Tootfinder

In #Slowenien und #Kroatien ist die #Bahn noch günstig: von Rijeka bis zur österreichischen Grenze um € 14,80 - inklusive natürlicher Klimaanlage: es gab im D Zug noch Waggons mit öffenbaren Fenstern zum Rausguc…

Dem Elefanten fehlt jetzt ein Stosszahn. Ein teures Lehrlingslager für den Strassenbaubetrieb… und wer sass am Steuer des Dumpers?
#Kinderzoo #Rapperswil #haftpflicht

Anzahl der installierten #Windkraftanlagen pro Jahr in Deutschland mit Stand vom 26.07.2025.
Zählung der Anlagen mit Inbetriebnahmedatum. Der aktuelle Betriebsstatus wird nicht berücksichtigt.
Der Datenbestand enthält ggf. unplausible Datensätze.
Anmerkung: Erster Versuch einer #Datenanalyse

This is the extremely rare Parachute penstemon, only found in a small area in northern Colorado, USA.
This penstemon grows on steep shale fields at 7,800 to 9,200 feet elevation. The flower blooms from about mid-June to mid-July each year.
Photo: CPW/Raquel Wertsbaugh
#Flower #Rare

Ik kook tegenwoordig meer en meer antika, wat in dit geval inhoudt dat ik extra knoflook, gember, kunjit en iets chili aan de Thaise restjesnasi toevoeging. Nifs vervelends aan dus.

Wenn’s draußen friert: Uschi, die Katze, kuschelt mit der warmen Heizung... 😊
#Caturdayeveryday #Uschi #Caturday

Heute vor 51 Jahren: Am 26. September 1974 testen die #USA die Atombombe "Trumbull". Die Operation Bedrock war eine Serie von 27 US-amerikanischen #Kernwaffentests, die 1974/75 auf der Nevada Test Site in Nevada unterirdisch durchgeführt wurde.

Rule of thumb:
Anytime you see the term "vibe shift", replace it in your mind with "dead internet".
https://gizmodo.com/cracker-barrel-outrage-was-almost-certainly-driven-by-bots-researchers-say-20…

Cracker Barrel Outrage Was Almost Certainly Driven by Bots, Researchers Say
Doesn't that make more sense than lots of people caring about Cracker Barrel?

Gaat het mes in verplichte cookies? ‘Niemand leest die banners’ | Economie | De Stentor.nl
https://www.ad.nl/economie/gaat-het-mes-in-verplichte-cookies-niemand-leest-die-banners~a6f3eb71/
Dat zou mooi zijn!! Hopelijk dat

In Mecklenburg-Vorpommern erzielt die AfD so viele Stimmen, wie SPD, CDU und Grünen zusammen. Eine Regierungsbildung ist kaum denkbar. Die CDU müsste sich bewegen, um auf die Linke zuzugehen.

So, jetzt hätte ich fast die #Hütte angezündet 🔥.
Bin vom Einkaufen nach Hause gekommen, habe den gut befüllten #Rucksack auf den #Herd gestellt, weg um die Schuhe auszuziehen, komme zurück und es raucht und st…

Good reminder, for all your coffee needs, including accessories, Edmonton-based Rogue Wave
#BuyCanadian

"Darüber ist jedoch der Gedanke verloren gegangen, dass Menschen – hört, hört – ab und an auch selbst Verantwortung tragen für Lebensentscheidungen, die sie an den einen oder anderen Punkt geführt haben. Aus dieser Verantwortung erwachsen womöglich auch einmal unschöne Konsequenzen." Wie wahr!
Zunehmend viele Menschen wollen keine Verantwortung für die Konsequenzen ihres Handelns übernehmen und wollen das auf den Staat abschieben - so geht das nicht!

Schwarz-rote Denkblockaden: Diese Koalition ist eine Gefahr für den Sozialstaat
Bei Schwarz-Rot herrscht Kommissionitis statt Tatendrang. Wenn aus dem Herbst der Reformen etwas werden soll, müssen Union wie SPD eigene Glaubenssätze dem Realitätscheck unterziehen.

Macht mit bei der Last-Minute-Mobilisierung zur Demo gegen die rassistische Hetze des Bundeskanzlers!
Aufruf vom @…: https://fedifreu.de/@bie_buendnis_gege

Empowering Computing Education Researchers Through LLM-Assisted Content Analysis
Laurie Gale, Sebastian Mateos Nicolajsen
https://arxiv.org/abs/2508.18872 https://

Empowering Computing Education Researchers Through LLM-Assisted Content Analysis
Computing education research (CER) is often instigated by practitioners wanting to improve both their own and the wider discipline's teaching practice. However, the latter is often difficult as many researchers lack the colleagues, resources, or capacity to conduct research that is generalisable or rigorous enough to advance the discipline. As a result, research methods that enable sense-making with larger volumes of qualitative data, while not increasing the burden on the researcher, have sign…

#update #Mastodon

"Was mich an der Sauce erstaunt hat, ist ihre Farbe von eher #Trump als Tomaten."
Uschi Ronnenberg
#Zitate
#Aufgelesen

Pastasauce mit gerösteten Tomaten
Eine feine, leichte Sache!

