Tootfinder

Understanding the relationship between Zionism and Fascism – Mondoweiss
https://mondoweiss.net/2025/12/understanding-the-relationship-between-zionism-and-fascism/

Understanding the Link between Animal Cruelty and Family Violence: The Bioecological Systems Model #AnimalRights

Understanding the Link between Animal Cruelty and Family Violence: The Bioecological Systems Model
Violence towards animals and violence towards people are often interconnected problems, and as such, this phenomenon has been termed the Link. Violence towards animals is a strong predictor that the abuser may inflict violence on people. However, it ...

Check out my latest article - "Do YOU have AI anxiety?"
#changemakers

Do You Have AI Anxiety? Understanding Fear, Capitalism, and the Future
AI and climate change trigger similar fears about the future. Learn how to transform anxiety into empowerment by understanding the systems beneath both crises and envisioning the world you want to build.

Seriously, the worst ones are nodejs and rust: they fundamentally break the nodejs dependency model, flattening everything. They've chosen _controlling_ dependencies instead of _annotating_ them for understanding. Metadata about what's in a package and a package-build-time mechanism for substituting things in lockfiles would be far far simpler for forcing security updates than rewriting everything to use system dependencies, and versions that are not reconcilable.
Heck, both npm and cargo have put a lot of effort into repeatability though not actual hermetic builds, so it's very much Good Enough if you're using lock files. The problems are in updating those, not building packages. Mirror the registries if you need to. That's a much more tractable problem than _rewriting parts of everything you package_ or _eagerly packaging every dependency as a separate [human] task_

US voters linking climate crisis to rising bills despite #Trump’s ‘green scam’ claims:
“It’s a fundamental error to treat these issues as mutually exclusive – climate solutions are also cost-of-living solutions. Most of the elite discourse is very bad at estimating or understanding levels of public concern, and this is a good example of this.”
#ClimateChange
https://www.theguardian.com/us-news/2025/dec/26/us-voters-link-climate-crisis-affordability?CMP=Share_AndroidApp_Other

Today's alarm in the Radisson Blu Hotel will just be a DRILL!
Der heutige Alarm im Radisson Blu Hotel ist nur eine ÜBUNG!
#radissonbluhotel #39c3

Which NFL players are the best (and worst) locker-room DJs? What music do they play? https://www.espn.com/nfl/story/_/id/47097079/team-djs-nba-youngboy-lions-jets-breece-hall-49ers-jets-bills-josh-allen

Guilbeault quits Carney’s cabinet over energy deal with Alberta | CBC News
https://www.cbc.ca/news/politics/guilbeault-quitting-cabinet-9.6995299

Guilbeault quits Carney’s cabinet over energy deal with Alberta | CBC News
Liberal MP Steven Guilbeault has quit cabinet over the federal government signing Thursday’s memorandum of understanding with Alberta.

It seems that both AI and climate anxiety share a common root: the current structure of capitalism.
Our system, which demands constant, unrestricted growth, shapes everything from our economy to our psychology.
In the climate crisis, it manifests as overproduction and overconsumption, while in AI, it drives the replacement of human labor with cheaper machine labor and the optimization of attention economies.

Do You Have AI Anxiety? Understanding Fear, Capitalism, and the Future
AI and climate change trigger similar fears about the future. Learn how to transform anxiety into empowerment by understanding the systems beneath both crises and envisioning the world you want to build.

pet peeve: "good intentions".
if the intentions consistently cause bad things, then they just aren't very good. yeah, it's based on bad reasoning/understanding. it always is, that's how evil happens.
how else are these intentions supposed to be "good"? by making people feel good about themselves?
even people who think they "do evil on purpose" are just semantically confused. they still act according to their own values. though their…

"Scientists detect new climate pattern in the tropics"
#Climate #ClimateChange
https://ph…

Scientists detect new climate pattern in the tropics
Tropical cyclones can unleash extensive devastation, as recent storms that swept over Jamaica and the Philippines made unmistakably clear. Accurate weather forecasts that buy more time to prepare are crucial for saving lives and are rooted in a deeper understanding of climate systems.

I was just thinking about how the fact that #Musk named his AI "Grok" is evidence that he "reads sci-fi" in the same way he "plays video games." Like, he claims to do it but when it comes time to show the evidence it's clear he does not actually "grok" it.
Like... To grok something is to have a layer deeper than simply knowledge, but mathematically encoding statistical relationships between words is pretty obviously not even understanding much less qualifying as "groking" it. In the book, the ability to grok something is also the ability to annihilate that thing with a thought. Just pretending that an LLM actually *was* something that could become AGI (which it's not), this name would imply the AI would have the power to annihilate reality. That's bad. That's a bad name for an AI.
And why would a greedy fascist name something of his after something an anarchist communist space Jesus taught to the hippie cult he started? There are so many layers of facepalm to this. It's some kind of php-esque fractal of incompetence.
Like, there's no reason to talk about this but my brain does this to me sometimes and now it's your problem.

Crosslisted article(s) found for physics.atom-ph. https://arxiv.org/list/physics.atom-ph/new
[1/1]:
- Towards an understanding of dipole-dipole interactions in nonlocal media
L. In\'acio, A. Kurumbail, S. K. Panja, I. Brevik, M. Bostr\"om

Is Raiders QB Geno Smith worth a late-round pick? https://raiderramble.com/2025/12/27/is-raiders-qb-geno-smith-worth-a-late-round-pick/

Comparison Traits - Understanding Equality and Ordering
#Rust

My colleague Lea Poropat is talking about how we integrate this data into the Danish climate atlas...
How do we get to #ClimateServices in the atlas, from IPCC CMIP6 via, local observations and process understanding and with a current focus on storm surges.. #NCKF25

Understanding How Cowboys Matchups Influence Betting Trends https://insidethestar.com/understanding-how-cowboys-matchups-influence-betting-trends

# Get Off My Lawn Manifesto
## For Technologists Who Still Care
We remember when computers were tools, not subscription funnels.
When “open” meant source code, not APIs with rate limits.
When you could fix things yourself, not just blindly hope that a reboot of the service in the cloud would magically solve the issue.
We still believe in:
* Understanding over abstraction.
* Control over convenience.
* Craftsmanship over compliance.
* Text…

All we're asking is for y'all to catch up on some history so you understand what you're coming into. Even #NoKings grew from #50501Movement, which started as a decentralized protest before being taken over by the nonprofit industrial complex. Antifa networks were doxxing fash hard through the first Trump admin, but those networks go all the way back to the 80's... And they inherited an even older tradition. If you really want to get down to it, the whole "no kings" thing in Europe was at the very least heavily influenced by indigenous folks in the so-called Americas. There's a lot of history that's lead to this moment, and it's kind of all relevant to understanding how we got here and how we actually get out.

