Tootfinder

KiseKloset: Comprehensive System For Outfit Retrieval, Recommendation, And Try-On
Thanh-Tung Phan-Nguyen, Khoi-Nguyen Nguyen-Ngoc, Tam V. Nguyen, Minh-Triet Tran, Trung-Nghia Le
https://arxiv.org/abs/2506.23471

KiseKloset: Comprehensive System For Outfit Retrieval, Recommendation, And Try-On
The global fashion e-commerce industry has become integral to people's daily lives, leveraging technological advancements to offer personalized shopping experiences, primarily through recommendation systems that enhance customer engagement through personalized suggestions. To improve customers' experience in online shopping, we propose a novel comprehensive KiseKloset system for outfit retrieval, recommendation, and try-on. We explore two approaches for outfit retrieval: similar item retrieval …

Ich fahre nach
"Ham Westfohlen"
Thank you for trävelling with Deutsche Barn.

Now I'm imagining installing a retractable white sheet that coudl be rolled out over the my existing roof in the summer, then rolled up in the winter.

Robust Distributed Phase Retrieval for Multi-View Compressive Networked Sensing With Outliers
Ming-Hsun Yang
https://arxiv.org/abs/2505.24651 https://

Robust Distributed Phase Retrieval for Multi-View Compressive Networked Sensing With Outliers
This work examines the multi-view compressive phase retrieval problem in a distributed sensor network, where each sensor device, limited by storage and sensing capabilities, can access only intensity measurements from an unknown part of the global sparse vector. The goal is to enable each sensor to recover its observable sparse signal when measurements are corrupted by outliers. To achieve reliable local signal recovery with limited data access, we propose a distributed reconstruction algorithm…

Hey! Just wanted to boost this cool shirt I bought from https://vkc.sh/merch/.
Linux is awesome & so are you! Thanks for making cool videos and shirts @…!
Support small busi…

Derivations of two one-dimensional models for transversely curved shallow shells: one leads to relaxation
Paroni Roberto, Picchi Scardaoni Marco
https://arxiv.org/abs/2507.23545

Derivations of two one-dimensional models for transversely curved shallow shells: one leads to relaxation
We study the $Γ$-limit of sequences of variational problems for straight, transversely curved shallow shells, as the width of the planform $\varepsilon$ goes to zero. The energy is of von Kármán type for shallow shells under suitable boundary conditions. What distinguishes the various regimes is the scaling of the stretching energy $\sim \varepsilon^{2β}$, with $β$ a positive number. We derive two one-dimensional models as $β$ ranges in $(0, 2]$. Remarkably, boundary conditions are esse…

Période : en semaine de 10h26 Š 15h30.
Dates : du lundi 01 au vendredi 19 septembre.
Le trafic est interrompu entre Melun et Montereau via Héricy.
Un service de bus de remplacement est mis en place, avec desserte des gares intermédiaires.
Les horaires du calculateur d'itinéraire tiennent compte des travaux.
Motif : travaux sur le réseau ferroviaire.
#Info_Travaux

Microsoft wirft Windows PowerShell 2.0 über Bord
PowerShell 2.0 hat schon einige Jahre auf dem Buckel. Microsoft wirft es daher aus Windows raus und rät zur Migration.
https://www.…

little fella knows nothing about mastodon #CatsOfMastodon

🔍 How to centaur a div

@… #moma berichtet heute stündlich über den #bürgerbus: "heute gibt es überall in deutschland den bürgerbus, aber vor 40 jahren war dieser der erste…

@… #moma berichtet heute stündlich über den #bürgerbus: "heute gibt es überall in deutschland den bürgerbus, aber vor 40 jahren war dieser der erste…

X hires Nikita Bier, the serial entrepreneur who was behind polling startup TBH and teen-focused social network Gas, as its new head of product (Kurt Wagner/Bloomberg)
https://www.bloomberg.com/news/articles/2025-06-30/…

This map of Europe showing housing cost, Copenhagen region just pops out compared to rest of Denmark... 😕
https://europeancorrespondent.com/en/r/living-at-great-cost

@… インストールして、認証、タイムライン表示、検索、ポストなどが機能するところまで確認できました！

@… beautiful post (of course the keyboards but the other parts looked great too)

Read the Docs Before Rewriting: Equip Rewriter with Domain Knowledge via Continual Pre-training
Qi Wang, Yixuan Cao, Yifan Liu, Jiangtao Zhao, Ping Luo
https://arxiv.org/abs/2507.00477

Read the Docs Before Rewriting: Equip Rewriter with Domain Knowledge via Continual Pre-training
A Retrieval-Augmented Generation (RAG)-based question-answering (QA) system enhances a large language model's knowledge by retrieving relevant documents based on user queries. Discrepancies between user queries and document phrasings often necessitate query rewriting. However, in specialized domains, the rewriter model may struggle due to limited domain-specific knowledge. To resolve this, we propose the R\&R (Read the doc before Rewriting) rewriter, which involves continual pre-training on pro…