LLM-Guided Genetic Improvement: Envisioning Semantic Aware Automated Software Evolution
Karine Even-Mendoza, Alexander Brownlee, Alina Geiger, Carol Hanna, Justyna Petke, Federica Sarro, Dominik Sobania
https://arxiv.org/abs/2508.18089

LLM-Guided Genetic Improvement: Envisioning Semantic Aware Automated Software Evolution
Genetic Improvement (GI) of software automatically creates alternative software versions that are improved according to certain properties of interests (e.g., running-time). Search-based GI excels at navigating large program spaces, but operates primarily at the syntactic level. In contrast, Large Language Models (LLMs) offer semantic-aware edits, yet lack goal-directed feedback and control (which is instead a strength of GI). As such, we propose the investigation of a new research line on AI-p…

The degrees of freedom of multiway junctions in three dimensional gravity
Avik Chakraborty, Tanay Kibe, Mart\'in Molina, Ayan Mukhopadhyay, Giuseppe Policastro
https://arxiv.org/abs/2509.20437

The degrees of freedom of multiway junctions in three dimensional gravity
We demonstrate that $n$-way junctions in three dimensional gravity correspond to coupled $n-1$ strings each satisfying the Nambu-Goto equation in the smoothened background, and with sources consisting of Monge-Ampère like terms which couple the strings. For $n\geq 3$, these $n-1$ degrees of freedom survive the tensionless limit implying that matter-like behavior can arise out of $pure$ gravity. We interpret these stringy degrees of freedom of gravitational junctions holographically in terms of…

Heute vor 53 Jahren: Am 26.09.1972 zündeten die USA im Rahmen von Operation Toggle die Atombombe "Delphinium". Toggle war eine Serie von #Kernwaffentests bei der 72/73 insgesamt 35 Bomben größtenteils im Testgebiet in #Nevada und Rio Blanco unterirdisch gezündet wurden.

No, it's not DNS! It can't be!

Replaced article(s) found for cs.IR. https://arxiv.org/list/cs.IR/new
[1/1]:
- LLM4MSR: An LLM-Enhanced Paradigm for Multi-Scenario Recommendation
Yuhao Wang, Yichao Wang, Zichuan Fu, Xiangyang Li, Xiangyu Zhao, Huifeng Guo, Ruiming Tang

Bei der US-Tochter von #Allianz wurden durch einen #Cyberangriff Mitte Juli 2025 personenbezogene Daten von Kunden, Beratern und Mitarbeitenden kompromittiert.
Betroffen sein könnten über eine Million Versicherte. Der Zugriff erfolgte über ein Drittanbietersystem mittels

Lebensversicherung: Allianz Life - Hacker stehlen Daten der meisten Kunden - Golem.de
Die US-Tochter der Allianz bestätigt einen Cyberangriff auf ihre Kundendatenbank. Über eine Million Versicherte könnten betroffen sein.

tonight at #reeperbahnfestival i shook hands with laurie anderson, and i do admit i am a bit star struck.
i was also amazed by every artist at the #AnchorAward ! #RIPmagic were …

🇨🇭 🇨🇭 🇨🇭 🇨🇭 🇨🇭
Mir sind 50 Millionen zuwenig.
Millionäre sind nicht das Problem.
Es sind die Milliardäre, die wir uns schlicht nicht leisten können.
Aber wenn die Juso-Initiative wirklich so abschifft, finde ich das als Signal voll schlecht.
https://www.srf.ch/n…

Abstimmungen vom 30.11.2025: 1. SRG-Umfrage zur Erbschaftssteuer
Wäre im Oktober über die Erbschaftssteuer-Initiative abgestimmt worden, wäre sie deutlich bachab geschickt worden.

Estimating the Local Hubble Parameter from the Thermal Evolution of Earth and Mars
Yurii V. Dumin, Elizaveta G. Khramova, Ludmila M. Svirskaya, Eugen S. Savinykh
https://arxiv.org/abs/2508.16694

Estimating the Local Hubble Parameter from the Thermal Evolution of Earth and Mars
The problem of local (e.g., interplanetary) Hubble expansion is studied for a long time but remains a controversial subject till now; and of particular interest is a plausible value of the local Hubble parameter at the scale of the Solar system. Here, we tried to estimate the corresponding quantity by the analysis of surface temperatures on the Earth and Mars, which are formed by a competition between a variable luminosity of the Sun and increasing radii of the planetary orbits. Our work employ…

Bei meiner ersten Gruppenwanderung war ich mit 99 Personen unterwegs - ein ganz anderes Erlebnis als zu zweit oder zu dritt, eben weil es ein Gruppenerlebnis war. Sogar ein Minihund mi dünnen, kurzen Beinchen war damals mitgewandert. Es war grandios.
Habe das heute wiederholt, war aber so la la. Aber die Strecke war wunderbar - wie immer in der Heide.
UND wir haben Heidschnucken getroffen.
#wandern

Well well well. Organizing works. They will hold off on rewriting that part of tenant laws
There’s a lot more shit coming down the pipe from the conservatives but I’ll take that win.
#ontario

Hat schon jemand von euch die 10 Euro von Paypal kassiert?
Der Zahlungsdienstleister hat eine Entschädigungsaktion gestartet und schreibt betroffenen Kunden 10 Euro gut. In einer Benachrichtigungs-E-Mail entschuldigt sich das Unternehmen für die "vorübergehende Störung" und die daraus entstandenen Unannehmlichkeiten.
Zum Artikel:

Nos despertó el #TemblorCR
Fuerte sonó en Heredia

also on the opposite platform there are no customers waiting for a train, but there is a #chicken.

