfinder

Opt-in global Mastodon full text search. Join the index!

No exact results. Similar results found.
@heiseonline@social.heise.de
2025-10-24 05:15:16

Noch einige der zuletzt hier besonders häufig geteilten #News:
Richard Stallman: "Chatbots sind Bullshit-Generatoren"

Richard Stallman: "Chatbots sind Bullshit-Generatoren"
Der Gründer der Free Software Foundation macht auf Europatour auch Halt in München. Dort mahnt er zu mehr Einsatz von Open Source – gerade beim Staat.

@fanf@mendeddrum.org
2025-09-24 08:42:03

from my link log —
Improving state machine code generation in the Rust compiler.
trifectatech.org/blog/improvin
saved 2025-09-12

Improving state machine code generation - Trifecta Tech Foundation

@benb@osintua.eu
2025-09-24 13:26:42

'Random phrase generator' — Trump remarks on Ukraine spark backlash in Russia: benborges.xyz/2025/09/24/rando

Tracking information about the Russian War against Ukraine — Support the OSINT Ukraine Archive the 🇷🇺 War against Ukraine 🇺🇦
Tracking information about the Russian War against Ukraine

@arXiv_csCV_bot@mastoxiv.page
2025-09-24 11:14:04

OverLayBench: A Benchmark for Layout-to-Image Generation with Dense Overlaps
Bingnan Li, Chen-Yu Wang, Haiyang Xu, Xiang Zhang, Ethan Armand, Divyansh Srivastava, Xiaojun Shan, Zeyuan Chen, Jianwen Xie, Zhuowen Tu
arxiv.org/abs/2509.19282

OverLayBench: A Benchmark for Layout-to-Image Generation with Dense Overlaps
Despite steady progress in layout-to-image generation, current methods still struggle with layouts containing significant overlap between bounding boxes. We identify two primary challenges: (1) large overlapping regions and (2) overlapping instances with minimal semantic distinction. Through both qualitative examples and quantitative analysis, we demonstrate how these factors degrade generation quality. To systematically assess this issue, we introduce OverLayScore, a novel metric that quantifi…

@arXiv_csCL_bot@mastoxiv.page
2025-09-24 10:42:54

Diversity Boosts AI-Generated Text Detection
Advik Raj Basani, Pin-Yu Chen
arxiv.org/abs/2509.18880 arxiv.org/pdf/2509.18880

Diversity Boosts AI-Generated Text Detection
Detecting AI-generated text is an increasing necessity to combat misuse of LLMs in education, business compliance, journalism, and social media, where synthetic fluency can mask misinformation or deception. While prior detectors often rely on token-level likelihoods or opaque black-box classifiers, these approaches struggle against high-quality generations and offer little interpretability. In this work, we propose DivEye, a novel detection framework that captures how unpredictability fluctuate…

@heiseonline@social.heise.de
2025-10-22 16:45:00

Richard Stallman: "Chatbots sind Bullshit-Generatoren"
Der Gründer der Free Software Foundation macht auf Europatour auch Halt in München. Dort mahnt er zu mehr Einsatz von Open Source – gerade beim Staat.

Richard Stallman: "Chatbots sind Bullshit-Generatoren"
Der Gründer der Free Software Foundation macht auf Europatour auch Halt in München. Dort mahnt er zu mehr Einsatz von Open Source – gerade beim Staat.

@arXiv_csCV_bot@mastoxiv.page
2025-09-24 11:13:44

Moving by Looking: Towards Vision-Driven Avatar Motion Generation
Markos Diomataris, Berat Mert Albaba, Giorgio Becherini, Partha Ghosh, Omid Taheri, Michael J. Black
arxiv.org/abs/2509.19259

Moving by Looking: Towards Vision-Driven Avatar Motion Generation
The way we perceive the world fundamentally shapes how we move, whether it is how we navigate in a room or how we interact with other humans. Current human motion generation methods, neglect this interdependency and use task-specific ``perception'' that differs radically from that of humans. We argue that the generation of human-like avatar behavior requires human-like perception. Consequently, in this work we present CLOPS, the first human avatar that solely uses egocentric vision to perceive …

@heiseonline@social.heise.de
2025-10-23 12:46:00

2,5 Stunden Social Media täglich: Wo wir besonders viel Zeit verbringen
Tiktok schlägt alle anderen Plattformen: Nutzer verbringen alleine dort über anderthalb Stunden täglich. Auch generative KI wird immer häufiger genutzt.

2,5 Stunden Social Media täglich: Wo wir besonders viel Zeit verbringen
Tiktok schlägt alle anderen Plattformen: Nutzer verbringen alleine dort über anderthalb Stunden täglich. Auch generative KI wird immer häufiger genutzt.

@arXiv_csCV_bot@mastoxiv.page
2025-09-24 11:12:04

Lavida-O: Elastic Masked Diffusion Models for Unified Multimodal Understanding and Generation
Shufan Li, Jiuxiang Gu, Kangning Liu, Zhe Lin, Zijun Wei, Aditya Grover, Jason Kuen
arxiv.org/abs/2509.19244

Lavida-O: Elastic Masked Diffusion Models for Unified Multimodal Understanding and Generation
We proposed Lavida-O, a unified multi-modal Masked Diffusion Model (MDM) capable of image understanding and generation tasks. Unlike existing multimodal diffsion language models such as MMaDa and Muddit which only support simple image-level understanding tasks and low-resolution image generation, Lavida-O exhibits many new capabilities such as object grounding, image-editing, and high-resolution (1024px) image synthesis. It is also the first unified MDM that uses its understanding capabilities …