Tootfinder

Reflective VLM Planning for Dual-Arm Desktop Cleaning: Bridging Open-Vocabulary Perception and Precise Manipulation
Yufan Liu, Yi Wu, Gweneth Ge, Haoliang Cheng, Rui Liu
https://arxiv.org/abs/2506.17328

Reflective VLM Planning for Dual-Arm Desktop Cleaning: Bridging Open-Vocabulary Perception and Precise Manipulation
Desktop cleaning demands open-vocabulary recognition and precise manipulation for heterogeneous debris. We propose a hierarchical framework integrating reflective Vision-Language Model (VLM) planning with dual-arm execution via structured scene representation. Grounded-SAM2 facilitates open-vocabulary detection, while a memory-augmented VLM generates, critiques, and revises manipulation sequences. These sequences are converted into parametric trajectories for five primitives executed by coordin…

I don't want to point fingers, so won't mention any names, but what would you think of an Open Source project where the main developer loves one- or two-word commit messages like:
push
fix push
cleaning
fix
async
But hey, as an end user, as long as it is tasty, no need to visit there sausage factory.

Cat was covered in car oil. Had to wash cat. Cat was not happy :(
#CatsOfMastodon

Lets be honest, we spend too much time cleaning data. {janitor} can help with that: #rstats

Despite our heroic fantasies, true societal transformation is often an undramatic, persistent task of caring for the world around us, like cleaning tables and picking up trash. full article @ https://www.brichapman.com/p/how-to-save-the-world

Erosion, not Explosion
A Field Guide to Slow Work, Sacred Mess, and Unseen Change

Watching window cleaning robots never gets old.

Years ago someone told me that most lab glassware that breaks does so during cleaning, not during actual experimental usage.
It makes some level of intuitive sense, given the amount of handling involved in cleaning. But has this ever been seriously studied?

Check out my new blog post: Better Video Audio with Auphonic
https://www.speedofcreativity.org/2025/05/18/better-video-audio-with-auphonic/
Featuring my new video: Spring Cleaning My RecTeq RT-700 Bull Smoker: Tips & Tricks!

Safe Robotic Capsule Cleaning with Integrated Transpupillary and Intraocular Optical Coherence Tomography
Yu-Ting Lai, Yasamin Foroutani, Aya Barzelay, Tsu-Chin Tsao
https://arxiv.org/abs/2507.13650

Safe Robotic Capsule Cleaning with Integrated Transpupillary and Intraocular Optical Coherence Tomography
Secondary cataract is one of the most common complications of vision loss due to the proliferation of residual lens materials that naturally grow on the lens capsule after cataract surgery. A potential treatment is capsule cleaning, a surgical procedure that requires enhanced visualization of the entire capsule and tool manipulation on the thin membrane. This article presents a robotic system capable of performing the capsule cleaning procedure by integrating a standard transpupillary and an in…

"Linkding – Bookmark-Manager nach dem Ende von Pocket nutzen" https://digital-cleaning.de/index.php/linkding-bookmark-manager-nach-dem-ende-von-pocket-nutzen/

Clorox lawsuit says help-desk contractors handed over passwords in 2023 cyberattack https://therecord.media/clorox-cyberattack-lawsuit-cognizant-it-contractor

Done for the day! Got so much done thanks to the much more mild temperatures (22°C with a breeze!)
Pebble and drain rock are complete in the Bay. Brought the pebble to just below the middle holes around the bin. (There is another row of them a few inches below)
The drain rock up to the larger holes so that larger debris can be drawn into the bin.
I was really hoping to get my big shipment of various sizes of rock/pebble this week but the rock place was too busy for little me. They promised Monday!
All the rock has to be clean to act as a good organic filter (dirt on rock means no space for good water cleaning bacteria to attach!) so I am washing as I go.
I try to wash most of it in the hole itself since then I can direct where it gets pumped out. Today the blueberry 🫐 and flower 🌹 garden was the benificiary. Tomorrow maybe the hazelnut tree 🌳
Still very happy with the progress though. Feel like I'm getting into the meat of the project now!
#pondpool #backyardpond #diy #portalberni

A Garden Aloft ⛲️
空中花园 ⛲️
📷 Nikon FE
🎞️Ilford FP4 Plus, expired 1994
buy me ☕️ ?/请我喝杯☕️？
#filmphotography

Wow, cleaning out my excess 😬 browser tabs last night, I came across this gem: https://ia.net/topics/markdown-and-the-slow-fade-of-the-formatting-fetish - this is something most people need to see, especially those in government and education.