Proud to have eaten a breakfast that includes 3 of the 4 major food groups: bread, coffee, and chocolate

‘Britain’s most tattooed man’ claims he is unable to watch p*rn as ‘new age check system mistakes his ink for a mask’
https://needtoknow.co.uk/2025/07/30/britains-most-tattooed-man-claims-he-i…

‘Britain’s most tattooed man’ claims he is unable to watch p*rn as 'new age check system mistakes his ink for a mask' | Need To Know
Britain’s most tattooed man says new UK age checks block him from p*rn sites as facial recognition mistakes his tattoos for a mask, calling the tech discriminatory.

Expect more content on @… from Sunday on, as I change my personality to full on Wikimedian for a week.

General Staff: Russia has lost 1,020,980 troops in Ukraine since Feb. 24, 2022: https://benborges.xyz/2025/07/01/general-staff-russia-has-lost.html

It is only a matter of time until noem, homan, dhs, ice and potus realize dropping people out of aircraft is cheaper than housing or moving them.
Unless they already have.
Rumors are the US is engaging in death flights. Already there are some known flight paths of ice flights turning around over bodies of water.
The US Congress and international community seem to be the only things that can stop this.

1/ I'm feeling real pain at the cuts to Indiana public universities, especially IU, especially cogsci. These are some of the biggest brains in cogsci and edupsych in the world, but why do *I* care? I'll tell you what they've done *for me, personally*. ↵
https://www.i…

Indiana public colleges cut almost 20% of degrees
Public Indiana colleges and universities have eliminated 19 percent of their degree programs to meet requirements added to the state’s budget, according to the Commission for Higher Education.

A jet carrying the European Commission president to Plovdiv, in Bulgaria, on Sunday had its GPS navigation services disabled, a spokesman for the commission told The Telegraph.
The plane was forced to circle the airport for an hour before the pilot landed using analogue maps in what officials said was “undeniable interference”.

Ursula von der Leyen’s plane forced to land blind after ‘Russia jams GPS’
Ursula von der Leyen’s plane has been targeted by suspected Russian interference, forcing her pilot to land using paper maps.

A couple years ago I made an accordion showing common message colors for applications:
https://codepen.io/aardrian/pen/qBLNYBe
Some details:

Common Application Message Colors
Reflects colors I have seen used in messaging systems. Uses my [progressively enhanced HTML accordion](https://adrianroselli.com/2023/08/progressively-...

Was immer schon genervt hat, nervt jetzt nur noch mehr: wenn man mehrere Konten hat, muss man sich ständig mit sämtlichen Überprüfungen ein und wieder ausloggen und wieder einloggen und wieder ausloggen. Warum diese App einfach nicht alle Konten verwalten kann, bleibt ein Rätsel.
https://mastodon.social/@mobiFlip/1146…

RSS RESURGENCE IN 2025 PLEASE!

Der @… hat gerade auf #NDRInfo eine rechtsstaatsfeindliche und europareichtsfeindliche Haltung aus der NZZ eine Bühne gegeben. Mir ist sofort schlecht geworden. Ich könnte kotzen. Da setzen sich Politiker über geltende Gesetze hinweg, zerstören die Freiheit und den Zusammenhalt in …

Wild @… and @… to be spotted too :D https://mastodon.social/@am…

This graphic showing that Cursor now has the majority market share over GitHub Copilot is fascinating. I’m curious if it’s because Cursor is an individual’s tool (so people are spending their own money). In contrast, GitHub Copilot is an enterprise tool (your corporate sugar daddy typically buys it for you).

Wie geht es jetzt weiter? Mein Plan ist, nächstes Wochenende am #reflab Festival in #Zürich teilzunehmen (https://reflab-festival.ch/

It's interesting how much Wikipedia's list of LLM catchphrases comes straight out of academic writing jargon.
Probably as a lot of the corpus that was mined for the LLM training goes back to the academic literature thanks to Sci-Hub et al.
https://en.wikipedia.org/wiki/Wikipedia:WikiProject_AI_Cleanup/AI_catchphrases#Language_and_tone

Another casualty of Mayor Lurie’s last-minute micromanagement in adding a left turn phase to Valencia at 17th, 21st and 23rd: The signals have lost their leading pedestrian intervals.
LPIs improve safety by letting peds/bikes go first, with 3-7sec of walk light before green light. Just added a few years ago as a state-funded safety improvement, they’re gone now.