Spectral peak picking improves tactile speech perception https://www.nature.com/articles/s41598-025-28930-6 "The algorithm is suitable for real-time use in wearable sensory substitution devices and could aid the development of effective haptic hearing aids."

SPORTS: Simultaneous Panoptic Odometry, Rendering, Tracking and Segmentation for Urban Scenes Understanding
Zhiliu Yang, Jinyu Dai, Jianyuan Zhang, Zhu Yang
https://arxiv.org/abs/2510.12749

SPORTS: Simultaneous Panoptic Odometry, Rendering, Tracking and Segmentation for Urban Scenes Understanding
The scene perception, understanding, and simulation are fundamental techniques for embodied-AI agents, while existing solutions are still prone to segmentation deficiency, dynamic objects' interference, sensor data sparsity, and view-limitation problems. This paper proposes a novel framework, named SPORTS, for holistic scene understanding via tightly integrating Video Panoptic Segmentation (VPS), Visual Odometry (VO), and Scene Rendering (SR) tasks into an iterative and unified perspective. Fir…

I keep saying that understanding an individual’s relationship with abuse and abusers is the key to understanding their relationship with Trump.
Add this from @… to the file of evidence for that claim: https://mastodon.social/@IveyJanette/115730378983568715

RE: https://graphics.social/@metin/115609395003766024
The claim "Evidence suggests early developing human brains are preconfigured with instructions for understanding the world" is not substantiated and impossible to base on experiments with brain …

Was in Japan übrigens so nebenbei zum Thema gemacht wird:
https://www.instagram.com/p/DSqy86IAJPZ/?utm_source=ig_web_copy_link&igsh=NTc4MTIwNjQ2YQ==

Japan Daily on Instagram: "For the first time in Japan, foreign nationals have begun driving local bus routes under the Specified Skilled Worker program to address severe labor shortages. Tokyo Bus launched the initiative on December 23 in Tokyo and Okinawa, hiring five drivers from the Philippines after long-term training. The company says even higher wages have not attracted enough domestic drivers, making outside talent necessary. New drivers initially operate with support from Japanese staff and are expected to work independently after several months. Industry leaders hope the move will stabilize bus services and ensure passenger safety. Public understanding and continued training will be important as Japan adapts to workforce shortages in essential public services. @YAHOO"
85 likes, 11 comments - japandaily_jp on December 24, 2025: "For the first time in Japan, foreign nationals have begun driving local bus routes under the Specified Skilled Worker program to address severe labor shortages. Tokyo Bus launched the initiative on December 23 in Tokyo and Okinawa, hiring five drivers from the Philippines after long-term training. The company says even higher wages have not attracted enough domestic drivers, making outside talent necessary. New drivers initially ope…

Understanding the New Wave of Chatbot Legislation: California SB 243 and Beyond
https://fpf.org/blog/understanding-the-new-wave-of-chatbot-legislation-california-sb-243-and-beyond/
@…

AgriDetective
I'm an Australian mixed farmer, a communications consultant, former journalist and someone who really wants to build the understanding of the Australian ag industry...
Great Australian Pods Podcast Directory: https://www.greataustralianpods.com/agridetective/

Donald Trump deeply misjudged his response to the deaths of Rob and Michele Reiner,
and he's incapable of understanding why.
https://bsky.app/profile/mirror.co.uk/post/3ma4h4dojyc26

The Mirror (@mirror.co.uk)
Donald Trump deeply misjudged his response to the deaths of Rob and Michele Reiner, and he's incapable of understanding why. https://www.mirror.co.uk/news/politics/9-unhinged-donald-trump-moments-36410478?utm_term=Autofeed&utm_medium=Social&utm_source=Bluesky#Echobox=1765898033

👨🏿‍🌾 Traces of old farm chemicals contaminate water across the US
#chemicals

Traces of old farm chemicals contaminate water across the US
Even though it delivers airtight data and analysis essential for understanding and managing the risks industrial societies pose to water, land, and health, the US Geological Survey is a federal science agency that rarely attracts public notice.

Railway is technically a PaaS (like Heroku). “serverless” because you don’t have to maintain the operating system. They have evolved buildpacks to Railpacks which will create containers on the fly.
OR you can use it as a Docker host
They are hosting their own bare metal servers. Recommended!
https://…

dan (@danabra.mov)
i'm highly enjoying using railway.app i think instead of starting with serverless, it would be good for many developers to start with Railway and then try serverless. i feel a lot more comfortable understanding the tradeoffs now https://railway.app

Understanding the Modality Gap: An Empirical Study on the Speech-Text Alignment Mechanism of Large Speech Language Models
Bajian Xiang, Shuaijiang Zhao, Tingwei Guo, Wei Zou
https://arxiv.org/abs/2510.12116

Understanding the Modality Gap: An Empirical Study on the Speech-Text Alignment Mechanism of Large Speech Language Models
End-to-end Large Speech Language Models (LSLMs) have demonstrated impressive conversational generation abilities, yet consistently fall short of traditional pipeline systems on semantic understanding benchmarks. In this work, we reveal through systematic experimentation that although LSLMs lose some text input performance after speech-text alignment training, the performance gap between speech and text inputs is more pronounced, which we refer to as the modality gap. To understand this gap, we …

Understanding Medieval Race-Making https://call-for-papers.sas.upenn.edu/cfp/2025/11/13/understanding-medieval-race-making