Cleaning up my #jellyfin genre metadata.
Wayne's World: #Movie - #Comedy
Dead Kennedys: #Music

Im cleaning out lots of old files. Im trying not to be a data horder. Amusingly I found two old talks I gave. In 2012 I gave a talk titled "Don't get hit by a bus!" and in 2019 "NMS for Fun and Profit". Reaching father back, in 1999 I made a presentation on "Using Email Effectively". Anyone remember Eudora? I also found some documentation on 'addzone'. No source code, sadly.

Got the documentation for the dice parser software online and now I can close the laptop and relax a bit. I think it still needs some cleaning up, but it's good enough for now.
#python

Machine learning approaches for automatic cleaning of investigative drilling data
Fei Huang (Flinders University), Hongyu Qin (Flinders University), Masoud Manafi (Civil Group), Ben Juett (Civil Group), Ben Evans (Civil Group)
https://arxiv.org/abs/2506.14289

Machine learning approaches for automatic cleaning of investigative drilling data
Investigative drilling (ID) is an innovative measurement while drilling (MWD) technique that has been implemented in various site investigation projects across Australia. While the automated drilling feature of ID substantially reduces noise within drilling data streams, data cleaning remains essential for removing anomalies to enable accurate strata classification and prediction of soil and rock properties. This study employed three machine learning algorithms--IsoForest, one-class SVM, and DB…

I’ve long been a fan of the Check My Ads people. Now they’re launching a really ambitious-looking “Policy Platform” aimed at cleaning up the online-advertising business. My belief is that anyone who’s had much exposure to that business or to “AdTech” probably agrees that cleanup is called for. Check it out: https://checkmyads.org/policy/

Towards Practical Benchmarking of Data Cleaning Techniques: On Generating Authentic Errors via Large Language Models
Xinyuan Liu, Jiahui Chen, Bocheng Hu, Yu Sun, Xinyang Chen, Shaoxu Song
https://arxiv.org/abs/2507.10934

Towards Practical Benchmarking of Data Cleaning Techniques: On Generating Authentic Errors via Large Language Models
Data quality remains an important challenge in data-driven systems, as errors in tabular data can severely compromise downstream analytics and machine learning performance. Although numerous error detection algorithms have been proposed, the lack of diverse, real-world error datasets limits comprehensive evaluation. Manual error annotation is both time-consuming and inconsistent, motivating the exploration of synthetic error generation as an alternative. In this work, we introduce TableEG, a fr…

Acoustic-Driven Surface Cleaning with Millimeter-Sized Bubbles at Translational Resonance
Yan Jun Lin, Zhengyang Liu, Sunghwan Jung
https://arxiv.org/abs/2506.06581

Acoustic-Driven Surface Cleaning with Millimeter-Sized Bubbles at Translational Resonance
Traditional surface cleaning methods often suffer from drawbacks such as chemical harshness, potential for surface damage, and high energy consumption. This study investigates an alternative approach: acoustic-driven surface cleaning using millimeter-sized bubbles excited at low, sub-cavitation frequencies. We identify and characterize a distinct translational resonance of these bubbles, occurring at significantly lower frequencies (e.g., 50 Hz for 1.3 mm diameter bubbles) than the Minnaert res…

This https://arxiv.org/abs/2503.22361 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_…

A novel approach of optimizing the image cleaning performance of Imaging Atmospheric Cherenkov Telescopes: Application to a time-based cleaning for H.E.S.S
This study introduces a time-based cleaning method for H.E.S.S. using CT5 in monoscopic mode and presents an optimization workflow for image-cleaning algorithms to enhance telescope sensitivity while minimizing systematic biases. We evaluate three methods - tail-cut cleaning and two flavours of time-based cleaning TIME3D and TIME4D - and find best-cut configurations for two cases: optimal overall sensitivity and minimal energy threshold. TIME3D achieves a $\sim 15\%$ improvement with regard to …

