Tootfinder

Kommission fordert 2.500 zusätzliche IKT-Fachkräfte für die EU
EU-Behörden wollen 2.500 zusätzliche Mitarbeiter in IKT-Bereichen. Das zeigt der Etatentwurf der EU-Kommission.
https://www.

FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space
Black Forest Labs, Stephen Batifol, Andreas Blattmann, Frederic Boesel, Saksham Consul, Cyril Diagne, Tim Dockhorn, Jack English, Zion English, Patrick Esser, Sumith Kulal, Kyle Lacey, Yam Levi, Cheng Li, Dominik Lorenz, Jonas M\"uller, Dustin Podell, Robin Rombach, Harry Saini, Axel Sauer, Luke Smith

FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space
We present evaluation results for FLUX.1 Kontext, a generative flow matching model that unifies image generation and editing. The model generates novel output views by incorporating semantic context from text and image inputs. Using a simple sequence concatenation approach, FLUX.1 Kontext handles both local editing and generative in-context tasks within a single unified architecture. Compared to current editing models that exhibit degradation in character consistency and stability across multip…

TalkLess: Blending Extractive and Abstractive Speech Summarization for Editing Speech to Preserve Content and Style
Karim Benharrak, Puyuan Peng, Amy Pavel
https://arxiv.org/abs/2507.15202

TalkLess: Blending Extractive and Abstractive Speech Summarization for Editing Speech to Preserve Content and Style
Millions of people listen to podcasts, audio stories, and lectures, but editing speech remains tedious and time-consuming. Creators remove unnecessary words, cut tangential discussions, and even re-record speech to make recordings concise and engaging. Prior work automatically summarized speech by removing full sentences (extraction), but rigid extraction limits expressivity. AI tools can summarize then re-synthesize speech (abstraction), but abstraction strips the speaker's style. We present T…

Next week is the first edition of the relaunch of Papers Club! Read the following paper in preparation: “Critical Ignoring as a Core Competence for Digital Citizens” by Anastasia Kozyreva, Sam Wineburg, Stephan Lewandowsky, and Ralph Hertwig.
Date: July 28th, 2025
Time: 6:00 PM (discussion will happen about a half an hour later).
Location: Victory Cafe, 440 Bloor St. W., Toronto.
A link to the paper and the PDF can be found at the Luma link. RSVP is not necessary but r…

Snippets in Visual Studio Code
You can easily define your own snippets without any extension.
https://code.visualstudio.com/docs/editing/userdefinedsnippets#_create-your-own-snippets

Das ist meine Hand und dass ich einmal der Editionsgeschichte der sogenannten Deutschen Ideologie so nah komme, hätte ich nie gedacht.
From: @…
https://…

Applying the Chinese Wall Reverse Engineering Technique to Large Language Model Code Editing
Manatsawin Hanmongkolchai
https://arxiv.org/abs/2507.15599 htt…

Applying the Chinese Wall Reverse Engineering Technique to Large Language Model Code Editing
Large language models for code (Code LLM) are increasingly utilized in programming environments. Despite their utility, the training datasets for top LLM remain undisclosed, raising concerns about potential copyright violations. Some models, such as Pleias and Comma put emphasis on data curation and licenses, however, with limited training data these models are not competitive and only serve as proof of concepts. To improve the utility of these models, we propose an application of the "Chinese …

1/ Something a bit unusual and fun: I read a travel book *after* returning from #Italy25. This is a book first written in 1913; I had the 1923 edition. It was tough going to read before I left, because (as the title suggests), it's really a tour guide of a book. #BookReview ↵

Der nunmehr unter dem Dach der Edition Atelier publizierende Marsyas Verlag hat zuletzt Eislers Gespräche mit Bunge - "Fragen Sie mehr über Brecht" - neu aufgelegt, @… weist in der aktuellen Ausgabe darauf hin;

Fragen Sie mehr über Brecht | Edition Atelier

Blended Point Cloud Diffusion for Localized Text-guided Shape Editing
Etai Sella, Noam Atia, Ron Mokady, Hadar Averbuch-Elor
https://arxiv.org/abs/2507.15399

Blended Point Cloud Diffusion for Localized Text-guided Shape Editing
Natural language offers a highly intuitive interface for enabling localized fine-grained edits of 3D shapes. However, prior works face challenges in preserving global coherence while locally modifying the input 3D shape. In this work, we introduce an inpainting-based framework for editing shapes represented as point clouds. Our approach leverages foundation 3D diffusion models for achieving localized shape edits, adding structural guidance in the form of a partial conditional shape, ensuring th…