Details of the MOU as reported by CBC. Hot Take:
It's a sh_t show of oil soaked hopeium and climate defeatism.
- Shovels in Ground by 2029 *(may this be forever extended)
- Tanker Ban will be lifted if the project is approved by MPO *(Coastal First Nations setting rhetorical fire to MPO in 3-2-1)
- July 1, 2026 deadline for submission to MPO *(OIL CANADA DAY)
- 75% methane emissions cut on 2014 levels from methane by 2035 *(*shaking head* We are VERY GOOD at hitting 10 year targets *shaking head*)
- "both sides commited to net-zero by 2050” (implied via CCS) *(carbon capture and storage? should be Carney Can't Stop -- Emissions)
- industrial carbon price of $130 -- down from $170
*(Oil Industry - Very Poor)
- Alberta exempt from fed O&G emissions cap and clean electricity regulation *(Woop Coal! Let's Mine the Rockies!)
- No private proponents have been announced. *(Hear No Evil)
- No pipeline path/route has been announced. *(See No Evil)
#TMX #EndFossilFuels #ClimateSellout #ClimateEmergency #CdnPoli #CanPoli #BCPoli #ABPoli
Since multiple Ottawa CBC reporters seem utterly incapable of understanding what First Nations groups are what in BC here are some facts about the Coastal First Nations. It has existed since 2003.
https://coastalfirstnations.ca/about/
"The Great Bear Initiative Society (a non-profit society under the BC Societies Act), also known as Coastal First Nations-Great Bear Initiative (CFN), is an alliance of First Nations on the North Pacific Coast that includes the Gitga’at, Gitxaała, Haida, Heiltsuk, Kitasoo Xai’xais, Metlakatla, Nuxalk and Wuikinuxv First Nations. " Their territories span on the mainland coast of BC from the top of Vancouver Island to the Alaska Border including Haida Gwaii.

STaR-Attack: A Spatio-Temporal and Narrative Reasoning Attack Framework for Unified Multimodal Understanding and Generation Models
Shaoxiong Guo, Tianyi Du, Lijun Li, Yuyao Wu, Jie Li, Jing Shao
https://arxiv.org/abs/2509.26473

STaR-Attack: A Spatio-Temporal and Narrative Reasoning Attack Framework for Unified Multimodal Understanding and Generation Models
Unified Multimodal understanding and generation Models (UMMs) have demonstrated remarkable capabilities in both understanding and generation tasks. However, we identify a vulnerability arising from the generation-understanding coupling in UMMs. The attackers can use the generative function to craft an information-rich adversarial image and then leverage the understanding function to absorb it in a single pass, which we call Cross-Modal Generative Injection (CMGI). Current attack methods on mali…

UALM: Unified Audio Language Model for Understanding, Generation and Reasoning
Jinchuan Tian, Sang-gil Lee, Zhifeng Kong, Sreyan Ghosh, Arushi Goel, Chao-Han Huck Yang, Wenliang Dai, Zihan Liu, Hanrong Ye, Shinji Watanabe, Mohammad Shoeybi, Bryan Catanzaro, Rafael Valle, Wei Ping
https://arxiv.org/abs/2510.12000

UALM: Unified Audio Language Model for Understanding, Generation and Reasoning
Recent advances in the audio language modeling (ALM) domain tackle audio understanding and text-to-audio generation as separate tasks. Very few studies attempt to unify these tasks -- an essential step toward advanced multimodal reasoning. This paper introduces U}nified Audio Language Model (UALM), which aims to unify audio understanding, text-to-audio generation, and multimodal reasoning in a single model. To achieve this goal, we first present UALM-Gen, a text-to-audio language model that dir…

So am I understanding this correctly that the upcoming NPM authentication and token changes mean our only publishing workflow options henceforth are either switching to OICD Trusted Publishing[1] via GitHub Actions or using granular access tokens. The problem with the former is that I wanted to migrate my projects to Codeberg soon (which isn't supported). The problem with the latter is that granular tokens are unsuitable for publishing packages from a large monorepo, since these tokens a…

thi.ng/umbrella

Diff-XYZ: A Benchmark for Evaluating Diff Understanding
Evgeniy Glukhov, Michele Conti, Egor Bogomolov, Yaroslav Golubev, Alexander Bezzubov
https://arxiv.org/abs/2510.12487 htt…

Diff-XYZ: A Benchmark for Evaluating Diff Understanding
Reliable handling of code diffs is central to agents that edit and refactor repositories at scale. We introduce Diff-XYZ, a compact benchmark for code-diff understanding with three supervised tasks: apply (old code $+$ diff $\rightarrow$ new code), anti-apply (new code $-$ diff $\rightarrow$ old code), and diff generation (new code $-$ old code $\rightarrow$ diff). Instances in the benchmark are triples $\langle \textit{old code}, \textit{new code}, \textit{diff} \rangle$ drawn from real commit…

Deutsche Talkshows
From: @…
https://spore.social/@RosethornRanger/115381838929942289

RosethornRanger (it/its) (TTV) (@RosethornRanger@spore.social)
Attached: 1 image stoneToss is a nazi, and trans people don't need cis peoples permission or understanding <3 #meme #anarchism #anarchyMeme

Network Traffic as a Scalable Ethnographic Lens for Understanding University Students' AI Tool Practices
Donghan Hu, Rameen Mahmood, Annabelle David, Danny Yuxing Huang
https://arxiv.org/abs/2510.09763

Network Traffic as a Scalable Ethnographic Lens for Understanding University Students' AI Tool Practices
AI-driven applications have become woven into students' academic and creative workflows, influencing how they learn, write, and produce ideas. Gaining a nuanced understanding of these usage patterns is essential, yet conventional survey and interview methods remain limited by recall bias, self-presentation effects, and the underreporting of habitual behaviors. While ethnographic methods offer richer contextual insights, they often face challenges of scale and reproducibility. To bridge this gap…

I like to play around as an anonymous commenter in online newspaper columns. If you point out the biases of #AI systems, the comment gets deleted because it is considered too polemical.
The comment was addressing an article about AI in public service and the use in refugee applications 🫣

Made another tool. Link Check will resolve any shortlink, including ones from LinkedIn.

This lets you see where a link leads you without clicking it, and helps you bypass any tracking that the shortlink engages in.

Since many QR codes make use of shortlinks, this is a good companion for understanding where QR codes take you.

https://toolbox.axbom.com/linkcheck/

19:10 fixed a spelling mistake

# Get Off My Lawn Manifesto
## For Technologists Who Still Care
We remember when computers were tools, not subscription funnels.
When “open” meant source code, not APIs with rate limits.
When you could fix things yourself, not just blindly hope that a reboot of the service in the cloud would magically solve the issue.
We still believe in:
* Understanding over abstraction.
* Control over convenience.
* Craftsmanship over compliance.
* Text…

All political violence is bad; violence is never a good answer.
From report AG and potus want to hide: "…the number of far-right attacks continues to outpace all other types of terrorism and domestic violent extremism."
https://www.scribd.com/document/9186184…

What NIJ Research Tells Us About Domestic Terrorism | PDF | Extremism | Crimes
NIJ-funded research has enhanced understanding of domestic terrorism, particularly the rise of far-right extremist violence in the U.S., which has outpaced other forms of terrorism. The studies reveal that radicalization processes vary by group and crime type, and highlight the importance of community-based prevention strategies. Key findings include the diversity of extremist beliefs and behaviors, the role of military experience in radicalization, and the need for targeted interventions to pr…

Understanding risk should be a required subject in school.