Where Did I Leave My Glasses? Open-Vocabulary Semantic Exploration in Real-World Semi-Static Environments
Benjamin Bogenberger, Oliver Harrison, Orrin Dahanaggamaarachchi, Lukas Brunke, Jingxing Qian, Siqi Zhou, Angela P. Schoellig
https://arxiv.org/abs/2509.19851

Where Did I Leave My Glasses? Open-Vocabulary Semantic Exploration in Real-World Semi-Static Environments
Robots deployed in real-world environments, such as homes, must not only navigate safely but also understand their surroundings and adapt to environment changes. To perform tasks efficiently, they must build and maintain a semantic map that accurately reflects the current state of the environment. Existing research on semantic exploration largely focuses on static scenes without persistent object-level instance tracking. A consistent map is, however, crucial for real-world robotic applications …

Ripple Effects
Hosted by Soph Dicker from So Invested following Australian founders and VC operators on a transformative two-week journey in Tanzania...
Great Australian Pods Podcast Directory: https://www.greataustralianpods.com/ripple-effects/

GO
C'est une abbération d'avoir des clubs de pêches américains qui possèdent une rivière (!) au Québec
https://www.lapresse.ca/actualites/regional/la-pre…

XMPP is here. Don't forget about it.
#xmpp

Crosslisted article(s) found for cs.IR. https://arxiv.org/list/cs.IR/new
[1/1]:
- Learn to Memorize: Optimizing LLM-based Agents with Adaptive Memory Framework
Zeyu Zhang, Quanyu Dai, Rui Li, Xiaohe Bo, Xu Chen, Zhenhua Dong

Sorry, heute wenigstens bis jetzt einen Lauf.
#pastpuzzle 373
🟩🟩🟩🟩 (0)
▪️▪️▪️▪️
▪️▪️▪️▪️
▪️▪️▪️▪️
1/4 🥇
https://www.pastpuzzle.de

Successfully upgraded my refurbished XIAOMI #smartphone to eOS 3.04 (=Android 14 without Google). Has amazing #privacy tools, such as a tracker monitor or that each app needs permission the access the Internet (which first made me think some routing tables got wild, but it is a securty feature!). And e…

Chui sur que la rive-sud va être contente
https://www.journaldequebec.com/2025/09/26/le-gouvernement-legault-mettra-en-place-un-peage-dynamique-pour-les-usagers-dun-futur…

Beim Ortsbus Uitikon ist freundeidgenössische Hilfestellung angesagt.
#Uitikon #Waldegg #öv #Bus

PCR-CA: Parallel Codebook Representations with Contrastive Alignment for Multiple-Category App Recommendation
Bin Tan, Wangyao Ge, Yidi Wang, Xin Liu, Jeff Burtoft, Hao Fan, Hui Wang
https://arxiv.org/abs/2508.18166

PCR-CA: Parallel Codebook Representations with Contrastive Alignment for Multiple-Category App Recommendation
Modern app store recommender systems struggle with multiple-category apps, as traditional taxonomies fail to capture overlapping semantics, leading to suboptimal personalization. We propose PCR-CA (Parallel Codebook Representations with Contrastive Alignment), an end-to-end framework for improved CTR prediction. PCR-CA first extracts compact multimodal embeddings from app text, then introduces a Parallel Codebook VQ-AE module that learns discrete semantic representations across multiple codeboo…

Sammy Obeid tried to organize a show in #Singapore
This did not go well. Had to submit his whole script in advance. Ultimately rejected.
That's the thing with Singapore, it's an awesome place to visit, but it's also not very democratic. Protests need a permit, etc.

Sure ... 😅
(Komt binnen op een oud adres.)
(*****spam**** is van FairEmail)
#TrapErNietIn

Test-Time Scaling Strategies for Generative Retrieval in Multimodal Conversational Recommendations
Hung-Chun Hsu, Yuan-Ching Kuo, Chao-Han Huck Yang, Szu-Wei Fu, Hanrong Ye, Hongxu Yin, Yu-Chiang Frank Wang, Ming-Feng Tsai, Chuan-Ju Wang
https://arxiv.org/abs/2508.18132

Test-Time Scaling Strategies for Generative Retrieval in Multimodal Conversational Recommendations
The rapid evolution of e-commerce has exposed the limitations of traditional product retrieval systems in managing complex, multi-turn user interactions. Recent advances in multimodal generative retrieval -- particularly those leveraging multimodal large language models (MLLMs) as retrievers -- have shown promise. However, most existing methods are tailored to single-turn scenarios and struggle to model the evolving intent and iterative nature of multi-turn dialogues when applied naively. Concu…

Die Vögel.
#vogel #Kran

At @… we are planning the next generation of servers offering virtual machines. While we are deploying many applications on our own #kubernetes cluster, there is still the need of VMs for development and some support services.
What is your preferred

HLLM-Creator: Hierarchical LLM-based Personalized Creative Generation
Junyi Chen, Lu Chi, Siliang Xu, Shiwei Ran, Bingyue Peng, Zehuan Yuan
https://arxiv.org/abs/2508.18118 http…

HLLM-Creator: Hierarchical LLM-based Personalized Creative Generation
AI-generated content technologies are widely used in content creation. However, current AIGC systems rely heavily on creators' inspiration, rarely generating truly user-personalized content. In real-world applications such as online advertising, a single product may have multiple selling points, with different users focusing on different features. This underscores the significant value of personalized, user-centric creative generation. Effective personalized content generation faces two main ch…

HyST: LLM-Powered Hybrid Retrieval over Semi-Structured Tabular Data
Jiyoon Myung, Jihyeon Park, Joohyung Han
https://arxiv.org/abs/2508.18048 https://arxi…

HyST: LLM-Powered Hybrid Retrieval over Semi-Structured Tabular Data
User queries in real-world recommendation systems often combine structured constraints (e.g., category, attributes) with unstructured preferences (e.g., product descriptions or reviews). We introduce HyST (Hybrid retrieval over Semi-structured Tabular data), a hybrid retrieval framework that combines LLM-powered structured filtering with semantic embedding search to support complex information needs over semi-structured tabular data. HyST extracts attribute-level constraints from natural langua…

Ein paar Bilder der heutigen - kurzen - Grenzwanderung, leider eher „technisch“. Es war eine undurchdachte Idee im Hochsommer: Die #Grenzsteine liegen im Unterholz, und die #Brennessel aufgrund der kurzen Hosen einen Freudentag.
Es ging von Wasterkingen (ernsthaft, war ich noch nie) ein paar Höhen…

