Tootfinder

Interesting and fulsome interview on exactly how NORAD reacted to the plane hijacking in Victoria/Vancouver on Tuesday. They speak to the commander of NORAD, currently a Canadian.
I appreciated the last section most though:
“It's the only bi-national command in the world; it's been a strong bi-national command since 1958, and nothing has changed.
We don't ever talk politics at work. It's not something that we do, nor does it affect what we do.
I would say that we are as tight, and probably tighter than we've ever been. As the world around us gets to be more dangerous, I would say that NORAD is even closer than it's ever been.
But one last thing — we have the watch. That's the slogan here for NORAD.
To give you a great example, all of the assessors, we all live on-base in homes that actually have a safe, we call it the SCIF. It's basically a classified room that has all of our systems. The days that you're on duty, you're either at work or in your house. Because the timelines are so small for answering the phone, you don't walk the dog; you don't do all these other things, and someone covers for you when you're going between work and home.
That's how important this mission is to us down here. It's really important for everybody in Canada to know that at NORAD, we have the watch”
#canpoli #norad #cf18
https://www.cbc.ca/news/canada/british-columbia/us-fighter-jets-bc-alleged-plane-hijacking-1.7588750

How you don't want to spend your Saturday: figuring out how many regressions #LLVM developers managed to sneak in just before the 21.x branching, and then bisecting them.
The answer: 2 serious regressions breaking libclc build and install, 2 test regressions in clang and compiler-rt respectively (the former quickly reverted on main, for the second time, but nobody thought of backporting), and 1 assertion failure in experimental backend.
Now I really hope I'll manage a clean run for 21.1.0-rc1 with the biggest zero-day LLVM patchset in the history of #Gentoo.
LLVM downstream maintenance is a nightmare.

AdaDocVQA: Adaptive Framework for Long Document Visual Question Answering in Low-Resource Settings
Haoxuan Li, Wei Song, Aofan Liu, Peiwu Qin
https://arxiv.org/abs/2508.13606 ht…

AdaDocVQA: Adaptive Framework for Long Document Visual Question Answering in Low-Resource Settings
Document Visual Question Answering (Document VQA) faces significant challenges when processing long documents in low-resource environments due to context limitations and insufficient training data. This paper presents AdaDocVQA, a unified adaptive framework addressing these challenges through three core innovations: a hybrid text retrieval architecture for effective document segmentation, an intelligent data augmentation pipeline that automatically generates high-quality reasoning question-answ…

I scored 20/21 on https://e-mail.wtf and all I got was this lousy text to share on social media.
This is an entertaining quiz. But RFC 5322 is not the right place to look for an answer to the question of what a (syntactically) valid email address is.

Describe Anything Model for Visual Question Answering on Text-rich Images
Yen-Linh Vu, Dinh-Thang Duong, Truong-Binh Duong, Anh-Khoi Nguyen, Thanh-Huy Nguyen, Le Thien Phuc Nguyen, Jianhua Xing, Xingjian Li, Tianyang Wang, Ulas Bagci, Min Xu
https://arxiv.org/abs/2507.12441

Describe Anything Model for Visual Question Answering on Text-rich Images
Recent progress has been made in region-aware vision-language modeling, particularly with the emergence of the Describe Anything Model (DAM). DAM is capable of generating detailed descriptions of any specific image areas or objects without the need for additional localized image-text alignment supervision. We hypothesize that such region-level descriptive capability is beneficial for the task of Visual Question Answering (VQA), especially in challenging scenarios involving images with dense tex…

FRIT: Using Causal Importance to Improve Chain-of-Thought Faithfulness
Anand Swaroop, Akshat Nallani, Saksham Uboweja, Adiliia Uzdenova, Michael Nguyen, Kevin Zhu, Sunishchal Dev, Ashwinee Panda, Vasu Sharma, Maheep Chaudhary
https://arxiv.org/abs/2509.13334

FRIT: Using Causal Importance to Improve Chain-of-Thought Faithfulness
Chain-of-thought (CoT) reasoning has emerged as a powerful tool for improving large language model performance on complex tasks, but recent work shows that reasoning steps often fail to causally influence the final answer, creating brittle and untrustworthy outputs. Prior approaches focus primarily on measuring faithfulness, while methods for systematically improving it remain limited. We introduce Faithful Reasoning via Intervention Training (FRIT), a scalable alignment method that trains mode…

Slim-SC: Thought Pruning for Efficient Scaling with Self-Consistency
Colin Hong, Xu Guo, Anand Chaanan Singh, Esha Choukse, Dmitrii Ustiugov
https://arxiv.org/abs/2509.13990 htt…

Slim-SC: Thought Pruning for Efficient Scaling with Self-Consistency
Recently, Test-Time Scaling (TTS) has gained increasing attention for improving LLM reasoning performance at test time without retraining the model. A notable TTS technique is Self-Consistency (SC), which generates multiple reasoning chains in parallel and selects the final answer via majority voting. While effective, the order-of-magnitude computational overhead limits its broad deployment. Prior attempts to accelerate SC mainly rely on model-based confidence scores or heuristics with limited …

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[3/7]:
- ETVA: Evaluation of Text-to-Video Alignment via Fine-grained Question Generation and Answering
Kaisi Guan, Zhengfeng Lai, Yuchong Sun, Peng Zhang, Wei Liu, Kieran Liu, Meng Cao, Ruihua Song

UnifiedVisual: A Framework for Constructing Unified Vision-Language Datasets
Pengyu Wang, Shaojun Zhou, Chenkun Tan, Xinghao Wang, Wei Huang, Zhen Ye, Zhaowei Li, Botian Jiang, Dong Zhang, Xipeng Qiu
https://arxiv.org/abs/2509.14738

UnifiedVisual: A Framework for Constructing Unified Vision-Language Datasets
Unified vision large language models (VLLMs) have recently achieved impressive advancements in both multimodal understanding and generation, powering applications such as visual question answering and text-guided image synthesis. However, progress in unified VLLMs remains constrained by the lack of datasets that fully exploit the synergistic potential between these two core abilities. Existing datasets typically address understanding and generation in isolation, thereby limiting the performance…

Cin\'{e}aste: A Fine-grained Contextual Movie Question Answering Benchmark
Nisarg A. Shah, Amir Ziai, Chaitanya Ekanadham, Vishal M. Patel
https://arxiv.org/abs/2509.14227 h…

Cinéaste: A Fine-grained Contextual Movie Question Answering Benchmark
While recent advancements in vision-language models have improved video understanding, diagnosing their capacity for deep, narrative comprehension remains a challenge. Existing benchmarks often test short-clip recognition or use template-based questions, leaving a critical gap in evaluating fine-grained reasoning over long-form narrative content. To address these gaps, we introduce $\mathsf{Cin\acute{e}aste}$, a comprehensive benchmark for long-form movie understanding. Our dataset comprises 3,…