We bought into the "post scarcity" narrative because digital tech feels so magic and ethereal but we need to get back to an understanding of the material costs and effects of those systems. They are not very post-scarce in reality.

The Colorful Cultures of Pre-Colonial Mindanao
Bridging the gap between what seems like ‘exotic’ Mindanao starts with understanding the culture of its people
https://www.esquiremag.ph/long-reads/features/mindano-culture-a2212-20200313-lfrm

#Twitter #elonmusk

Why your boss isn't worried about AI
When it comes to understanding the dangers of AI systems, the general public has the worst kind of knowledge: that what you know for sure that just ain’t so. […]
😒 https://boydkane.com/essays/boss

Why your boss isn't worried about AI
...

reposting this because it’s important to understanding why I am the way that I am #discord #youtube

Scattering in Time-Varying Drude-Lorentz Models
Bryce Dixon, Calvin M. Hooper, Ian R. Hooper, Simon A. R. Horsley
https://arxiv.org/abs/2511.19322 https://arxiv.org/pdf/2511.19322 https://arxiv.org/html/2511.19322
arXiv:2511.19322v1 Announce Type: new
Abstract: Motivated by recent experiments, the theoretical study of wave propagation in time varying materials is of current interest. Although significant in nearly all such experiments, material dispersion is commonly neglected in theoretical studies. Yet, as we show here, understanding the precise microscopic model for the material dispersion is crucial for predicting experimental outcomes. Here we study the temporal scattering coefficients of four different time-varying Drude-Lorentz models, exploring how an incident continuous wave splits into forward and backward waves due to an abrupt change in plasma frequency. The differences in the predicted scattering are unique to time-varying media, and arise from the exact way in which the time variation appears in the various model parameters. We verify our results using a custom finite difference time domain algorithm, concluding with a discussion of the limitations that arise from using these models with an abrupt change in plasma frequency.
toXiv_bot_toot

What If : Understanding Motion Through Sparse Interactions
Stefan Andreas Baumann, Nick Stracke, Timy Phan, Bj\"orn Ommer
https://arxiv.org/abs/2510.12777 https://

What If : Understanding Motion Through Sparse Interactions
Understanding the dynamics of a physical scene involves reasoning about the diverse ways it can potentially change, especially as a result of local interactions. We present the Flow Poke Transformer (FPT), a novel framework for directly predicting the distribution of local motion, conditioned on sparse interactions termed "pokes". Unlike traditional methods that typically only enable dense sampling of a single realization of scene dynamics, FPT provides an interpretable directly accessible repr…

I have a serious question about deadnaming of trans people. Please answer kindly, I'm seeking understanding. Do trans people refer to their deadname as a previous life of themselves? An old mask of a time that they were not feeling themselves? Or deadnaming is just something that trans people want to completely forget as it was always wrong?
I'm expecting two types of answer here:
1. It really depends on the person, some trans have different relationships than others with …

I received a bug report about picolibc's iconv implementation. So I added a test case. Which pushed the CI runtime up over *six hours* at which point github gave up and killed it.
I spent a bit of time yesterday and today re-implementing the JIS to Unicode conversion function to make it faster. Lines changed: 5125 additions & 7495 deletions. Runtime is back to normal now. And I have a deeper understanding of these encodings.

Iconv fixes by keith-packard · Pull Request #1141 · picolibc/picolibc
PR #1139 fixes one issue in iconv, but when I implemented an exhaustive test case, I found a bunch more.

Making Power Explicable in AI: Analyzing, Understanding, and Redirecting Power to Operationalize Ethics in AI Technical Practice
Weina Jin, Elise Li Zheng, Ghassan Hamarneh
https://arxiv.org/abs/2510.10588

Making Power Explicable in AI: Analyzing, Understanding, and Redirecting Power to Operationalize Ethics in AI Technical Practice
The operationalization of ethics in the technical practices of artificial intelligence (AI) is facing significant challenges. To address the problem of ineffective implementation of AI ethics, we present our diagnosis, analysis, and interventional recommendations from a unique perspective of the real-world implementation of AI ethics through explainable AI (XAI) techniques. We first describe the phenomenon (i.e., the "symptoms") of ineffective implementation of AI ethics in explainable AI using…

AccidentBench: Benchmarking Multimodal Understanding and Reasoning in Vehicle Accidents and Beyond
Shangding Gu, Xiaohan Wang, Donghao Ying, Haoyu Zhao, Runing Yang, Ming Jin, Boyi Li, Marco Pavone, Serena Yeung-Levy, Jun Wang, Dawn Song, Costas Spanos
https://arxiv.org/abs/2509.26636

AccidentBench: Benchmarking Multimodal Understanding and Reasoning in Vehicle Accidents and Beyond
Rapid advances in multimodal models demand benchmarks that rigorously evaluate understanding and reasoning in safety-critical, dynamic real-world settings. We present AccidentBench, a large-scale benchmark that combines vehicle accident scenarios with Beyond domains, safety-critical settings in air and water that emphasize spatial and temporal reasoning (e.g., navigation, orientation, multi-vehicle motion). The benchmark contains approximately 2000 videos and over 19000 human-annotated question…

Neuron-Level Analysis of Cultural Understanding in Large Language Models
Taisei Yamamoto, Ryoma Kumon, Danushka Bollegala, Hitomi Yanaka
https://arxiv.org/abs/2510.08284 https:/…

Neuron-Level Analysis of Cultural Understanding in Large Language Models
As large language models (LLMs) are increasingly deployed worldwide, ensuring their fair and comprehensive cultural understanding is important. However, LLMs exhibit cultural bias and limited awareness of underrepresented cultures, while the mechanisms underlying their cultural understanding remain underexplored. To fill this gap, we conduct a neuron-level analysis to identify neurons that drive cultural behavior, introducing a gradient-based scoring method with additional filtering for precise…

Frontiers call for papers: Innovative electrode and bioelectronic technologies for neural recording and stimulation https://www.frontiersin.org/research-topics/75514/innovative-electrode-and-bioelec…