Retrieval Feedback Memory Enhancement Large Model Retrieval Generation Method
Leqian Li, Dianxi Shi, Jialu Zhou, Xinyu Wei, Mingyue Yang, Songchang Jin, Shaowu Yang
https://arxiv.org/abs/2508.17862

Retrieval Feedback Memory Enhancement Large Model Retrieval Generation Method
Large Language Models (LLMs) have shown remarkable capabilities across diverse tasks, yet they face inherent limitations such as constrained parametric knowledge and high retraining costs. Retrieval-Augmented Generation (RAG) augments the generation process by retrieving externally stored knowledge absent from the models internal parameters. However, RAG methods face challenges such as information loss and redundant retrievals during multi-round queries, accompanying the difficulties in precise…

Microsoft has terminated the Israeli military’s access to technology it used to operate a powerful surveillance system that collected millions of Palestinian civilian phone calls made each day in Gaza and the West Bank
https://www.

LexSemBridge: Fine-Grained Dense Representation Enhancement through Token-Aware Embedding Augmentation
Shaoxiong Zhan, Hai Lin, Hongming Tan, Xiaodong Cai, Hai-Tao Zheng, Xin Su, Zifei Shan, Ruitong Liu, Hong-Gee Kim
https://arxiv.org/abs/2508.17858

LexSemBridge: Fine-Grained Dense Representation Enhancement through Token-Aware Embedding Augmentation
As queries in retrieval-augmented generation (RAG) pipelines powered by large language models (LLMs) become increasingly complex and diverse, dense retrieval models have demonstrated strong performance in semantic matching. Nevertheless, they often struggle with fine-grained retrieval tasks, where precise keyword alignment and span-level localization are required, even in cases with high lexical overlap that would intuitively suggest easier retrieval. To systematically evaluate this limitation,…

Research on Evaluation Methods for Patent Novelty Search Systems and Empirical Analysis
Shu Zhang, LiSha Zhang, Kai Duan, XinKai Sun
https://arxiv.org/abs/2508.17782 https://

Research on Evaluation Methods for Patent Novelty Search Systems and Empirical Analysis
Patent novelty search systems are critical to IP protection and innovation assessment; their retrieval accuracy directly impacts patent quality. We propose a comprehensive evaluation methodology that builds high-quality, reproducible datasets from examiner citations and X-type citations extracted from technically consistent family patents, and evaluates systems using invention descriptions as inputs. Using Top-k Detection Rate and Recall as core metrics, we further conduct multi-dimensional ana…

Bonne journée des franco-ontariens!
#onfr #Francophonie

DiffusionGS: Generative Search with Query Conditioned Diffusion in Kuaishou
Qinyao Li, Xiaoyang Zheng, Qihang Zhao, Ke Xu, Zhongbo Sun, Chao Wang, Chenyi Lei, Han Li, Wenwu Ou
https://arxiv.org/abs/2508.17754

DiffusionGS: Generative Search with Query Conditioned Diffusion in Kuaishou
Personalized search ranking systems are critical for driving engagement and revenue in modern e-commerce and short-video platforms. While existing methods excel at estimating users' broad interests based on the filtered historical behaviors, they typically under-exploit explicit alignment between a user's real-time intent (represented by the user query) and their past actions. In this paper, we propose DiffusionGS, a novel and scalable approach powered by generative models. Our key insight is t…

Es gibt also nicht nur ein Cannes, sondern kurz davor auch noch ein Cagnes. Das muss die sonnige Variante des Verwirrspiels von Dietikon/Dietlikon sein. Aber hey, hintergrundbeleuchtete Steckdosen im Zug sind schon fancy (auch wenn sie, wie die Trams hier auch, offensichtlich nicht auf maximal einfachen Passagierfluss ausgelegt sind).
#bahnbubble

How Do LLM-Generated Texts Impact Term-Based Retrieval Models?
Wei Huang, Keping Bi, Yinqiong Cai, Wei Chen, Jiafeng Guo, Xueqi Cheng
https://arxiv.org/abs/2508.17715 https://…

How Do LLM-Generated Texts Impact Term-Based Retrieval Models?
As more content generated by large language models (LLMs) floods into the Internet, information retrieval (IR) systems now face the challenge of distinguishing and handling a blend of human-authored and machine-generated texts. Recent studies suggest that neural retrievers may exhibit a preferential inclination toward LLM-generated content, while classic term-based retrievers like BM25 tend to favor human-written documents. This paper investigates the influence of LLM-generated content on term-…

Semantic Search for Information Retrieval
Kayla Farivar
https://arxiv.org/abs/2508.17694 https://arxiv.org/pdf/2508.17694

Semantic Search for Information Retrieval
Information retrieval systems have progressed notably from lexical techniques such as BM25 and TF-IDF to modern semantic retrievers. This survey provides a brief overview of the BM25 baseline, then discusses the architecture of modern state-of-the-art semantic retrievers. Advancing from BERT, we introduce dense bi-encoders (DPR), late-interaction models (ColBERT), and neural sparse retrieval (SPLADE). Finally, we examine MonoT5, a cross-encoder model. We conclude with common evaluation tactics,…

Demographically-Inspired Query Variants Using an LLM
Marwah Alaofi, Nicola Ferro, Paul Thomas, Falk Scholer, Mark Sanderson
https://arxiv.org/abs/2508.17644 https://

Demographically-Inspired Query Variants Using an LLM
This study proposes a method to diversify queries in existing test collections to reflect some of the diversity of search engine users, aligning with an earlier vision of an 'ideal' test collection. A Large Language Model (LLM) is used to create query variants: alternative queries that have the same meaning as the original. These variants represent user profiles characterised by different properties, such as language and domain proficiency, which are known in the IR literature to influence quer…

Preference Trajectory Modeling via Flow Matching for Sequential Recommendation
Li Li, Mingyue Cheng, Yuyang Ye, Zhiding Liu, Enhong Chen
https://arxiv.org/abs/2508.17618 https:/…

Preference Trajectory Modeling via Flow Matching for Sequential Recommendation
Sequential recommendation predicts each user's next item based on their historical interaction sequence. Recently, diffusion models have attracted significant attention in this area due to their strong ability to model user interest distributions. They typically generate target items by denoising Gaussian noise conditioned on historical interactions. However, these models face two critical limitations. First, they exhibit high sensitivity to the condition, making it difficult to recover target …

Ohne die Bemalung würde diese Kurve ja gar niemand kennen.