🇺🇦 #NowPlaying on KEXP's #DriveTime
Dry Cleaning:
🎵 Unsmart Lady
#DryCleaning
https://drycleaning.bandcamp.com/track/unsmart-lady
https://open.spotify.com/track/3iY8QI12kti4hVZYMZvsbd

Once again, after cleaning up the desk I'm working hard at bending the gamepad's USB cable to make it work.
I suppose I could get a new cable…

The MRI at Iceland's biggest hospital Landspítalinn is broken at the moment.
A scrubber that cleaning personal brought into the room is now stuck inside. 😂
Repairs are under way
https://www.mbl.is/frettir/innlent/2025/06

Skúringatæki festist á segulómtæki Landspítalans
Skúringatæki festist á segulómtæki Landspítalans við Hringbraut. Tækið er nú óvirkt en unnið er að því að losa skúringatækið af vélinni.

Linking Multi-Site Sex Ad Data at the Individual Level to Aid Counter-Trafficking Efforts
Nickolas K. Freeman, Gregory J. Bott, Burcu B. Keskin, Jason M. Parton, James J. Cochran
https://arxiv.org/abs/2507.13477

Linking Multi-Site Sex Ad Data at the Individual Level to Aid Counter-Trafficking Efforts
The Internet facilitates sex trafficking through adult service websites (ASWs) that host online advertisements for sexual services (sex ads). Since the closure of the popular site Backpage.com, the ecosystem of ASWs has expanded to include multiple competing sites that are hosted outside US jurisdiction. Gaining intelligence for counter-trafficking efforts requires collecting, linking, and cleaning the data from multiple sites. However, high ad volumes, disparate data types, and the existence o…

Again, learn from Turkey, because Trump sure is. Erdoğan did the same thing, cleaning out the ranks… and he’s managed to cling onto power for decades because of it. https://infosec.exchange/@Nonya_Bidniss/114797134888601938

Cleaning up Trump's mess, California surges regional law enforcement response in Los Angeles (Marissasaldivar/Governor of California)
https://www.gov.ca.gov/2025/06/09/100885/
http://www.memeorandum.com/250609/p151#a250609p151

a recipe adjustment for my cheese / ham / egg toastie:
cooking it open in the panini press is good if i have good ham, but it requires more cleaning
so i put a butter / bread / cheese / ham / ham / cheese / bread / butter toastie as a single stack in the press
fry an egg while it is grilling
when they are done, split the toastie between the ham slices
slide in the fried egg and chilli sauce
and enjoy a post-pub uitsmijter toastie, with just an easy wipe cl…

Took a day off work to get ready for holiday tomorrow. Predictably I have spent the whole day working. 🙄
Must get on actually packing, cleaning, and other essentials now...
#AcademicChatter

On Saturday we spent a deal of time cleaning up the shed and whist it's not finished it's a lot closer to the way it looked some 15 years ago when I started using it.
There is still a lot to do, build another 2 bookcases and put them in the server room at the end of the shed. And then replace the blinds.
#Shed

Was cleaning out my tabs, and wow, this article aged well. 😂
https://www.theverge.com/2024/9/18/24247985/tesla-cybertruck-july-2024-sales-deliveries-match-all-ev-trucks

Tesla sold more Cybertrucks than almost all other EV trucks combined
Tesla Cybertruck registrations in July almost match overall EV truck registrations, including Rivian R1T and Ford F-150 Lightning, suggesting strong Cybertruck demand.

Crystal Collimation Cleaning Measurements with 6.5 TeV protons in the LHC
Roberto Rossi, Gianluca Cavoto, Daniele Mirarchi, Stefano Redaelli, Walter Scandale
https://arxiv.org/abs/2507.13315

Crystal Collimation Cleaning Measurements with 6.5 TeV protons in the LHC
Safe disposal of beam halo is a fundamental requirement of modern superconductive hadron colliders to reduce thermal load on magnets and background to experimental detectors. In the CERN Large Hadron Collider (LHC) a multistage system fully compliant with the needs of the baseline operation was build. At a later stage, two short bent crystals were interleaved to the devices for betatron collimation to investigate efficiency enhancement of the halo disposal when inserting them as primary stages …

Urban Discoveries 🏙️
都市发现 🏙️
📷 Pentax MX
🎞️Lucky SHD 400
buy me ☕️ ?/请我喝杯☕️？
#filmphotography

Yiding Cao Geld mit PayPal.Me senden
Folgen Sie dem Link PayPal.Me/dingsterdingster und geben Sie den Betrag ein. Es ist bequem und sicher. Sie haben noch kein PayPal-Konto? Kein Problem.