“How do we move forward in a way that everybody feels like they’re being engaged, they’re being heard and they’re understanding that elections have consequences?” she asks rhetorically.
“You have to come out and vote. You lose your voice if you don’t come out to vote.
One of the problems that’s happening right now is people are fearful and that’s how dictatorship begins. That’s how authoritarian regimes start.
They create this chaos and then this fear and we cannot be fe…

Israel calls us “human animals,” never understanding that our bond with animals is the deepest proof of our humanity
https://prismreports.org/2025/10/08/israel-calls-us-human-animals-never-understanding-that-our-bond-with-animals-is-the-deepest-proof-of-our-humanity/

You Are On Native Land: Understanding Medieval Studies in Turtle Island https://call-for-papers.sas.upenn.edu/cfp/2025/11/13/you-are-on-native-land-understanding-medieval-studies-in-turtle-island

Nearly 47 million Americans live near hidden fossil fuel sites #America

Nearly 47 million Americans live near hidden fossil fuel sites
A nationwide analysis has uncovered how sprawling fossil fuel infrastructure sits surprisingly close to millions of American homes. The research shows that 46.6 million people live within about a mile of wells, refineries, pipelines, storage sites, or transport facilities. Many of these locations release pollutants that may affect nearby communities, yet mid-supply-chain sites have rarely been studied. The findings reveal major gaps in understanding how this hidden network affects health.

CodeWatcher: IDE Telemetry Data Extraction Tool for Understanding Coding Interactions with LLMs
Manaal Basha, Aime\^e M. Ribeiro, Jeena Javahar, Cleidson R. B. de Souza, Gema Rodr\'iguez-P\'erez
https://arxiv.org/abs/2510.11536

CodeWatcher: IDE Telemetry Data Extraction Tool for Understanding Coding Interactions with LLMs
Understanding how developers interact with code generation tools (CGTs) requires detailed, real-time data on programming behavior which is often difficult to collect without disrupting workflow. We present \textit{CodeWatcher}, a lightweight, unobtrusive client-server system designed to capture fine-grained interaction events from within the Visual Studio Code (VS Code) editor. \textit{CodeWatcher} logs semantically meaningful events such as insertions made by CGTs, deletions, copy-paste action…

This is so damning. The top of the CBC story (JP Tasker reporting)
“Smith said she got Carney to back down on most of the Trudeau-era "nine bad laws," as she calls them, that restricted oil and gas development in Alberta.
Carney, meanwhile, says he got Alberta to buy into the Pathways carbon capture project to try and decarbonize the oil pumped out of the province.”
It would be like Putin saying he got Zelenskyy to back down on Donbas and Crimea, but Zelenskyy says Putin agreed to security guarantees from Russia and the USA.
Carney = Capitulator
Also... YOU CAN'T DECARBONIZE OIL.
ffs. what a stupid statement.
Maybe Putin will De-TNT his Ballistic Missiles.
#baitandswitch #climateEmergency #ABPoli #CanPoli #CdnPoli #RussiaUkraineWar
https://www.cbc.ca/news/politics/livestory/alberta-ottawa-memorandum-of-understanding-energy-deal-pipeline-bc-9.6993431

RefineShot: Rethinking Cinematography Understanding with Foundational Skill Evaluation
Hang Wu, Yujun Cai, Haonan Ge, Hongkai Chen, Ming-Hsuan Yang, Yiwei Wang
https://arxiv.org/abs/2510.02423

RefineShot: Rethinking Cinematography Understanding with Foundational Skill Evaluation
Cinematography understanding refers to the ability to recognize not only the visual content of a scene but also the cinematic techniques that shape narrative meaning. This capability is attracting increasing attention, as it enhances multimodal understanding in real-world applications and underpins coherent content creation in film and media. As the most comprehensive benchmark for this task, ShotBench spans a wide range of cinematic concepts and VQA-style evaluations, with ShotVL achieving sta…

Prompt-Guided Spatial Understanding with RGB-D Transformers for Fine-Grained Object Relation Reasoning
Tanner Muturi, Blessing Agyei Kyem, Joshua Kofi Asamoah, Neema Jakisa Owor, Richard Dyzinela, Andrews Danyo, Yaw Adu-Gyamfi, Armstrong Aboah
https://arxiv.org/abs/2510.11996

Prompt-Guided Spatial Understanding with RGB-D Transformers for Fine-Grained Object Relation Reasoning
Spatial reasoning in large-scale 3D environments such as warehouses remains a significant challenge for vision-language systems due to scene clutter, occlusions, and the need for precise spatial understanding. Existing models often struggle with generalization in such settings, as they rely heavily on local appearance and lack explicit spatial grounding. In this work, we introduce a dedicated spatial reasoning framework for the Physical AI Spatial Intelligence Warehouse dataset introduced in th…

Understanding #Docker Internals: Building a Container Runtime in Python
https://muhammadraza.me/2024/building-container-runtime-python/

Gauging the Competition: Understanding Social Comparison and Anxiety through Eye-tracking in Virtual Reality Group Interview
Shi-Ting Ni, Kairong Fang, Yuyang Wang, Pan Hui
https://arxiv.org/abs/2510.12590

Gauging the Competition: Understanding Social Comparison and Anxiety through Eye-tracking in Virtual Reality Group Interview
Virtual Reality (VR) is a promising tool for interview training, yet the psychological dynamics of group interviews, such as social comparison, remain underexplored. We investigate this phenomenon by developing an immersive VR group interview system and conducting an eye-tracking study with 73 participants. We manipulated peer performance using ambiguous behavioral cues (e.g., hand-raising) and objective information (public test scores) to measure their effect on participants' attention and sel…

Of course we humans have never had a single “shared reality,” and we never will. But there are times places when we’ve had more robust ongoing sharing and boundary-crossing and comfort with the limits of our own understanding — “shared reality” not as a fact, but as a direction.
These thoughts are still forming, and I think that’s where my thread ends for today: no answers, but yet another plea for systems thinking.
6/

💫 Scientists discover how nanoplastics disrupt brain energy metabolism
#brain

Scientists discover how nanoplastics disrupt brain energy metabolism
Scientists from the Trinity Biomedical Sciences Institute (TBSI) have discovered how nanoplastics—even smaller than microplastics—disrupt energy metabolism in brain cells. Their findings may have implications for better understanding neurodegenerative diseases characterized by declining neurological or brain function, and even shed new light on issues with learning and memory.

Fossil-fuel propaganda is stalling climate action; here's what we can do about it #fossilfuel

Fossil-fuel propaganda is stalling climate action; here's what we can do about it
2025 has been a year of setbacks for Canada's climate policy. In November, the federal and Alberta governments signed a memorandum of understanding to remove strict climate policies in the province and to support the construction of a new pipeline from Alberta to northern British Columbia.