Maximally recoverable codes with locality and availability
Umberto Mart\'inez-Pe\~nas, V. Lalitha
https://arxiv.org/abs/2505.24573 https://

Maximally recoverable codes with locality and availability
In this work, we introduce maximally recoverable codes with locality and availability. We consider locally repairable codes (LRCs) where certain subsets of $ t $ symbols belong each to $ N $ local repair sets, which are pairwise disjoint after removing the $ t $ symbols, and which are of size $ r+δ-1 $ and can correct $ δ-1 $ erasures locally. Classical LRCs with $ N $ disjoint repair sets and LRCs with $ N $-availability are recovered when setting $ t = 1 $ and $ t=δ-1=1 $, respectively. Al…

[2025-08-01 Fri (UTC), 1 new article found for math-ph Mathematical Physics]
toXiv_bot_toot

Prévoir un allongement de temps de trajet de 20 minutes environ pour le train suivant : - KUMO départ de Paris Gare de Lyon Š 08h46, arrivée Š Montereau 09h44.
Pour plus d'informations sur cette perturbation, consultez le fil Twitter de la ligne.
Motif : acte de vandalisme Š bord du train (intervention des forces de l'ordre).
🤖 01/09 09:31

On Mitigating Data Sparsity in Conversational Recommender Systems
Sixiao Zhang, Mingrui Liu, Cheng Long, Wei Yuan, Hongxu Chen, Xiangyu Zhao, Hongzhi Yin
https://arxiv.org/abs/2507.00479

On Mitigating Data Sparsity in Conversational Recommender Systems
Conversational recommender systems (CRSs) capture user preference through textual information in dialogues. However, they suffer from data sparsity on two fronts: the dialogue space is vast and linguistically diverse, while the item space exhibits long-tail and sparse distributions. Existing methods struggle with (1) generalizing to varied dialogue expressions due to underutilization of rich textual cues, and (2) learning informative item representations under severe sparsity. To address these …

What? I did exactly what you asked.

@CoMaps@floss.social
The settings offer the option to use ‘Google Fused Location Services’. I assume this is so that this Google service can still be used even if it is disabled in the Android settings. @… offers an alternative #locationService

Fragile Tresor gut schützen.

Multi-Waveguide Pinching Antennas for ISAC
Weihao Mao, Yang Lu, Yanqing Xu, Bo Ai, Octavia A. Dobre, Dusit Niyato
https://arxiv.org/abs/2505.24307 https://…

Multi-Waveguide Pinching Antennas for ISAC
Recently, a novel flexible-antenna technology, called pinching antennas, has attracted growing academic interest. By inserting discrete dielectric materials, pinching antennas can be activated at arbitrary points along waveguides, allowing for flexible customization of large-scale path loss. This paper investigates a multi-waveguide pinching-antenna integrated sensing and communications (ISAC) system, where transmit pinching antennas (TPAs) and receive pinching antennas (RPAs) coordinate to sim…

Replaced article(s) found for math-ph. https://arxiv.org/list/math-ph/new
[1/1]:
- Correlation functions for open XXZ spin 1/2 quantum chains with unparallel boundary magnetic fields
G. Niccoli, V. Terras

Risque de forte affluence Š bord du train. Le train suivant passe de long Š court : - GAME, départ Paris Gare de Lyon 17h32, arrivée Montargis 18h56.
Motif : indisponibilité du matériel.
🤖 01/09 16:54

Microsoft says it agreed to give the US GSA $6B in potential savings on Office, Azure, 365, and other tools over three years, including $3.1B in the first year (Jordan Novet/CNBC)
https://www.cnbc.com/2025/09/02/microsoft-offers-us-…

Microsoft offers U.S. government over $6 billion in savings on cloud services over 3 years
Microsoft is the latest company to discount the cost of its software to the General Services Administration.

@… ooh, I like that thought!

8 killed, injured in Russian attacks on Ukraine over past day: https://benborges.xyz/2025/09/02/killed-injured-in-russian-attacks.html

Unions are challenged with protecting their members from the Trump Administration's immigration raids, cuts in Medicaid services and a weakened National Labor Relations Board.
In June, tens of thousands of demonstrators showed up for "No Kings" protests across Southern California.
Now union organizers have put together the nationwide protest
"Workers over Billionaires,"
calling it a "refusal to let billionaires slash care, scapegoat immigran…

Cryptocurrency fraud ring busted in Spain after laundering $540 million, Europol says
https://www.reuters.com/business/finance/cryptocurrency-fraud-ring-busted-spain-after-laundering-540-million-europol-says…

Zohran said “Billionaires should not exist” and it’s like, dude, I’ve already got an erection because of you are you trying to make me love you even harder!?