A Universal Framework for Offline Serendipity Evaluation in Recommender Systems via Large Language Models
Yu Tokutake, Kazushi Okamoto, Kei Harada, Atsushi Shibata, Koki Karube
https://arxiv.org/abs/2508.17571

A Universal Framework for Offline Serendipity Evaluation in Recommender Systems via Large Language Models
Serendipity in recommender systems (RSs) has attracted increasing attention as a concept that enhances user satisfaction by presenting unexpected and useful items. However, evaluating serendipitous performance remains challenging because its ground truth is generally unobservable. The existing offline metrics often depend on ambiguous definitions or are tailored to specific datasets and RSs, thereby limiting their generalizability. To address this issue, we propose a universally applicable eval…

Un Québécois au Championnat mondial d’Excel
Fascinant
https://www.lapresse.ca/affaires/techno/2025-10-23/un-quebecois-au-championnat-mondial-d-excel.php

Opening the Black Box: Interpretable Remedies for Popularity Bias in Recommender Systems
Parviz Ahmadov, Masoud Mansoury
https://arxiv.org/abs/2508.17297 https://

Opening the Black Box: Interpretable Remedies for Popularity Bias in Recommender Systems
Popularity bias is a well-known challenge in recommender systems, where a small number of popular items receive disproportionate attention, while the majority of less popular items are largely overlooked. This imbalance often results in reduced recommendation quality and unfair exposure of items. Although existing mitigation techniques address this bias to some extent, they typically lack transparency in how they operate. In this paper, we propose a post-hoc method using a Sparse Autoencoder (S…

Was man nicht alles lernt, wenn man mit der #Tochter in den #Ferien ist. Man kann im Kleidergeschäft auch Plastiksäcke kaufen. Und sicher gibt es die selben auch zuhause.
#bershka

VQL: An End-to-End Context-Aware Vector Quantization Attention for Ultra-Long User Behavior Modeling
Kaiyuan Li, Yongxiang Tang, Yanhua Cheng, Yong Bai, Yanxiang Zeng, Chao Wang, Xialong Liu, Peng Jiang
https://arxiv.org/abs/2508.17125

VQL: An End-to-End Context-Aware Vector Quantization Attention for Ultra-Long User Behavior Modeling
In large-scale recommender systems, ultra-long user behavior sequences encode rich signals of evolving interests. Extending sequence length generally improves accuracy, but directly modeling such sequences in production is infeasible due to latency and memory constraints. Existing solutions fall into two categories: (1) top-k retrieval, which truncates the sequence and may discard most attention mass when L >> k; and (2) encoder-based compression, which preserves coverage but often over-compres…

#Qlub abandonne le modèle d'avoir 2 instances séparées (1 gratuite, 1 payante pour les membres plus), les membres seront ré-intégrés.
C'est certainement mieux de cette façon, ça envoyait les power users sur une instance séparée donc réduisait l'achalandage de l'instance principale

Zero-shot Multimodal Document Retrieval via Cross-modal Question Generation
Yejin Choi, Jaewoo Park, Janghan Yoon, Saejin Kim, Jaehyun Jeon, Youngjae Yu
https://arxiv.org/abs/2508.17079

Zero-shot Multimodal Document Retrieval via Cross-modal Question Generation
Rapid advances in Multimodal Large Language Models (MLLMs) have expanded information retrieval beyond purely textual inputs, enabling retrieval from complex real world documents that combine text and visuals. However, most documents are private either owned by individuals or confined within corporate silos and current retrievers struggle when faced with unseen domains or languages. To address this gap, we introduce PREMIR, a simple yet effective framework that leverages the broad knowledge of a…

Towards a Real-World Aligned Benchmark for Unlearning in Recommender Systems
Pierre Lubitzsch, Olga Ovcharenko, Hao Chen, Maarten de Rijke, Sebastian Schelter
https://arxiv.org/abs/2508.17076

Towards a Real-World Aligned Benchmark for Unlearning in Recommender Systems
Modern recommender systems heavily leverage user interaction data to deliver personalized experiences. However, relying on personal data presents challenges in adhering to privacy regulations, such as the GDPR's "right to be forgotten". Machine unlearning (MU) aims to address these challenges by enabling the efficient removal of specific training data from models post-training, without compromising model utility or leaving residual information. However, current benchmarks for unlearning in reco…

Québec et la CAQ veut bannir le pronom "iel" et l'écriture inclusive, encore une fois ono s'attaque aux minorités et on veut avoir l'air anti-woke.
#quebec

Die Tochter hat den Hairstraightener und ihren eigenen Fön ausgepackt. Was man so alles braucht für eine Reise an die Côte d‘Azur. Aber sie buckelt das Zeugs selbst vom Bahnhof zum Hotel.