Roadmap: Emerging Platforms and Applications of Optical Frequency Combs and Dissipative Solitons
Dmitry Skryabin, Arne Kordts, Richard Zeltner, Ronald Holzwarth, Victor Torres-Company, Tobias Herr, Fuchuan Lei, Qi-Fan Yang, Camille-Sophie Br\`es, John F. Donegan, Hai-Zhong Weng, Delphine Marris-Morini, Adel Bousseksou, Markku Vainio, Thomas Bunel, Matteo Conforti, Arnaud Mussot, Erwan Lucas, Julien Fatome, Yuk Shan Cheng, Derryck T. Reid, Alessia Pasquazi, Marco Peccianti, M. Giudici, M. Marconi, A. Bartolo, N. Vigne, B. Chomet, A. Garnache, G. Beaudoin, I. Sagnes, Richard Burguete, Sarah Hammer, Jonathan Silver
https://arxiv.org/abs/2511.18231 https://arxiv.org/pdf/2511.18231 https://arxiv.org/html/2511.18231
arXiv:2511.18231v1 Announce Type: new
Abstract: The discovery of optical frequency combs (OFCs) has revolutionised science and technology by bridging electronics and photonics, driving major advances in precision measurements, atomic clocks, spectroscopy, telecommunications, and astronomy. However, current OFC systems still require further development to enable broader adoption in fields such as communication, aerospace, defence, and healthcare. There is a growing need for compact, portable OFCs that deliver high output power, robust self-referencing, and application-specific spectral coverage. On the conceptual side, progress toward such systems is hindered by an incomplete understanding of the fundamental principles governing OFC generation in emerging devices and materials, as well as evolving insights into the interplay between soliton and mode-locking effects. This roadmap presents the vision of a diverse group of academic and industry researchers and educators from Europe, along with their collaborators, on the current status and future directions of OFC science. It highlights a multidisciplinary approach that integrates novel physics, engineering innovation, and advanced researcher training. Topics include advances in soliton science as it relates to OFCs, the extension of OFC spectra into the visible and mid-infrared ranges, metrology applications and noise performance of integrated OFC sources, new fibre-based OFC modules, OFC lasers and OFC applications in astronomy.
toXiv_bot_toot

PHORECAST: Enabling AI Understanding of Public Health Outreach Across Populations
Rifaa Qadri, Anh Nhat Nhu, Swati Ramnath, Laura Yu Zheng, Raj Bhansali, Sylvette La Touche-Howard, Tracy Marie Zeeger, Tom Goldstein, Ming Lin
https://arxiv.org/abs/2510.02535

PHORECAST: Enabling AI Understanding of Public Health Outreach Across Populations
Understanding how diverse individuals and communities respond to persuasive messaging holds significant potential for advancing personalized and socially aware machine learning. While Large Vision and Language Models (VLMs) offer promise, their ability to emulate nuanced, heterogeneous human responses, particularly in high stakes domains like public health, remains underexplored due in part to the lack of comprehensive, multimodal dataset. We introduce PHORECAST (Public Health Outreach REceptiv…

QAgent: A modular Search Agent with Interactive Query Understanding
Yi Jiang, Lei Shen, Lujie Niu, Sendong Zhao, Wenbo Su, Bo Zheng
https://arxiv.org/abs/2510.08383 https://

QAgent: A modular Search Agent with Interactive Query Understanding
Large language models (LLMs) excel at natural language tasks but are limited by their static parametric knowledge, especially in knowledge-intensive task. Retrieval-augmented generation (RAG) mitigates this by integrating external information. However, (1) traditional RAG struggles with complex query understanding, and (2) even search agents trained with reinforcement learning (RL), despite their promise, still face generalization and deployment challenges. To address these limitations, we prop…

Ming-UniVision: Joint Image Understanding and Generation with a Unified Continuous Tokenizer
Ziyuan Huang, DanDan Zheng, Cheng Zou, Rui Liu, Xiaolong Wang, Kaixiang Ji, Weilong Chai, Jianxin Sun, Libin Wang, Yongjie Lv, Taozhi Huang, Jiajia Liu, Qingpei Guo, Ming Yang, Jingdong Chen, Jun Zhou
https://arxiv.org/abs/2510.06590

Ming-UniVision: Joint Image Understanding and Generation with a Unified Continuous Tokenizer
Visual tokenization remains a core challenge in unifying visual understanding and generation within the autoregressive paradigm. Existing methods typically employ tokenizers in discrete latent spaces to align with the tokens from large language models, where the quantization errors can limit semantic expressiveness and degrade the capability of vision-language understanding. To address this, we introduce MingTok, a new family of visual tokenizers with a continuous latent space, for unified auto…

VISaGE: Understanding Visual Generics and Exceptions
Stella Frank, Emily Allaway
https://arxiv.org/abs/2510.12548 https://arxiv.org/pdf/2510.12548

VISaGE: Understanding Visual Generics and Exceptions
While Vision Language Models (VLMs) learn conceptual representations, in the form of generalized knowledge, during training, they are typically used to analyze individual instances. When evaluation instances are atypical, this paradigm results in tension between two priors in the model. The first is a pragmatic prior that the textual and visual input are both relevant, arising from VLM finetuning on congruent inputs; the second is a semantic prior that the conceptual representation is generally…

The U.S. Department of Justice has sent a confidential draft agreement to more than a dozen states
that would require election officials to
🆘 remove any
🔸alleged 🔸
ineligible voters identified during a federal review of their voter rolls.
The agreement
— called a memorandum of understanding, or MOU
— would❌ hand the federal government a major role in election administration,
a responsibility that belongs to the states under the U.S. Constitution.…

Waiting for the announcment and press conference, the CBC live blog has this nugget:
"Alberta's deficit was initially $1.3B in the February budget, then grew to $6.5B by summer and has likely swelled even further with weak oil and natural gas prices."
Is there an Albertan leader of any party willing to utter the words:
"Maybe the vagaries of Oil and Gas prices is not what we should base our provincial budget on. Perhaps it is time to look at something else.”
#ABPoli #Oil #Gas #LNG #OilPipeline #NorthernGateway #HaidaGwaii #BCPoli
https://www.cbc.ca/news/politics/livestory/alberta-ottawa-memorandum-of-understanding-energy-deal-pipeline-bc-9.6993431