Der NRW-Lokalwahlkampf erreicht mich durch SPD-Videos auf TikTok, bei denen an verschiedenen Orten im Rhein-Sieg-Kreis (Hennef, St. Augustin) eine „Dönerpreisbremse“ auf einen Preis von 3 € (nur bei einem Dönerladen und nur an einem Tag, limitiert auf 200 Döner) versprochen wird. Ich finde das sehr sozialdemokratisch: Ein Problem, was die Menschen berührt (Dönerpreis) wird aufgegriffen und in einer symbolischen Aktion nicht wirklich gelöst, weil man ja leider an den Ursachen nichts ändern ka…

Rydberg Atomic Receivers for Multi-Band Communications and Sensing
Mingyao Cui, Qunsong Zeng, Zhanwei Wang, Kaibin Huang
https://arxiv.org/abs/2505.24168 h…

Rydberg Atomic Receivers for Multi-Band Communications and Sensing
Harnessing multi-level electron transitions, Rydberg Atomic Receivers (RAREs) can detect wireless signals across a wide range of frequency bands, from Megahertz to Terahertz, enabling multi-band communications and sensing (C&S). Current research on multi-band RAREs primarily focuses on experimental demonstrations, lacking an interpretable model to mathematically characterize their mechanisms. This issue leaves the multi-band RARE as a black box, posing challenges in its practical C&S applicatio…

Teaching a Language Model to Speak the Language of Tools
Simeon Emanuilov
https://arxiv.org/abs/2506.23394 https://arxiv.org/pdf/2506…

Teaching a Language Model to Speak the Language of Tools
External tool integration through function-calling is essential for practical language model applications, yet most multilingual models lack reliable tool-use capabilities in non-English languages. Even state-of-the-art multilingual models struggle with determining when to use tools and generating the structured outputs required for function calls, often exhibiting language confusion when prompted in lower-resource languages. This work presents a methodology for adapting existing language model…

Départ différé de 10 minutes pour le train suivant : -KUMO, départ Paris Gare de Lyon 15h46, passage Moret-Veneux-les-Sablons 16h32, arrivée Montereau 16h44.
Pour plus d'informations sur cette perturbation, consultez le fil X de la ligne R.
Motif : conditions de départ non réunies.
🤖 01/09 15:59

Fragile Tresor gut schützen.

Filing: Klarna and some shareholders are selling 34.3M shares for $35 to $37 each, aiming to raise up to $1.27B and giving it an up to ~$14B market cap (Matthew Griffin/Bloomberg)
https://www.bloomberg.com/news/articles/2025-09…

thinking about a new 11ty mascot as I work on some slides this morning

Bounds on the Excess Minimum Risk via Generalized Information Divergence Measures
Ananya Omanwar, Fady Alajaji, Tam\'as Linder
https://arxiv.org/abs/2505.24117

Bounds on the Excess Minimum Risk via Generalized Information Divergence Measures
Given finite-dimensional random vectors $Y$, $X$, and $Z$ that form a Markov chain in that order (i.e., $Y \to X \to Z$), we derive upper bounds on the excess minimum risk using generalized information divergence measures. Here, $Y$ is a target vector to be estimated from an observed feature vector $X$ or its stochastically degraded version $Z$. The excess minimum risk is defined as the difference between the minimum expected loss in estimating $Y$ from $X$ and from $Z$. We present a family of …

Learning to Rank with Variable Result Presentation Lengths
Norman Knyazev, Harrie Oosterhuis
https://arxiv.org/abs/2506.23319 https://

Learning to Rank with Variable Result Presentation Lengths
Learning to Rank (LTR) methods generally assume that each document in a top-K ranking is presented in an equal format. However, previous work has shown that users' perceptions of relevance can be changed by varying presentations, i.e., allocating more vertical space to some documents to provide additional textual or image information. Furthermore, presentation length can also redirect attention, as users are more likely to notice longer presentations when scrolling through results. Deciding on …

Période : Š partir de 21h55.
Dates : en semaine, du lundi 01 septembre au vendredi 03 octobre.
Le trafic est interrompu entre Paris Gare de Lyon et Montargis.
Un service de bus de remplacement est mis en place, avec desserte des gares intermédiaires.
Les horaires du calculateur d'itinéraire tiennent compte des travaux.
Motif : travaux sur le réseau ferroviaire.
#Info_Travaux

Countries on track to eliminate cervical cancer:
-Australia by 2028
-Sweden by 2027
-Rwanda by 2030
-UK by 2040
-Indonesia by 2030
-Bhutan 2030
-El Salvador by 2030
-Canada by 2040
How? HPV vaccine. Same one RFK Jr is trying to ban.
You will note USA is not on this list.
https://…

Amid Russian economy warnings, Lavrov says NATO's increased defense spending will lead to 'collapse' of alliance: https://benborges.xyz/2025/06/30/amid-russian-economy-warnings-lavrov.html

[2025-06-02 Mon (UTC), 5 new articles found for cs.IT Information Theory]
#toXiv_bot_toot