Bootstrapping Conditional Retrieval for User-to-Item Recommendations
Hongtao Lin, Haoyu Chen, Jaewon Jang, Jiajing Xu
https://arxiv.org/abs/2508.16793 https://

Bootstrapping Conditional Retrieval for User-to-Item Recommendations
User-to-item retrieval has been an active research area in recommendation system, and two tower models are widely adopted due to model simplicity and serving efficiency. In this work, we focus on a variant called \textit{conditional retrieval}, where we expect retrieved items to be relevant to a condition (e.g. topic). We propose a method that uses the same training data as standard two tower models but incorporates item-side information as conditions in query. This allows us to bootstrap new c…

[2025-08-26 Tue (UTC), 18 new articles found for cs.IR Information Retrieval]
toXiv_bot_toot

Urban observations about #Winnipeg
-Why are the downtown streets so large? For a city built before car dependency, I find everything very large
-So many one-ways
-While it looks quite car centric, I see many people at bus stop. (I hope it means transit is decent and not that there’s isn’t enough bus)
-Sadly downtown has seen better days. Beautiful buildings but ma…

Replaced article(s) found for cs.IR. https://arxiv.org/list/cs.IR/new
[1/1]:
- Post-fusion monolithic hybrid recommender system for suggesting relevant movies to users
Mahdi Rezapour

Optimization of Latent-Space Compression using Game-Theoretic Techniques for Transformer-Based Vector Search
Kushagra Agrawal, Nisharg Nargund, Oishani Banerjee
https://arxiv.org/abs/2508.18877

Optimization of Latent-Space Compression using Game-Theoretic Techniques for Transformer-Based Vector Search
Vector similarity search plays a pivotal role in modern information retrieval systems, especially when powered by transformer-based embeddings. However, the scalability and efficiency of such systems are often hindered by the high dimensionality of latent representations. In this paper, we propose a novel game-theoretic framework for optimizing latent-space compression to enhance both the efficiency and semantic utility of vector search. By modeling the compression strategy as a zero-sum game b…

Taming the One-Epoch Phenomenon in Online Recommendation System by Two-stage Contrastive ID Pre-training
Yi-Ping Hsu, Po-Wei Wang, Chantat Eksombatchai, Jiajing Xu
https://arxiv.org/abs/2508.18700

Taming the One-Epoch Phenomenon in Online Recommendation System by Two-stage Contrastive ID Pre-training
ID-based embeddings are widely used in web-scale online recommendation systems. However, their susceptibility to overfitting, particularly due to the long-tail nature of data distributions, often limits training to a single epoch, a phenomenon known as the "one-epoch problem." This challenge has driven research efforts to optimize performance within the first epoch by enhancing convergence speed or feature sparsity. In this study, we introduce a novel two-stage training strategy that incorporat…

Membership Inference Attacks on LLM-based Recommender Systems
Jiajie He, Yuechun Gu, Min-Chun Chen, Keke Chen
https://arxiv.org/abs/2508.18665 https://arxi…

Membership Inference Attacks on LLM-based Recommender Systems
Large language models (LLMs) based Recommender Systems (RecSys) can flexibly adapt recommendation systems to different domains. It utilizes in-context learning (ICL), i.e., the prompts, to customize the recommendation functions, which include sensitive historical user-specific item interactions, e.g., implicit feedback like clicked items or explicit product reviews. Such private information may be exposed to novel privacy attack. However, no study has been done on this important issue. We desig…

Extracting Information from Scientific Literature via Visual Table Question Answering Models
Dongyoun Kim, Hyung-do Choi, Youngsun Jang, John Kim
https://arxiv.org/abs/2508.18661

Extracting Information from Scientific Literature via Visual Table Question Answering Models
This study explores three approaches to processing table data in scientific papers to enhance extractive question answering and develop a software tool for the systematic review process. The methods evaluated include: (1) Optical Character Recognition (OCR) for extracting information from documents, (2) Pre-trained models for document visual question answering, and (3) Table detection and structure recognition to extract and merge key information from tables with textual content to answer extra…

DenseRec: Revisiting Dense Content Embeddings for Sequential Transformer-based Recommendation
Jan Malte Lichtenberg, Antonio De Candia, Matteo Ruffini
https://arxiv.org/abs/2508.18442

DenseRec: Revisiting Dense Content Embeddings for Sequential Transformer-based Recommendation
Transformer-based sequential recommenders, such as SASRec or BERT4Rec, typically rely solely on learned item ID embeddings, making them vulnerable to the item cold-start problem, particularly in environments with dynamic item catalogs. While dense content embeddings from pre-trained models offer potential solutions, direct integration into transformer-based recommenders has consistently underperformed compared to ID-only approaches. We revisit this integration challenge and propose DenseRec, a …

REALM: Recursive Relevance Modeling for LLM-based Document Re-Ranking
Pinhuan Wang, Zhiqiu Xia, Chunhua Liao, Feiyi Wang, Hang Liu
https://arxiv.org/abs/2508.18379 https://

REALM: Recursive Relevance Modeling for LLM-based Document Re-Ranking
Large Language Models (LLMs) have shown strong capabilities in document re-ranking, a key component in modern Information Retrieval (IR) systems. However, existing LLM-based approaches face notable limitations, including ranking uncertainty, unstable top-k recovery, and high token cost due to token-intensive prompting. To effectively address these limitations, we propose REALM, an uncertainty-aware re-ranking framework that models LLM-derived relevance as Gaussian distributions and refines them…

[2025-08-27 Wed (UTC), 6 new articles found for cs.IR Information Retrieval]
toXiv_bot_toot

Interactive Recommendation Agent with Active User Commands
Jiakai Tang, Yujie Luo, Xunke Xi, Fei Sun, Xueyang Feng, Sunhao Dai, Chao Yi, Dian Chen, Zhujin Gao, Yang Li, Xu Chen, Wen Chen, Jian Wu, Yuning Jiang, Bo Zheng
https://arxiv.org/abs/2509.21317