Disruptive Mobilities: Unsettling Law, Space, and Identities through Movement https://www.socialifeoflaw.com/post/disruptive-mobilities-unsettling-law-space-and-identities-through-movement

Disruptive Mobilities: Unsettling Law, Space, and Identities through Movement
The onset of the pandemic generated a powerful, universal newfound currency for mobility. Around the world, many yearned to exercise their freedom of movement, even those who had long settled into sedentary lives. In this context, this seminar series asks: what does mobility mean in today’s times?While the practice of mobility has been normalised as the physical movement across space, its conceptual understanding reveals a more complex relationship between the body, agency, and the State. At …

Read the Room or Lead the Room: Understanding Socio-Cognitive Dynamics in Human-AI Teaming
Jaeyoon Choi, Mohammad Amin Samadi, Spencer JaQuay, Seehee Park, Nia Nixon
https://arxiv.org/abs/2510.09944

Read the Room or Lead the Room: Understanding Socio-Cognitive Dynamics in Human-AI Teaming
Research on Collaborative Problem Solving (CPS) has traditionally examined how humans rely on one another cognitively and socially to accomplish tasks together. With the rapid advancement of AI and large language models, however, a new question emerge: what happens to team dynamics when one of the "teammates" is not human? In this study, we investigate how the integration of an AI teammate -- a fully autonomous GPT-4 agent with social, cognitive, and affective capabilities -- shapes the socio-c…

StreamingVLM: Real-Time Understanding for Infinite Video Streams
Ruyi Xu, Guangxuan Xiao, Yukang Chen, Liuning He, Kelly Peng, Yao Lu, Song Han
https://arxiv.org/abs/2510.09608 …

StreamingVLM: Real-Time Understanding for Infinite Video Streams
Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding near-infinite video streams without escalating latency and memory usage. Processing entire videos with full attention leads to quadratic computational costs and poor performance on long videos. Meanwhile, simple sliding window methods are also flawed, as they either break coherence or suffer from high latency due to redundant recomputation. In this paper, we in…

Vector Graph-Based Repository Understanding for Issue-Driven File Retrieval
Kostiantyn Bevziuk, Andrii Fatula, Svetozar Lashin Yaroslav Opanasenko, Anna Tukhtarova, Ashok Jallepalli Pradeepkumar Sharma, Hritvik Shrivastava
https://arxiv.org/abs/2510.08876

Vector Graph-Based Repository Understanding for Issue-Driven File Retrieval
We present a repository decomposition system that converts large software repositories into a vectorized knowledge graph which mirrors project architectural and semantic structure, capturing semantic relationships and allowing a significant level of automatization of further repository development. The graph encodes syntactic relations such as containment, implementation, references, calls, and inheritance, and augments nodes with LLM-derived summaries and vector embeddings. A hybrid retrieval …

💢 How do drivers react to partisan bumper stickers? Understanding polarization in apolitical settings
#science

Frontiers | How do drivers react to partisan bumper stickers? Understanding polarization in apolitical settings
IntroductionThe impact of political polarization is no longer confined to the voting booth, and partisan identity can shape behavior even in seemingly apolit...

Generation Space Size: Understanding and Calibrating Open-Endedness of LLM Generations
Sunny Yu, Ahmad Jabbar, Robert Hawkins, Dan Jurafsky, Myra Cheng
https://arxiv.org/abs/2510.12699

Generation Space Size: Understanding and Calibrating Open-Endedness of LLM Generations
Different open-ended generation tasks require different degrees of output diversity. However, current LLMs are often miscalibrated. They collapse to overly homogeneous outputs for creative tasks and hallucinate diverse but incorrect responses for factual tasks. We argue that these two failure modes are unified by, and can both be addressed by, the notion of effective generation space size (GSS) -- the set of semantically distinct outputs a model considers for a prompt. We present GSSBench, a ta…

PhysToolBench: Benchmarking Physical Tool Understanding for MLLMs
Zixin Zhang, Kanghao Chen, Xingwang Lin, Lutao Jiang, Xu Zheng, Yuanhuiyi Lyu, Litao Guo, Yinchuan Li, Ying-Cong Chen
https://arxiv.org/abs/2510.09507

PhysToolBench: Benchmarking Physical Tool Understanding for MLLMs
The ability to use, understand, and create tools is a hallmark of human intelligence, enabling sophisticated interaction with the physical world. For any general-purpose intelligent agent to achieve true versatility, it must also master these fundamental skills. While modern Multimodal Large Language Models (MLLMs) leverage their extensive common knowledge for high-level planning in embodied AI and in downstream Vision-Language-Action (VLA) models, the extent of their true understanding of phys…

Understanding and Predicting Temporal Visual Attention Influenced by Dynamic Highlights in Monitoring Task
Zekun Wu, Anna Maria Feit
https://arxiv.org/abs/2510.08777 https://

Understanding and Predicting Temporal Visual Attention Influenced by Dynamic Highlights in Monitoring Task
Monitoring interfaces are crucial for dynamic, highstakes tasks where effective user attention is essential. Visual highlights can guide attention effectively but may also introduce unintended disruptions. To investigate this, we examined how visual highlights affect users' gaze behavior in a drone monitoring task, focusing on when, how long, and how much attention they draw. We found that highlighted areas exhibit distinct temporal characteristics compared to non-highlighted ones, quantified u…

Congress Works For You.
Here’s How to Be a Better Boss:
https://www.propublica.org/series/a-users-guide-to-democracy

A User’s Guide to Democracy
From understanding political ads to seeing what your representatives are actually doing (or not doing), these short guides will help you become a more informed, more engaged, more confident voter.