Impact of Shallow vs. Deep Relevance Judgments on BERT-based Reranking Models
Gabriel Iturra-Bocaz, Danny Vo, Petra Galuscakova
https://arxiv.org/abs/2506.23191

Impact of Shallow vs. Deep Relevance Judgments on BERT-based Reranking Models
This paper investigates the impact of shallow versus deep relevance judgments on the performance of BERT-based reranking models in neural Information Retrieval. Shallow-judged datasets, characterized by numerous queries each with few relevance judgments, and deep-judged datasets, involving fewer queries with extensive relevance judgments, are compared. The research assesses how these datasets affect the performance of BERT-based reranking models trained on them. The experiments are run on the M…

Période : Š partir de 21h50.
Dates : du lundi 01 septembre au vendredi 03 octobre sauf les weeks-end
Le trafic est interrompu entre Montereau et Melun via Moret Veneux les S. Un service de bus de remplacement est mis en place, avec desserte des gares intermédiaires.
Les trains entre Paris Gare de Lyon et Montereau desserviront la gare de Melun et Champagne sur Seine.
Les horaires du calculateur d'itinéraire tiennent compte des travaux.
Motif : travaux sur le …

Sources: OpenAI is scouting local partners to set up a 1GW data center in India, although the exact timeline is unclear; Sam Altman is set to visit this month (Bloomberg)
https://www.bloomberg.com/news/articles/2025-09-01/openai-…

A controversial new book:
"We are eating the Earth"
says excess carbon dioxide in the atmosphere is a long-term challenge resulting from an otherwise cheerful story,
in which more people live better lives with fuller bellies and bigger dreams.
Lawyer-turned-science-cop Tim Searchinger discovered that the popular carbon solution of 20 years ago,
-- plant-based biofuels,
-- was a disaster in the making.
His insight: Land used to grow fuel w…

There’s new hope that humans will save our planet
‘We Are Eating the Earth,’ argues for producing more food on less land to avert climate crisis.

This https://arxiv.org/abs/2504.18022 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIT_…

Iterative Joint Detection of Kalman Filter and Channel Decoder for Sensor-to-Controller Link in Wireless Networked Control Systems
In this letter, we propose an iterative joint detection algorithm of Kalman filter (KF) and channel decoder for the sensor-to-controller link of wireless networked control systems, which utilizes the prior information of control system to improve control and communication performance. In this algorithm, we first use the KF to estimate the probability density of the control system outputs and calculate the prior probability of received signals to assist decoder. Then, the possible outputs of the…

Compositions of Variant Experts for Integrating Short-Term and Long-Term Preferences
Jaime Hieu Do, Trung-Hoang Le, Hady W. Lauw
https://arxiv.org/abs/2506.23170

Compositions of Variant Experts for Integrating Short-Term and Long-Term Preferences
In the online digital realm, recommendation systems are ubiquitous and play a crucial role in enhancing user experience. These systems leverage user preferences to provide personalized recommendations, thereby helping users navigate through the paradox of choice. This work focuses on personalized sequential recommendation, where the system considers not only a user's immediate, evolving session context, but also their cumulative historical behavior to provide highly relevant and timely recommen…

Période : en semaine dès 21h45.
Dates : du lundi 01 au vendredi 26 septembre.
Tous les trains de la ligne R au départ de Paris Lyon pour Montereau sont sans arrêt jusqu'Š la gare de Champagne-sur-Seine, puis directs jusqu'Š leur terminus Montereau.
Les horaires du calculateur d'itinéraire tiennent compte des travaux.
Motif : travaux sur le réseau ferroviaire.
#Info_Travaux

Ukrainian "Flamingo" hits Crimea. A new zxis of dictators: https://benborges.xyz/2025/09/01/ukrainian-quotflamingoquot-hits-crimea-a.html

China accuses the US of exploiting an old Microsoft Exchange flaw to control a key Chinese defense company's servers for nearly a year and steal military data (Bloomberg)
https://www.bloomberg.com/news/articles/2025-08-01…

This https://arxiv.org/abs/2407.18929 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIT_…

Disturbance-based Discretization, Differentiable IDS Channel, and an IDS-Correcting Code for DNA Storage
Insertion, deletion, and substitution (IDS) error-correcting codes have garnered increased attention with recent advancements in DNA storage technology. However, a universal method for designing tailored IDS-correcting codes across varying channel settings remains underexplored. We present an autoencoder-based approach, THEA-code, aimed at efficiently generating IDS-correcting codes for complex IDS channels. In the work, a disturbance-based discretization is proposed to discretize the features …

Multi-task Offline Reinforcement Learning for Online Advertising in Recommender Systems
Langming Liu, Wanyu Wang, Chi Zhang, Bo Li, Hongzhi Yin, Xuetao Wei, Wenbo Su, Bo Zheng, Xiangyu Zhao
https://arxiv.org/abs/2506.23090

