Tootfinder

Selenskyj: Ukraine vereinbart Drohnen-Produktion mit US-Firma
Die Ukraine will nach den Worten von Präsident Wolodymyr Selenskyj in diesem Jahr gemeinsam mit dem US-Unternehmen Swift Beat Hunderttausende Drohnen produzieren. "Abfangdrohnen zur Zerstörung feindlicher Drohnen und Raketen, Quadrocopter zur Aufklärung und Feuerleitung, Langstrecken-Kampfdrohnen - von all dem wird es viel mehr geben", kündigt Selenskyj während ein…
📑

Ukraine-Liveblog: ++ Russland meldet Eroberung in Region Charkiw ++
Im ostukrainischen Gebiet Charkiw hat die russische Armee eigenen Angaben nach den Grenzort Milowe erobert. Die Ukraine meldet acht Tote nach Angriffen in mehreren Regionen.

A Hollywood producer calls a friend, another producer on the phone.
"Hello?" his friend answers.
"Hi!" says the man. "This is Bob, how are you doing?"
"Oh," says the friend, "I'm doing great! I just sold a screenplay
for two hundred thousand dollars. I've started a novel adaptation and the
studio advanced me fifty thousand dollars on it. I also have a television
series coming on next week, and everyone …

Limited edition replica of the computer-access wearable from Death Stranding 2.
https://www.anicorn-watches.com/products/death-stranding-2-x-anicorn-watches-ring-terminal

DEATH STRANDING 2 by KOJIMA PRODUCTIONS x ANICORN - RING TERMINAL

I published my slides from @… on my site, as well as capturing answers to questions from @… and @… and linking to ap…

CMRAG: Co-modality-based document retrieval and visual question answering
Wang Chen, Guanqiang Qi, Weikang Li, Yang Li
https://arxiv.org/abs/2509.02123 https://

CMRAG: Co-modality-based document retrieval and visual question answering
Retrieval-Augmented Generation (RAG) has become a core paradigm in document question answering tasks. However, existing methods have limitations when dealing with multimodal documents: one category of methods relies on layout analysis and text extraction, which can only utilize explicit text information and struggle to capture images or unstructured content; the other category treats document segmentation as visual input and directly passes it to visual language models (VLMs) for processing, ye…

This https://arxiv.org/abs/2505.18492 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

Enumerate-Conjecture-Prove: Formally Solving Answer-Construction Problems in Math Competitions
Mathematical reasoning lies at the heart of artificial intelligence, underpinning applications in education, program verification, and research-level mathematical discovery. Mathematical competitions, in particular, present two challenging problem types: theorem-proving, requiring rigorous proofs of stated conclusions, and answer-construction, involving hypothesizing and formally verifying mathematical objects. Large Language Models (LLMs) effectively generate creative candidate answers but str…

Brandgefahr: Anker ruft mehrere Powerbank-Modelle zurück – auch in Deutschland
Anker ruft mehrere Powerbank-Modelle zurück. Die Produkte werden auch in Deutschland verkauft. 
https://…

iQUEST: An Iterative Question-Guided Framework for Knowledge Base Question Answering
Shuai Wang, Yinan Yu
https://arxiv.org/abs/2506.01784 https://

iQUEST: An Iterative Question-Guided Framework for Knowledge Base Question Answering
While Large Language Models (LLMs) excel at many natural language processing tasks, they often suffer from factual inaccuracies in knowledge-intensive scenarios. Integrating external knowledge resources, particularly knowledge graphs (KGs), provides a transparent and updatable foundation for more reliable reasoning. Knowledge Base Question Answering (KBQA), which queries and reasons over KGs, is central to this effort, especially for complex, multi-hop queries. However, multi-hop reasoning pose…

The Confidence Paradox: Can LLM Know When It's Wrong
Sahil Tripathi, Md Tabrez Nafis, Imran Hussain, Jiechao Gao
https://arxiv.org/abs/2506.23464 https…

The Confidence Paradox: Can LLM Know When It's Wrong
Document Visual Question Answering (DocVQA) systems are increasingly deployed in real world applications, yet they remain ethically opaque-often producing overconfident answers to ambiguous questions or failing to communicate uncertainty in a trustworthy manner. This misalignment between model confidence and actual knowledge poses significant risks, particularly in domains requiring ethical accountability. Existing approaches such as LayoutLMv3, UDOP, and DONUT have advanced SOTA performance by…

Self-ensemble: Mitigating Confidence Distortion for Large Language Models
Zicheng Xu, Guanchu Wang, Guangyao Zheng, Yu-Neng Chuang, Alexander Szalay, Xia Hu, Vladimir Braverman
https://arxiv.org/abs/2506.01951

Self-ensemble: Mitigating Confidence Distortion for Large Language Models
Although Large Language Models (LLMs) perform well in general fields, they exhibit a confidence distortion problem on multi-choice question-answering (MCQA), particularly as the number of answer choices increases. Specifically, on MCQA with many choices, LLMs suffer from under-confidence in correct predictions and over-confidence in incorrect ones, leading to a substantially degraded performance. To solve this problem, we propose Self-ensemble in this work. Our method splits the choices into se…