Re this from @…, of the biggest tells about the current AI hype bubble:
Instead of replacing the work humans don’t want to do, it’s purporting to replace the work executives hate paying for.
Instead of an end to drudgery, they’re pushing an end to purpose and meaning.
And yeah, we’re going to end up cleaning up the AI’s messes. And doing its laundry.
https://mastodon.social/@PavelASamsonov/114598616057210141

Replaced the garbage #disposal last night. It's one of those jobs like redoing the guts of a toilet; seemed intimidating but it was far easier than I expected. (Replacing with the same model helps.) #insinkerator #diy

🇺🇦 Auf radioeins läuft...
Dry Cleaning:
🎵 Strong Feelings
#NowPlaying #DryCleaning
https://drycleaning.bandcamp.com/track/strong-feelings
https://open.spotify.com/track/4w7iiR54wJS8qYJG7dwcIX

If anyone in Seattle is looking for some vintage Apple gear (old Intel Mac Pro towers, old Intel MacBook Pros, old Apple Cinema and Thunderbolt displays, old iPhones and iPads and Apple Watches, etc.), we're doing some spring cleaning! Many of these are currently going for $20 or less.
https://mastodon.om…

Cleaning up my lab after removing a piece of client hardware from a $dayjob project.
Durng that project I was using *every single one* of the 12 RJ45 gig-e drops on the west wall of my lab:
* Siglent load
* MultiLane BERT
* 4 GHz LeCroy scope
* R&S DMM
* R&S PSU
* Work laptop on sandbox vlan
* 2x Siglent AWG for ThunderScope testing
* Windows laptop for ThunderScope testing
* Siglent PSU on bench with client device
* Two NICs on…

Dirty Data in the Newsroom: Comparing Data Preparation in Journalism and Data Science
Stephen Kasica, Charles Berret, Tamara Munzner
https://arxiv.org/abs/2507.07238

Dirty Data in the Newsroom: Comparing Data Preparation in Journalism and Data Science
The work involved in gathering, wrangling, cleaning, and otherwise preparing data for analysis is often the most time consuming and tedious aspect of data work. Although many studies describe data preparation within the context of data science workflows, there has been little research on data preparation in data journalism. We address this gap with a hybrid form of thematic analysis that combines deductive codes derived from existing accounts of data science workflows and inductive codes arisin…

Surface cleaning archives may be considered mundane but for people who pay attention, one can see all kinds of interesting things like this early style of #paperclip.
#VintageStationery

I hate it when I spill my drink on the keyboard. 2 seconds for the accident to happen. 25 minutes cleaning the damn thing. Thankfully, everything is working as it should be, so business as normal.

Almost 40 years ago. Was cleaning up a messy desk, found an old photo album. Pretty glad I took and saved these photos. I was still floundering in gradual school, not yet engaged, and in the evening I would ride my bike uphill (Quimby Road, 9% average grade for about 2000 feet of elevation) so as to improve my mood and my knees. Earlier that day I had stepped out the back door of work (IBM SJRL in the old triangle building) and the whole sky was full of smoke.

Networking is finished, and every port on the QNAP switch is in use along with every port on each MS-A2. Also tracked down an `interfaces` file typo. The next step is cleaning up the "server room" and getting this situated.
#homelab #minirack

Yesterday I cleaned the hallway and had a first pass at the kitchen. Vacuum cleaned the floor, the walls, the ceilings. Today I'll mop the living room and bed room and take another pass at the kitchen. If time permits will do a bit of cleaning on the outside to remove spiderwebs and muss. Kids installed a hammock and we went swimming in the lake #project25

Urban Discoveries 🏙️
都市发现 🏙️
📷 Pentax MX
🎞️Lucky SHD 400
buy me ☕️ ?/请我喝杯☕️？
#filmphotography

Yiding Cao Geld mit PayPal.Me senden
Folgen Sie dem Link PayPal.Me/dingsterdingster und geben Sie den Betrag ein. Es ist bequem und sicher. Sie haben noch kein PayPal-Konto? Kein Problem.