Multi-task Offline Reinforcement Learning for Online Advertising in Recommender Systems
Online advertising in recommendation platforms has gained significant attention, with a predominant focus on channel recommendation and budget allocation strategies. However, current offline reinforcement learning (RL) methods face substantial challenges when applied to sparse advertising scenarios, primarily due to severe overestimation, distributional shifts, and overlooking budget constraints. To address these issues, we propose MTORL, a novel multi-task offline RL model that targets two key…

Période : en semaine de 10h26 Š 15h30.
Dates : du lundi 01 au vendredi 19 septembre.
Le trafic est interrompu entre Melun et Montereau via Héricy.
Un service de bus de remplacement est mis en place, avec desserte des gares intermédiaires.
Les horaires du calculateur d'itinéraire tiennent compte des travaux.
Motif : travaux sur le réseau ferroviaire.
#Info_Travaux

Russian forces allegedly preparing major assault toward Siversk in Donetsk Oblast, Ukraine's military says: https://benborges.xyz/2025/09/01/russian-forces-allegedly-preparing-major.html

Mathematicians are excited about how Cairo’s work will inspire new research. “I am certain that, from now on, whenever we come upon a problem of similar flavor, we will try to test it against Cairo-like constructions,” Oliveira said.
He and others in the harmonic analysis community will also have to reckon with a changed landscape.
In harmonic analysis, there’s a constellation of questions about how the energy of a wave concentrates.
If a conjecture known as Stein’s conje…

At 17, Hannah Cairo Solved a Major Math Mystery | Quanta Magazine
After finding the homeschooling life confining, the teen petitioned her way into a graduate class at Berkeley, where she ended up disproving a 40-year-old conjecture.

This https://arxiv.org/abs/2403.11436 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIT_…

Deep Holes of Twisted Reed-Solomon Codes
The deep holes of a linear code are the vectors that achieve the maximum error distance (covering radius) to the code. {Determining the covering radius and deep holes of linear codes is a fundamental problem in coding theory. In this paper, we investigate the problem of deep holes of twisted Reed-Solomon codes.} The covering radius and a standard class of deep holes of twisted Reed-Solomon codes ${\rm TRS}_k(\mathcal{A}, θ)$ are obtained for a general evaluation set $\mathcal{A} \subseteq \mat…

Enhancing Live Broadcast Engagement: A Multi-modal Approach to Short Video Recommendations Using MMGCN and User Preferences
Saeid Aghasoleymani Najafabadi
https://arxiv.org/abs/2506.23085

Enhancing Live Broadcast Engagement: A Multi-modal Approach to Short Video Recommendations Using MMGCN and User Preferences
The purpose of this paper is to explore a multi-modal approach to enhancing live broadcast engagement by developing a short video recommendation system that incorporates Multi-modal Graph Convolutional Networks (MMGCN) with user preferences. In order to provide personalized recommendations tailored to individual interests, the proposed system takes into account user interaction data, video content features, and contextual information. With the aid of a hybrid approach combining collaborative fi…

Le train suivant voit son départ différé de 45 minutes environ :
- KUMO départ de Paris Gare de Lyon Š 08h46, arrivée Š Montereau 09h44.
Pour plus d'informations sur cette perturbation, consultez le fil Twitter de la ligne.
Motif : malaise voyageur Š bord du train.
🤖 02/09 09:22

Circle applies for a US national trust bank license, which would let it act as a custodian for its own reserves and hold crypto for its institutional clients (Hannah Lang/Reuters)
https://www.reuters.com/sustainability/boa

This https://arxiv.org/abs/2301.10980 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIT_…

Beyond scalar quasi-arithmetic means: Quasi-arithmetic averages and quasi-arithmetic mixtures in information geometry
We generalize quasi-arithmetic means beyond scalars by considering the gradient map of a Legendre type real-valued function. The gradient map of a Legendre type function is proven strictly comonotone with a global inverse. It thus yields a generalization of strictly mononotone and differentiable functions generating scalar quasi-arithmetic means. Furthermore, the Legendre transformation gives rise to pairs of dual quasi-arithmetic averages via the convex duality. We study the invariance and equ…

Synergizing Implicit and Explicit User Interests: A Multi-Embedding Retrieval Framework at Pinterest
Zhibo Fan, Hongtao Lin, Haoyu Chen, Bowen Deng, Hedi Xia, Yuke Yan, James Li
https://arxiv.org/abs/2506.23060

Synergizing Implicit and Explicit User Interests: A Multi-Embedding Retrieval Framework at Pinterest
Industrial recommendation systems are typically composed of multiple stages, including retrieval, ranking, and blending. The retrieval stage plays a critical role in generating a high-recall set of candidate items that covers a wide range of diverse user interests. Effectively covering the diverse and long-tail user interests within this stage poses a significant challenge: traditional two-tower models struggle in this regard due to limited user-item feature interaction and often bias towards t…