COLE: a Comprehensive Benchmark for French Language Understanding Evaluation
David Beauchemin, Yan Tremblay, Mohamed Amine Youssef, Richard Khoury
https://arxiv.org/abs/2510.05046

COLE: a Comprehensive Benchmark for French Language Understanding Evaluation
To address the need for a more comprehensive evaluation of French Natural Language Understanding (NLU), we introduce COLE, a new benchmark composed of 23 diverse task covering a broad range of NLU capabilities, including sentiment analysis, paraphrase detection, grammatical judgment, and reasoning, with a particular focus on linguistic phenomena relevant to the French language. We benchmark 94 large language models (LLM), providing an extensive analysis of the current state of French NLU. Our r…

UniVideo: Unified Understanding, Generation, and Editing for Videos
Cong Wei, Quande Liu, Zixuan Ye, Qiulin Wang, Xintao Wang, Pengfei Wan, Kun Gai, Wenhu Chen
https://arxiv.org/abs/2510.08377

UniVideo: Unified Understanding, Generation, and Editing for Videos
Unified multimodal models have shown promising results in multimodal content generation and editing but remain largely limited to the image domain. In this work, we present UniVideo, a versatile framework that extends unified modeling to the video domain. UniVideo adopts a dual-stream design, combining a Multimodal Large Language Model (MLLM) for instruction understanding with a Multimodal DiT (MMDiT) for video generation. This design enables accurate interpretation of complex multimodal instru…

"Having Lunch Now": Understanding How Users Engage with a Proactive Agent for Daily Planning and Self-Reflection
Adnan Abbas, Caleb Wohn, Arnav Jagtap, Eugenia H Rho, Sang Won Lee
https://arxiv.org/abs/2509.24073

"Having Lunch Now": Understanding How Users Engage with a Proactive Agent for Daily Planning and Self-Reflection
Conversational agents have been studied as tools to scaffold planning and self-reflection for productivity and well-being. While prior work has demonstrated positive outcomes, we still lack a clear understanding of what drives these results and how users behave and communicate with agents that act as coaches rather than assistants. Such understanding is critical for designing interactions in which agents foster meaningful behavioral change. We conducted a 14-day longitudinal study with 12 parti…

Understanding the Effects of Domain Finetuning on LLMs
Eshaan Tanwar, Deepak Nathani, William Yang Wang, Tanmoy Chakraborty
https://arxiv.org/abs/2510.09359 https://

Understanding the Effects of Domain Finetuning on LLMs
Large Language Models (LLMs) fine-tuned for specific domains exhibit strong performance; however, the underlying mechanisms by which this fine-tuning reshapes their parametric space are not well understood. Prior works primarily focus on auto-regressive or general-purpose instruct models, leaving domain-specialised LLMs under-explored. We present the first systematic study of domain-specific fine-tuning in large medical language models. Our analysis reveals that fine-tuning modifies only a smal…

A Set of Quebec-French Corpus of Regional Expressions and Terms
David Beauchemin, Yan Tremblay, Mohamed Amine Youssef, Richard Khoury
https://arxiv.org/abs/2510.05026 https://…

A Set of Quebec-French Corpus of Regional Expressions and Terms
The tasks of idiom understanding and dialect understanding are both well-established benchmarks in natural language processing. In this paper, we propose combining them, and using regional idioms as a test of dialect understanding. Towards this end, we propose two new benchmark datasets for the Quebec dialect of French: QFrCoRE, which contains 4,633 instances of idiomatic phrases, and QFrCoRT, which comprises 171 regional instances of idiomatic words. We explain how to construct these corpora, …

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 …

ExpVid: A Benchmark for Experiment Video Understanding & Reasoning
Yicheng Xu, Yue Wu, Jiashuo Yu, Ziang Yan, Tianxiang Jiang, Yinan He, Qingsong Zhao, Kai Chen, Yu Qiao, Limin Wang, Manabu Okumura, Yi Wang
https://arxiv.org/abs/2510.11606

ExpVid: A Benchmark for Experiment Video Understanding & Reasoning
Multimodal Large Language Models (MLLMs) hold promise for accelerating scientific discovery by interpreting complex experimental procedures. However, their true capabilities are poorly understood, as existing benchmarks neglect the fine-grained and long-horizon nature of authentic laboratory work, especially in wet-lab settings. To bridge this gap, we introduce ExpVid, the first benchmark designed to systematically evaluate MLLMs on scientific experiment videos. Curated from peer-reviewed video…

SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models
Weiyang Jin, Yuwei Niu, Jiaqi Liao, Chengqi Duan, Aoxue Li, Shenghua Gao, Xihui Liu
https://arxiv.org/abs/2510.12784

SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models
Recently, remarkable progress has been made in Unified Multimodal Models (UMMs), which integrate vision-language generation and understanding capabilities within a single framework. However, a significant gap exists where a model's strong visual understanding often fails to transfer to its visual generation. A model might correctly understand an image based on user instructions, yet be unable to generate a faithful image from text prompts. This phenomenon directly raises a compelling question: …

AdaRD-key: Adaptive Relevance-Diversity Keyframe Sampling for Long-form Video understanding
Xian Zhang, Zexi Wu, Zinuo Li, Hongming Xu, Luqi Gong, Farid Boussaid, Naoufel Werghi, Mohammed Bennamoun
https://arxiv.org/abs/2510.02778

AdaRD-key: Adaptive Relevance-Diversity Keyframe Sampling for Long-form Video understanding
Understanding long-form videos remains a significant challenge for vision--language models (VLMs) due to their extensive temporal length and high information density. Most current multimodal large language models (MLLMs) rely on uniform sampling, which often overlooks critical moments, leading to incorrect responses to queries. In parallel, many keyframe selection approaches impose rigid temporal spacing: once a frame is chosen, an exclusion window suppresses adjacent timestamps to reduce redun…

MomentSeg: Moment-Centric Sampling for Enhanced Video Pixel Understanding
Ming Dai, Sen Yang, Boqiang Duan, Wankou Yang, Jingdong Wang
https://arxiv.org/abs/2510.09274 https://

MomentSeg: Moment-Centric Sampling for Enhanced Video Pixel Understanding
Referring Video Object Segmentation (RefVOS) seeks to segment target objects in videos guided by natural language descriptions, demanding both temporal reasoning and fine-grained visual comprehension. Existing sampling strategies for LLM-based approaches typically rely on either handcrafted heuristics or external keyframe models. The former often overlooks essential temporal cues, while the latter increases system complexity. To address this, we propose a unified framework that jointly optimize…

VideoNSA: Native Sparse Attention Scales Video Understanding
Enxin Song, Wenhao Chai, Shusheng Yang, Ethan Armand, Xiaojun Shan, Haiyang Xu, Jianwen Xie, Zhuowen Tu
https://arxiv.org/abs/2510.02295

VideoNSA: Native Sparse Attention Scales Video Understanding
Video understanding in multimodal language models remains limited by context length: models often miss key transition frames and struggle to maintain coherence across long time scales. To address this, we adapt Native Sparse Attention (NSA) to video-language models. Our method, VideoNSA, adapts Qwen2.5-VL through end-to-end training on a 216K video instruction dataset. We employ a hardware-aware hybrid approach to attention, preserving dense attention for text, while employing NSA for video. Co…