Interactive Recommendation Agent with Active User Commands
Traditional recommender systems rely on passive feedback mechanisms that limit users to simple choices such as like and dislike. However, these coarse-grained signals fail to capture users' nuanced behavior motivations and intentions. In turn, current systems cannot also distinguish which specific item attributes drive user satisfaction or dissatisfaction, resulting in inaccurate preference modeling. These fundamental limitations create a persistent gap between user intentions and system interp…

IntSR: An Integrated Generative Framework for Search and Recommendation
Huimin Yan, Longfei Xu, Junjie Sun, Ni Ou, Wei Luo, Xing Tan, Ran Cheng, Kaikui Liu, Xiangxiang Chu
https://arxiv.org/abs/2509.21179

IntSR: An Integrated Generative Framework for Search and Recommendation
Generative recommendation has emerged as a promising paradigm, demonstrating remarkable results in both academic benchmarks and industrial applications. However, existing systems predominantly focus on unifying retrieval and ranking while neglecting the integration of search and recommendation (S&R) tasks. What makes search and recommendation different is how queries are formed: search uses explicit user requests, while recommendation relies on implicit user interests. As for retrieval versus r…

FORGE: Forming Semantic Identifiers for Generative Retrieval in Industrial Datasets
Kairui Fu, Tao Zhang, Shuwen Xiao, Ziyang Wang, Xinming Zhang, Chenchi Zhang, Yuliang Yan, Junjun Zheng, Yu Li, Zhihong Chen, Jian Wu, Xiangheng Kong, Shengyu Zhang, Kun Kuang, Yuning Jiang, Bo Zheng
https://arxiv.org/abs/2509.20904

FORGE: Forming Semantic Identifiers for Generative Retrieval in Industrial Datasets
Semantic identifiers (SIDs) have gained increasing attention in generative retrieval (GR) due to their meaningful semantic discriminability. However, current research on SIDs faces three main challenges: (1) the absence of large-scale public datasets with multimodal features, (2) limited investigation into optimization strategies for SID generation, which typically rely on costly GR training for evaluation, and (3) slow online convergence in industrial deployment. To address these challenges, w…

RecIS: Sparse to Dense, A Unified Training Framework for Recommendation Models
Hua Zong, Qingtao Zeng, Zhengxiong Zhou, Zhihua Han, Zhensong Yan, Mingjie Liu, Hechen Sun, Jiawei Liu, Yiwen Hu, Qi Wang, YiHan Xian, Wenjie Guo, Houyuan Xiang, Zhiyuan Zeng, Xiangrong Sheng, Bencheng Yan, Nan Hu, Yuheng Huang, Jinqing Lian, Ziru Xu, Yan Zhang, Ju Huang, Siran Yang, Huimin Yi, Jiamang Wang, Pengjie Wang, Han Zhu, Jian Wu, Dan Ou, Jian Xu, Haihong Tang, Yuning Jiang, Bo Zheng, Lin Qu

RecIS: Sparse to Dense, A Unified Training Framework for Recommendation Models
In this paper, we propose RecIS, a unified Sparse-Dense training framework designed to achieve two primary goals: 1. Unified Framework To create a Unified sparse-dense training framework based on the PyTorch ecosystem that meets the training needs of industrial-grade recommendation models that integrated with large models. 2.System Optimization To optimize the sparse component, offering superior efficiency over the TensorFlow-based recommendation models. The dense component, meanwhile, leverage…

Performance Consistency of Learning Methods for Information Retrieval Tasks
Meng Yuan, Justin Zobel
https://arxiv.org/abs/2509.20804 https://arxiv.org/pdf/…

Performance Consistency of Learning Methods for Information Retrieval Tasks
A range of approaches have been proposed for estimating the accuracy or robustness of the measured performance of IR methods. One is to use bootstrapping of test sets, which, as we confirm, provides an estimate of variation in performance. For IR methods that rely on a seed, such as those that involve machine learning, another approach is to use a random set of seeds to examine performance variation. Using three different IR tasks we have used such randomness to examine a range of traditional s…

Provenance Analysis of Archaeological Artifacts via Multimodal RAG Systems
Tuo Zhang, Yuechun Sun, Ruiliang Liu
https://arxiv.org/abs/2509.20769 https://ar…

Provenance Analysis of Archaeological Artifacts via Multimodal RAG Systems
In this work, we present a retrieval-augmented generation (RAG)-based system for provenance analysis of archaeological artifacts, designed to support expert reasoning by integrating multimodal retrieval and large vision-language models (VLMs). The system constructs a dual-modal knowledge base from reference texts and images, enabling raw visual, edge-enhanced, and semantic retrieval to identify stylistically similar objects. Retrieved candidates are synthesized by the VLM to generate structured…

DELM: a Python toolkit for Data Extraction with Language Models
Eric Fithian, Kirill Skobelev
https://arxiv.org/abs/2509.20617 https://arxiv.org/pdf/2509.2…

DELM: a Python toolkit for Data Extraction with Language Models
Large Language Models (LLMs) have become powerful tools for annotating unstructured data. However, most existing workflows rely on ad hoc scripts, making reproducibility, robustness, and systematic evaluation difficult. To address these challenges, we introduce DELM (Data Extraction with Language Models), an open-source Python toolkit designed for rapid experimental iteration of LLM-based data extraction pipelines and for quantifying the trade-offs between them. DELM minimizes boilerplate code …

[2025-09-26 Fri (UTC), 9 new articles found for cs.IR Information Retrieval]
toXiv_bot_toot

Replaced article(s) found for cs.IR. https://arxiv.org/list/cs.IR/new
[1/1]:
- Application of Audio Fingerprinting Techniques for Real-Time Scalable Speech Retrieval and Speech...
Kemal Altwlkany, Sead Delali\'c, Adis Alihod\v{z}i\'c, Elmedin Selmanovi\'c, Damir Hasi\'c