Le train suivant voit sa composition modifiée et passe de long Š court :
- GAMO départ départ Paris Gare de Lyon 09h16, arrivée Montargis 10h55.
🤖 02/09 09:11

Sources: xAI is launching a $300M secondary stock offering that values the group at $113B, allowing staff to sell shares to new investors (Financial Times)
https://www.ft.com/content/703e93f1-28bf-4890-8c9c-141bf81dd206

Elon Musk’s xAI seeks $113bn valuation in $300mn share sale
Deal to allow investors to buy into group following March takeover of X

Machine Assistant with Reliable Knowledge: Enhancing Student Learning via RAG-based Retrieval
Yongsheng Lian
https://arxiv.org/abs/2506.23026 https://

Machine Assistant with Reliable Knowledge: Enhancing Student Learning via RAG-based Retrieval
We present Machine Assistant with Reliable Knowledge (MARK), a retrieval-augmented question-answering system designed to support student learning through accurate and contextually grounded responses. The system is built on a retrieval-augmented generation (RAG) framework, which integrates a curated knowledge base to ensure factual consistency. To enhance retrieval effectiveness across diverse question types, we implement a hybrid search strategy that combines dense vector similarity with sparse…

Le train suivant voit son départ différé de 25 minutes environ :
- KUMO départ de Paris Gare de Lyon Š 08h46, arrivée Š Montereau 09h44.
Pour plus d'informations sur cette perturbation, consultez le fil Twitter de la ligne.
Motif : malaise voyageur Š bord du train.
🤖 02/09 09:00

Interact2Vec -- An efficient neural network-based model for simultaneously learning users and items embeddings in recommender systems
Pedro R. Pires, Tiago A. Almeida
https://arxiv.org/abs/2506.22648

Interact2Vec -- An efficient neural network-based model for simultaneously learning users and items embeddings in recommender systems
Over the past decade, recommender systems have experienced a surge in popularity. Despite notable progress, they grapple with challenging issues, such as high data dimensionality and sparseness. Representing users and items as low-dimensional embeddings learned via neural networks has become a leading solution. However, while recent studies show promising results, many approaches rely on complex architectures or require content data, which may not always be available. This paper presents Intera…

SoftBank and Intel form Saimemory, a new company to develop stacked DRAM memory chips for AI that consume ~50% of the power of current HBM in the next two years (Nikkei Asia)
https://asia.nikkei.com/Business/Tech/

SoftBank, Intel work on AI memory chips that use half as much power
Japanese tech investor sets sights on domestic data centers with $70m project

[2025-07-01 Tue (UTC), 12 new articles found for cs.IR Information Retrieval]
toXiv_bot_toot

Act-With-Think: Chunk Auto-Regressive Modeling for Generative Recommendation
Yifan Wang, Weinan Gan, Longtao Xiao, Jieming Zhu, Heng Chang, Haozhao Wang, Rui Zhang, Zhenhua Dong, Ruiming Tang, Ruixuan Li
https://arxiv.org/abs/2506.23643

Act-With-Think: Chunk Auto-Regressive Modeling for Generative Recommendation
Generative recommendation (GR) typically encodes behavioral or semantic aspects of item information into discrete tokens, leveraging the standard autoregressive (AR) generation paradigm to make predictions. However, existing methods tend to overlook their intrinsic relationship, that is, the semantic usually provides some reasonable explainability "$\textbf{why}$" for the behavior "$\textbf{what}$", which may constrain the full potential of GR. To this end, we present Chunk AutoRegressive Model…

NaviX: A Native Vector Index Design for Graph DBMSs With Robust Predicate-Agnostic Search Performance
Gaurav Sehgal, Semih Salihoglu
https://arxiv.org/abs/2506.23397

NaviX: A Native Vector Index Design for Graph DBMSs With Robust Predicate-Agnostic Search Performance
There is an increasing demand for extending existing DBMSs with vector indices so that they become unified systems capable of supporting modern predictive applications, which require joint querying of vector embeddings together with the structured properties and connections of objects. We present NaviX, a native vector index for graph DBMSs (GDBMSs) that has two main design goals. First, we aim to implement a disk-based vector index that leverages the core storage and query-processing capabilit…

Replaced article(s) found for cs.IR. https://arxiv.org/list/cs.IR/new
[1/1]:
- A Pre-trained Sequential Recommendation Framework: Popularity Dynamics for Zero-shot Transfer
Junting Wang, Praneet Rathi, Hari Sundaram

