Tootfinder

https://taz.de/Rechter-Angriff-auf-Jugendhaus/!6126204/
"Das Autonome Jugendhaus in Bargteheide ist am Wochenende erneut verwüstet worden. Unbekannte hinterließen rechtsextreme Symbole und AfD-Schriftzüge. "
"„Sie haben uns noch vor Ort gesagt, dass da…

Test-Time Anchoring for Discrete Diffusion Posterior Sampling
Litu Rout, Andreas Lugmayr, Yasamin Jafarian, Srivatsan Varadharajan, Constantine Caramanis, Sanjay Shakkottai, Ira Kemelmacher-Shlizerman
https://arxiv.org/abs/2510.02291

Test-Time Anchoring for Discrete Diffusion Posterior Sampling
We study the problem of posterior sampling using pretrained discrete diffusion foundation models, aiming to recover images from noisy measurements without retraining task-specific models. While diffusion models have achieved remarkable success in generative modeling, most advances rely on continuous Gaussian diffusion. In contrast, discrete diffusion offers a unified framework for jointly modeling categorical data such as text and images. Beyond unification, discrete diffusion provides faster i…

Detecting (Un)answerability in Large Language Models with Linear Directions
Maor Juliet Lavi, Tova Milo, Mor Geva
https://arxiv.org/abs/2509.22449 https://…

Detecting (Un)answerability in Large Language Models with Linear Directions
Large language models (LLMs) often respond confidently to questions even when they lack the necessary information, leading to hallucinated answers. In this work, we study the problem of (un)answerability detection, focusing on extractive question answering (QA) where the model should determine if a passage contains sufficient information to answer a given question. We propose a simple approach for identifying a direction in the model's activation space that captures unanswerability and uses it …

Using #PHP arrays as pseudo-objects is almost never the right answer. They're less self-documenting, slower, worse on memory, and more bug prone.
https://peakd.com/php/@crell/php-use-a

VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenes
Paul Gavrikov, Wei Lin, M. Jehanzeb Mirza, Soumya Jahagirdar, Muhammad Huzaifa, Sivan Doveh, Serena Yeung-Levy, James Glass, Hilde Kuehne
https://arxiv.org/abs/2509.25339

VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenes
Is basic visual understanding really solved in state-of-the-art VLMs? We present VisualOverload, a slightly different visual question answering (VQA) benchmark comprising 2,720 question-answer pairs, with privately held ground-truth responses. Unlike prior VQA datasets that typically focus on near global image understanding, VisualOverload challenges models to perform simple, knowledge-free vision tasks in densely populated (or, overloaded) scenes. Our dataset consists of high-resolution scans …

Channel 4 reveals that the anchor who narrates and appears throughout a special titled "Will AI Take My Job?" was AI-generated, a first for British television (Ethan Shanfeld/Variety)
https://variety.com/2025/tv/news/ai-news-anchor-channel-4-1236557295/…

AI News Anchor Debuts on Channel 4 in British TV Stunt
An AI-generated news anchor appeared on Britain's Channel 4 in a stunt proving the dangers of artificial intelligence.

On November 5th, Trump will keep trying to blur truth and fiction through his staged shadow hearings.
Our answer will be simple:
Circles of light around our local government buildings.
Testimony shared openly and honestly.
A united message: The people are watching.
Some will stand silently in person.
Some will speak through livestreams and digital testimony.

Together, we will form a national chorus of truth.

Shadow Hearings - The Parallel Government You Weren’t Meant to See
Remember - Remember - the 5th of November

Can LLMs Refuse Questions They Do Not Know? Measuring Knowledge-Aware Refusal in Factual Tasks
Wenbo Pan, Jie Xu, Qiguang Chen, Junhao Dong, Libo Qin, Xinfeng Li, Haining Yu, Xiaohua Jia
https://arxiv.org/abs/2510.01782

Can LLMs Refuse Questions They Do Not Know? Measuring Knowledge-Aware Refusal in Factual Tasks
Large Language Models (LLMs) should refuse to answer questions beyond their knowledge. This capability, which we term knowledge-aware refusal, is crucial for factual reliability. However, existing metrics fail to faithfully measure this ability. On the one hand, simple refusal-based metrics are biased by refusal rates and yield inconsistent scores when models exhibit different refusal tendencies. On the other hand, existing calibration metrics are proxy-based, capturing the performance of auxil…

Anchored Langevin Algorithms
Mert Gurbuzbalaban, Hoang M. Nguyen, Xicheng Zhang, Lingjiong Zhu
https://arxiv.org/abs/2509.19455 https://arxiv.org/pdf/2509.…

Anchored Langevin Algorithms
Standard first-order Langevin algorithms such as the unadjusted Langevin algorithm (ULA) are obtained by discretizing the Langevin diffusion and are widely used for sampling in machine learning because they scale to high dimensions and large datasets. However, they face two key limitations: (i) they require differentiable log-densities, excluding targets with non-differentiable components; and (ii) they generally fail to sample heavy-tailed targets. We propose anchored Langevin dynamics, a unif…

NeuS-QA: Grounding Long-Form Video Understanding in Temporal Logic and Neuro-Symbolic Reasoning
Sahil Shah, S P Sharan, Harsh Goel, Minkyu Choi, Mustafa Munir, Manvik Pasula, Radu Marculescu, Sandeep Chinchali
https://arxiv.org/abs/2509.18041

NeuS-QA: Grounding Long-Form Video Understanding in Temporal Logic and Neuro-Symbolic Reasoning
Long-Form Video Question Answering (LVQA) poses challenges beyond traditional visual question answering (VQA), which is often limited to static images or short video clips. While current vision-language models (VLMs) perform well in those settings, they struggle with complex queries in LVQA over long videos involving multi-step temporal reasoning and causality. Vanilla approaches, which sample frames uniformly and feed them to a VLM with the question, incur significant token overhead, forcing s…