SCCRUB: Surface Cleaning Compliant Robot Utilizing Bristles
Jakub F. Kowalewski, Keeyon Hajjafar, Alyssa Ugent, Jeffrey Ian Lipton
https://arxiv.org/abs/2507.06053

SCCRUB: Surface Cleaning Compliant Robot Utilizing Bristles
Scrubbing surfaces is a physically demanding and time-intensive task. Removing adhered contamination requires substantial friction generated through pressure and torque or high lateral forces. Rigid robotic manipulators, while capable of exerting these forces, are usually confined to structured environments isolated from humans due to safety risks. In contrast, soft robot arms can safely work around humans and adapt to environmental uncertainty, but typically struggle to transmit the continuous…

Packed up my XBOX and large TV in the basement today :-(
I don't play video games every day, but 2 or 3 days a week, my daughter, who lives in Toronto, and I will play Halo online and defend the universe from Covenant forces. It's now 22 days until the moving trucks arrive, and planning for activities each day is underway. We have to allocate time for yard maintenance, packing, and cleaning. Accompanying music choices are important...
#MyPlaylist #RandomTune
https://youtu.be/t267aQJcwjs?si=jb8_X470NFFXY6Yp

This https://arxiv.org/abs/2504.13070 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_…

A quadratic estimator view of the transfer function correction in intensity mapping surveys
In single dish neutral hydrogen (HI) intensity mapping, signal separation methods such as principal component analysis (PCA) are used to clean the astrophysical foregrounds. PCA induces a signal loss in the estimated power spectrum, which can be corrected by a transfer function (TF). By injecting mock signals of HI into the data and performing the PCA cleaning, we can use the cleaned mock HI signal to cross-correlate with the original mock, and estimate the signal loss as a TF, ${T}(\vec{k})$. …

End-to-End Large Portfolio Optimization for Variance Minimization with Neural Networks through Covariance Cleaning
Christian Bongiorno, Efstratios Manolakis, Rosario Nunzio Mantegna
https://arxiv.org/abs/2507.01918

End-to-End Large Portfolio Optimization for Variance Minimization with Neural Networks through Covariance Cleaning
We develop a rotation-invariant neural network that provides the global minimum-variance portfolio by jointly learning how to lag-transform historical returns and how to regularise both the eigenvalues and the marginal volatilities of large equity covariance matrices. This explicit mathematical mapping offers clear interpretability of each module's role, so the model cannot be regarded as a pure black-box. The architecture mirrors the analytical form of the global minimum-variance solution yet …

Cleaning out a closet.
I have no use for these but feels a shame to get rid of them. Anybody have a good home for them?

🇺🇦 #NowPlaying on KEXP's #VarietyMix
Dry Cleaning:
🎵 Oblivion
#DryCleaning
https://open.spotify.com/track/02HD6cY24Q6YQoefbwtWsl

Re this from @…, of the biggest tells about the current AI hype bubble:
Instead of replacing the work humans don’t want to do, it’s purporting to replace the work executives hate paying for.
Instead of an end to drudgery, they’re pushing an end to purpose and meaning.
And yeah, we’re going to end up cleaning up the AI’s messes. And doing its laundry.
https://mastodon.social/@PavelASamsonov/114598616057210141

All three nodes are installed. The "server room" is an absolute mess, but figured I'd snap a picture of the back of the minirack. I'll be cleaning up tomorrow, but for now: we are 100% back online here. Migrations work, iSCSI works...well, everything works. Very happy with how this has turned out thus far.
#minirack

🇺🇦 #NowPlaying on #BBC6Music's #NickGrimshaw
Dry Cleaning:
🎵 Don't Press Me
#DryCleaning
https://drycleaning.bandcamp.com/track/dont-press-me
https://open.spotify.com/track/3z0aEiTNaPtOFPUPHpMEjO

