Tootfinder

Black Forest Labs: Bildbearbeitung über KI-Prompt
Die künstliche Intelligenz "Flux.1 Kontext" vom Freiburger KI-Startup Black Forest Labs analysiert den Bildinhalt, um ihn per Prompteingabe zu bearbeiten.

Pornhub is making bullshit claims regarding the privacy issues of the French gov age verification requirements. There are very real and significant problems with the French gov approach, but Pornhub's approach is significantly worse.
Pornhub wants to put the burden of age verification and enforcement on user devices. They even name the actors that should have to bear that burden: Google, Apple and Microsoft.
First off, this creates an artificial monopoly: three American compa…

Meta SecAlign: A Secure Foundation LLM Against Prompt Injection Attacks
Sizhe Chen, Arman Zharmagambetov, David Wagner, Chuan Guo
https://arxiv.org/abs/2507.02735

Meta SecAlign: A Secure Foundation LLM Against Prompt Injection Attacks
Prompt injection attacks pose a significant security threat to LLM-integrated applications. Model-level defenses have shown strong effectiveness, but are currently deployed into commercial-grade models in a closed-source manner. We believe open-source models are needed by the AI security community, where co-development of attacks and defenses through open research drives scientific progress in mitigation against prompt injection attacks. To this end, we develop Meta SecAlign, the first open-sou…

Interplay of prompt and non-prompt photons in photon-triggered jet observables
Chathuranga Sirimanna (JETSCAPE Collaboration), Yasuki Tachibana (JETSCAPE Collaboration), Abhijit Majumder (JETSCAPE Collaboration), Aaron Angerami (JETSCAPE Collaboration), Ritu Arora (JETSCAPE Collaboration), Steffen Bass (JETSCAPE Collaboration), Yi Chen (JETSCAPE Collaboration), Ritoban Datta (JETSCAPE Collaboration), Lipei Du (JETSCAPE Collaboration), Raymond Ehlers (JETSCAPE Collaboration), Hannah Elf…

Interplay of prompt and non-prompt photons in photon-triggered jet observables
Prompt photons are important yet challenging to observe in relativistic heavy-ion collisions, as they are produced in the early stages and traverse almost the entire QGP medium without interaction. Experimental analyses typically employ isolation cuts, in the hope to identify prompt photons. Most theoretical studies consider only events with actual prompt photons, assuming no contribution from isolated non-prompt photons to reduce computational cost. For the first time, we present a study that …

This https://arxiv.org/abs/2505.18924 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

LLM-Guided Taxonomy and Hierarchical Uncertainty for 3D Point CLoud Active Learning
We present a novel active learning framework for 3D point cloud semantic segmentation that, for the first time, integrates large language models (LLMs) to construct hierarchical label structures and guide uncertainty-based sample selection. Unlike prior methods that treat labels as flat and independent, our approach leverages LLM prompting to automatically generate multi-level semantic taxonomies and introduces a recursive uncertainty projection mechanism that propagates uncertainty across hier…

This https://arxiv.org/abs/2504.00420 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Think Small, Act Big: Primitive Prompt Learning for Lifelong Robot Manipulation
Building a lifelong robot that can effectively leverage prior knowledge for continuous skill acquisition remains significantly challenging. Despite the success of experience replay and parameter-efficient methods in alleviating catastrophic forgetting problem, naively applying these methods causes a failure to leverage the shared primitives between skills. To tackle these issues, we propose Primitive Prompt Learning (PPL), to achieve lifelong robot manipulation via reusable and extensible primi…

Controllable Text-to-Speech Synthesis with Masked-Autoencoded Style-Rich Representation
Yongqi Wang, Chunlei Zhang, Hangting Chen, Zhou Zhao, Dong Yu
https://arxiv.org/abs/2506.02997

Controllable Text-to-Speech Synthesis with Masked-Autoencoded Style-Rich Representation
Controllable TTS models with natural language prompts often lack the ability for fine-grained control and face a scarcity of high-quality data. We propose a two-stage style-controllable TTS system with language models, utilizing a quantized masked-autoencoded style-rich representation as an intermediary. In the first stage, an autoregressive transformer is used for the conditional generation of these style-rich tokens from text and control signals. The second stage generates codec tokens from b…

Catastrophic Forgetting Mitigation via Discrepancy-Weighted Experience Replay
Xinrun Xu, Jianwen Yang, Qiuhong Zhang, Zhanbiao Lian, Zhiming Ding, Shan Jiang
https://arxiv.org/abs/2507.00042

Catastrophic Forgetting Mitigation via Discrepancy-Weighted Experience Replay
Continually adapting edge models in cloud-edge collaborative object detection for traffic monitoring suffers from catastrophic forgetting, where models lose previously learned knowledge when adapting to new data distributions. This is especially problematic in dynamic traffic environments characterised by periodic variations (e.g., day/night, peak hours), where past knowledge remains valuable. Existing approaches like experience replay and visual prompts offer some mitigation, but struggle to e…

Gravitational waves from a dilaton-induced, first-order QCD phase transition
Aleksandr Chatrchyan, M. C. David Marsh, Charalampos Nikolis
https://arxiv.org/abs/2507.01191

Gravitational waves from a dilaton-induced, first-order QCD phase transition
We show that a `QCD dilaton' field, whose vacuum expectation value sets the strong coupling, can render the Quantum Chromodynamic (QCD) confinement transition first-order. The QCD dilaton is cosmologically attracted to a false vacuum at weak coupling in the early universe. Quantum tunnelling towards the true vacuum triggers prompt chiral symmetry breaking and confinement of QCD, leading to detonating bubbles of the hadronic phase. We find that plasma sound waves produced by this dilaton-induced…

SABRE-FL: Selective and Accurate Backdoor Rejection for Federated Prompt Learning
Momin Ahmad Khan, Yasra Chandio, Fatima Muhammad Anwar
https://arxiv.org/abs/2506.22506

SABRE-FL: Selective and Accurate Backdoor Rejection for Federated Prompt Learning
Federated Prompt Learning has emerged as a communication-efficient and privacy-preserving paradigm for adapting large vision-language models like CLIP across decentralized clients. However, the security implications of this setup remain underexplored. In this work, we present the first study of backdoor attacks in Federated Prompt Learning. We show that when malicious clients inject visually imperceptible, learnable noise triggers into input images, the global prompt learner becomes vulnerable …