Replaced article(s) found for cs.IR. https://arxiv.org/list/cs.IR/new
[1/1]:
- Towards Competitive Search Relevance For Inference-Free Learned Sparse Retrievers
Zhichao Geng, Yiwen Wang, Dongyu Ru, Yang Yang

WebArXiv: Evaluating Multimodal Agents on Time-Invariant arXiv Tasks
Zihao Sun, Meng Fang, Ling Chen
https://arxiv.org/abs/2507.00938 https://

WebArXiv: Evaluating Multimodal Agents on Time-Invariant arXiv Tasks
Recent progress in large language models (LLMs) has enabled the development of autonomous web agents capable of navigating and interacting with real websites. However, evaluating such agents remains challenging due to the instability and inconsistency of existing benchmarks, which often rely on dynamic content or oversimplified simulations. In this work, we introduce WebArXiv, a static and time-invariant benchmark comprising 275 web-based tasks grounded in the arXiv platform. WebArXiv ensures r…

EARN: Efficient Inference Acceleration for LLM-based Generative Recommendation by Register Tokens
Chaoqun Yang, Xinyu Lin, Wenjie Wang, Yongqi Li, Teng Sun, Xianjing Han, Tat-Seng Chua
https://arxiv.org/abs/2507.00715

EARN: Efficient Inference Acceleration for LLM-based Generative Recommendation by Register Tokens
Large Language Model-based generative recommendation (LLMRec) has achieved notable success, but it suffers from high inference latency due to massive computational overhead and memory pressure of KV Cache. Existing KV Cache reduction methods face critical limitations: cache compression offers marginal acceleration given recommendation tasks' short decoding steps, while prompt compression risks discarding vital interaction history. Through systematic analysis of attention patterns in LLMRec, we …

Reliable Annotations with Less Effort: Evaluating LLM-Human Collaboration in Search Clarifications
Leila Tavakoli, Hamed Zamani
https://arxiv.org/abs/2507.00543

Reliable Annotations with Less Effort: Evaluating LLM-Human Collaboration in Search Clarifications
Despite growing interest in using large language models (LLMs) to automate annotation, their effectiveness in complex, nuanced, and multi-dimensional labelling tasks remains relatively underexplored. This study focuses on annotation for the search clarification task, leveraging a high-quality, multi-dimensional dataset that includes five distinct fine-grained annotation subtasks. Although LLMs have shown impressive capabilities in general settings, our study reveals that even state-of-the-art m…

Rethinking Group Recommender Systems in the Era of Generative AI: From One-Shot Recommendations to Agentic Group Decision Support
Dietmar Jannach, Amra Deli\'c, Francesco Ricci, Markus Zanker
https://arxiv.org/abs/2507.00535

Rethinking Group Recommender Systems in the Era of Generative AI: From One-Shot Recommendations to Agentic Group Decision Support
More than twenty-five years ago, first ideas were developed on how to design a system that can provide recommendations to groups of users instead of individual users. Since then, a rich variety of algorithmic proposals were published, e.g., on how to acquire individual preferences, how to aggregate them, and how to generate recommendations for groups of users. However, despite the rich literature on the topic, barely any examples of real-world group recommender systems can be found. This lets u…

\texttt{WebANNS}: Fast and Efficient Approximate Nearest Neighbor Search in Web Browsers
Mugeng Liu, Siqi Zhong, Qi Yang, Yudong Han, Xuanzhe Liu, Yun Ma
https://arxiv.org/abs/2507.00521

\texttt{WebANNS}: Fast and Efficient Approximate Nearest Neighbor Search in Web Browsers
Approximate nearest neighbor search (ANNS) has become vital to modern AI infrastructure, particularly in retrieval-augmented generation (RAG) applications. Numerous in-browser ANNS engines have emerged to seamlessly integrate with popular LLM-based web applications, while addressing privacy protection and challenges of heterogeneous device deployments. However, web browsers present unique challenges for ANNS, including computational limitations, external storage access issues, and memory utiliz…

MassTool: A Multi-Task Search-Based Tool Retrieval Framework for Large Language Models
Jianghao Lin, Xinyuan Wang, Xinyi Dai, Menghui Zhu, Bo Chen, Ruiming Tang, Yong Yu, Weinan Zhang
https://arxiv.org/abs/2507.00487

MassTool: A Multi-Task Search-Based Tool Retrieval Framework for Large Language Models
Tool retrieval is a critical component in enabling large language models (LLMs) to interact effectively with external tools. It aims to precisely filter the massive tools into a small set of candidates for the downstream tool-augmented LLMs. However, most existing approaches primarily focus on optimizing tool representations, often neglecting the importance of precise query comprehension. To address this gap, we introduce MassTool, a multi-task search-based framework designed to enhance both qu…

[2025-07-02 Wed (UTC), 8 new articles found for cs.IR Information Retrieval]
toXiv_bot_toot