KramaBench: A Benchmark for AI Systems on Data-to-Insight Pipelines over Data Lakes
Eugenie Lai, Gerardo Vitagliano, Ziyu Zhang, Sivaprasad Sudhir, Om Chabra, Anna Zeng, Anton A. Zabreyko, Chenning Li, Ferdi Kossmann, Jialin Ding, Jun Chen, Markos Markakis, Matthew Russo, Weiyang Wang, Ziniu Wu, Michael J. Cafarella, Lei Cao, Samuel Madden, Tim Kraska

KramaBench: A Benchmark for AI Systems on Data-to-Insight Pipelines over Data Lakes
Constructing real-world data-to-insight pipelines often involves data extraction from data lakes, data integration across heterogeneous data sources, and diverse operations from data cleaning to analysis. The design and implementation of data science pipelines require domain knowledge, technical expertise, and even project-specific insights. AI systems have shown remarkable reasoning, coding, and understanding capabilities. However, it remains unclear to what extent these capabilities translate…

🇺🇦 #NowPlaying on KEXP's #MiddayShow
Dry Cleaning:
🎵 Conversation
#DryCleaning
https://drycleaning.bandcamp.com/track/conversation
https://open.spotify.com/track/0MZfMBqsHdmfyIy2Ksiqoi

That sewing machine part from Canada? It was reshipped, and hopefully will arrive this time. Who knows what process it will go through, or what I will have to do to get it. If the gub-mint imposes a tax, do I pay it on pickup or what? All this to get a sewing machine from 1953 sewing again. Yeesh. I other sewing news, the 1937 Featherweight is working. I removed the old busted (and hardwired) pedal, and got a replacement cord/pedal. I just need to finish the cleaning / lube job and then gif…

Lessons Learned from the URGENT 2024 Speech Enhancement Challenge
Wangyou Zhang, Kohei Saijo, Samuele Cornell, Robin Scheibler, Chenda Li, Zhaoheng Ni, Anurag Kumar, Marvin Sach, Wei Wang, Yihui Fu, Shinji Watanabe, Tim Fingscheidt, Yanmin Qian
https://arxiv.org/abs/2506.01611

Lessons Learned from the URGENT 2024 Speech Enhancement Challenge
The URGENT 2024 Challenge aims to foster speech enhancement (SE) techniques with great universality, robustness, and generalizability, featuring a broader task definition, large-scale multi-domain data, and comprehensive evaluation metrics. Nourished by the challenge outcomes, this paper presents an in-depth analysis of two key, yet understudied, issues in SE system development: data cleaning and evaluation metrics. We highlight several overlooked problems in traditional SE pipelines: (1) misma…

The Case for Instance-Optimized LLMs in OLAP Databases
Bardia Mohammadi, Laurent Bindschaedler
https://arxiv.org/abs/2507.04967 https://

The Case for Instance-Optimized LLMs in OLAP Databases
Large Language Models (LLMs) can enhance analytics systems with powerful data summarization, cleaning, and semantic transformation capabilities. However, deploying LLMs at scale -- processing millions to billions of rows -- remains prohibitively expensive in computation and memory. We present IOLM-DB, a novel system that makes LLM-enhanced database queries practical through query-specific model optimization. Instead of using general-purpose LLMs, IOLM-DB generates lightweight, specialized model…

Effective Explanations for Belief-Desire-Intention Robots: When and What to Explain
Cong Wang, Roberto Calandra, Verena Kl\"os
https://arxiv.org/abs/2507.02016

Effective Explanations for Belief-Desire-Intention Robots: When and What to Explain
When robots perform complex and context-dependent tasks in our daily lives, deviations from expectations can confuse users. Explanations of the robot's reasoning process can help users to understand the robot intentions. However, when to provide explanations and what they contain are important to avoid user annoyance. We have investigated user preferences for explanation demand and content for a robot that helps with daily cleaning tasks in a kitchen. Our results show that users want explanatio…

🇺🇦 #NowPlaying on #BBC6Music's #6MusicsIndieForever
Dry Cleaning:
🎵 Gary Ashby
#DryCleaning
https://drycleaning.bandcamp.com/track/gary-ashby
https://open.spotify.com/track/10yQwebXPazuU2KxH1XR4r