Crosslisted article(s) found for cs.IR. https://arxiv.org/list/cs.IR/new
[1/1]:
- Dynamic ReAct: Scalable Tool Selection for Large-Scale MCP Environments
Nishant Gaurav, Adit Akarsh, Ankit Ranjan, Manoj Bajaj

Replaced article(s) found for cs.IR. https://arxiv.org/list/cs.IR/new
[1/1]:
- Monolithic Hybrid Recommender System for Suggesting Relevant Movies
Mahdi Rezapour
…

Crosslisted article(s) found for cs.IR. https://arxiv.org/list/cs.IR/new
[1/1]:
- An Auditable Pipeline for Fuzzy Full-Text Screening in Systematic Reviews: Integrating Contrastiv...
Pouria Mortezaagha, Arya Rahgozar

ORCA: Mitigating Over-Reliance for Multi-Task Dwell Time Prediction with Causal Decoupling
Huishi Luo, Fuzhen Zhuang, Yongchun Zhu, Yiqing Wu, Bo Kang, Ruobing Xie, Feng Xia, Deqing Wang, Jin Dong
https://arxiv.org/abs/2508.16573

ORCA: Mitigating Over-Reliance for Multi-Task Dwell Time Prediction with Causal Decoupling
Dwell time (DT) is a critical post-click metric for evaluating user preference in recommender systems, complementing the traditional click-through rate (CTR). Although multi-task learning is widely adopted to jointly optimize DT and CTR, we observe that multi-task models systematically collapse their DT predictions to the shortest and longest bins, under-predicting the moderate durations. We attribute this moderate-duration bin under-representation to over-reliance on the CTR-DT spurious correl…

Enhanced NIRMAL Optimizer With Damped Nesterov Acceleration: A Comparative Analysis
Nirmal Gaud, Prasad Krishna Murthy, Mostaque Md. Morshedur Hassan, Abhijit Ganguly, Vinay Mali, Ms Lalita Bhagwat Randive, Abhaypratap Singh
https://arxiv.org/abs/2508.16550

Enhanced NIRMAL Optimizer With Damped Nesterov Acceleration: A Comparative Analysis
This study introduces the Enhanced NIRMAL (Novel Integrated Robust Multi-Adaptation Learning with Damped Nesterov Acceleration) optimizer, an improved version of the original NIRMAL optimizer. By incorporating an $(α, r)$-damped Nesterov acceleration mechanism, Enhanced NIRMAL improves convergence stability while retaining chess-inspired strategies of gradient descent, momentum, stochastic perturbations, adaptive learning rates, and non-linear transformations. We evaluate Enhanced NIRMAL aga…

A Node-Aware Dynamic Quantization Approach for Graph Collaborative Filtering
Lin Li, Chunyang Li, Yu Yin, Xiaohui Tao, Jianwei Zhang
https://arxiv.org/abs/2508.16516 https://

A Node-Aware Dynamic Quantization Approach for Graph Collaborative Filtering
In the realm of collaborative filtering recommendation systems, Graph Neural Networks (GNNs) have demonstrated remarkable performance but face significant challenges in deployment on resource-constrained edge devices due to their high embedding parameter requirements and computational costs. Using common quantization method directly on node embeddings may overlooks their graph based structure, causing error accumulation during message passing and degrading the quality of quantized embeddings.To…

OPERA: A Reinforcement Learning--Enhanced Orchestrated Planner-Executor Architecture for Reasoning-Oriented Multi-Hop Retrieval
Yu Liu, Yanbing Liu, Fangfang Yuan, Cong Cao, Youbang Sun, Kun Peng, WeiZhuo Chen, Jianjun Li, Zhiyuan Ma
https://arxiv.org/abs/2508.16438

OPERA: A Reinforcement Learning--Enhanced Orchestrated Planner-Executor Architecture for Reasoning-Oriented Multi-Hop Retrieval
Recent advances in large language models (LLMs) and dense retrievers have driven significant progress in retrieval-augmented generation (RAG). However, existing approaches face significant challenges in complex reasoning-oriented multi-hop retrieval tasks: 1) Ineffective reasoning-oriented planning: Prior methods struggle to generate robust multi-step plans for complex queries, as rule-based decomposers perform poorly on out-of-template questions. 2) Suboptimal reasoning-driven retrieval: Relat…

Modeling User Preferences as Distributions for Optimal Transport-based Cross-domain Recommendation under Non-overlapping Settings
Ziyin Xiao, Toyotaro Suzumura
https://arxiv.org/abs/2508.16210

Modeling User Preferences as Distributions for Optimal Transport-based Cross-domain Recommendation under Non-overlapping Settings
Cross-Domain Recommender (CDR) systems aim to transfer knowledge from dense to sparse domains, alleviating data sparsity and cold-start issues in single-domain recommendation. While many methods assume overlapping users or items to connect domains, this is often unrealistic in real-world settings. Thus, non-overlapping CDR systems, which require no shared users or items, are needed. However, non-overlapping CDR is challenging due to: (1) the absence of overlap preventing direct bridges betwee…

EGRA:Toward Enhanced Behavior Graphs and Representation Alignment for Multimodal Recommendation
Xiaoxiong Zhang, Xin Zhou, Zhiwei Zeng, Yongjie Wang, Dusit Niyato, Zhiqi Shen
https://arxiv.org/abs/2508.16170

EGRA:Toward Enhanced Behavior Graphs and Representation Alignment for Multimodal Recommendation
MultiModal Recommendation (MMR) systems have emerged as a promising solution for improving recommendation quality by leveraging rich item-side modality information, prompting a surge of diverse methods. Despite these advances, existing methods still face two critical limitations. First, they use raw modality features to construct item-item links for enriching the behavior graph, while giving limited attention to balancing collaborative and modality-aware semantics or mitigating modality noise i…