Tootfinder

Opens with a True Story.

This https://arxiv.org/abs/2506.06278 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Distillation Robustifies Unlearning
Current LLM unlearning methods are not robust: they can be reverted easily with a few steps of finetuning. This is true even for the idealized unlearning method of training to imitate an oracle model that was never exposed to unwanted information, suggesting that output-based finetuning is insufficient to achieve robust unlearning. In a similar vein, we find that training a randomly initialized student to imitate an unlearned model transfers desired behaviors while leaving undesired capabilitie…

Crossed paths with this nice turtle. Maybe a map turtle?
#Indiana #Wildlife #Herpetology

Testing response to a different thumbnail:
https://youtu.be/dWv-5nENq7I?si=pXPEUH_cX5zzTNT1

Viture Luma: Neue Display-Brillen bieten bis zu 173 Zoll Bildschirmdiagonale
Ab Juli kommen vier neue Modelle der Viture-Luma-Serie auf den Markt. Wir klären, wie sich die Smart Glasses mit Schwerpunkt Medienwiedergabe unterscheiden.

From private eye

#perl

I was most interested in how A.I.
— one of whose many superpowers is the ability to inhale large amounts of text in an instant and offer credible summaries of it
— might transform the way history is written.
https://www.…

A.I. Is Poised to Rewrite History. Literally.
The technology’s ability to read and summarize text is already making it a useful tool for scholarship. How will it change the stories we tell about the past?

This https://arxiv.org/abs/2506.06105 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Text-to-LoRA: Instant Transformer Adaption
While Foundation Models provide a general tool for rapid content creation, they regularly require task-specific adaptation. Traditionally, this exercise involves careful curation of datasets and repeated fine-tuning of the underlying model. Fine-tuning techniques enable practitioners to adapt foundation models for many new applications but require expensive and lengthy training while being notably sensitive to hyper-parameter choices. To overcome these limitations, we introduce Text-to-LoRA (T2…

Learning to use my media tools- I made some video therapy.

I made the music in Reason and the animation in After Effects. I might have borrowed a few pictures from the web too.
It might not be pretty, but it's also not AI!
#resist #support

ISWS 2025 evening at the Bertinoro village square. waiting for the surprise event 😉
#ISWS2025 #semanticweb #KnowledgeGraphs

Schön in HH bei IKEA gewesen, danach bei Eis Café Höft in Schnelsen.

A constant with #metrolinx is
1-they don’t seem to have deadlines. A culture based on having no deadlines goes against every project management principles
2. They can never answer you about what’s happening and what’s taking so long. You don’t have anyone to pressure to get answers
That’s what make Metrolinx much more undemocratic than the TTC.

New shelves came in, went ahead and pulled the shorter ones out, installed the full length ones, installed the supports, and cleaned up the power cables. Also adjusted the hooks on the back so they make a bit more sense.
Do the new shelves seem crooked? Yes. However they should support the MS-A2s a bit better.
#homelab

Multi-Qubit Parity Gates for Rydberg Atoms in Various Configurations
Javad Kazemi, Michael Schuler, Christian Ertler, Wolfgang Lechner
https://arxiv.org/abs/2506.09686

Multi-Qubit Parity Gates for Rydberg Atoms in Various Configurations
We present a native approach for realizing multi-qubit parity phase gates in neutral atom systems through global phase modulation of a Rydberg excitation laser. By shaping the temporal profile of the laser's phase, we enable high fidelity, time efficient entangling operations between multiple qubits without requiring individual qubit addressing. To mitigate intrinsic noise sources including spontaneous decay and motional effects, we develop a noise-aware optimal control framework that reduces g…

This https://arxiv.org/abs/2506.05960 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

AQUATIC-Diff: Additive Quantization for Truly Tiny Compressed Diffusion Models
Significant investments have been made towards the commodification of diffusion models for generation of diverse media. Their mass-market adoption is however still hobbled by the intense hardware resource requirements of diffusion model inference. Model quantization strategies tailored specifically towards diffusion models have been useful in easing this burden, yet have generally explored the Uniform Scalar Quantization (USQ) family of quantization methods. In contrast, Vector Quantization (VQ…

First run in over a month. No goals other than to clear my mind, enjoy the cooler evening temperatures, feel the breeze and enjoy the rustling of the leaves as the wind stirred the branches, to enjoy looking up at a nearly full moon, and let it all wash over me.
#Running

Irgendetwas stimmt mit nvmi nicht :(

#DonnaDErrico #Lifeguards
Season 7 Episode 12 "Bachelor of the Month"
#RandomBaywatch #lvdlpx

Replaced article(s) found for cs.IR. https://arxiv.org/list/cs.IR/new
[1/1]:
- Adaptive Graph Integration for Cross-Domain Recommendation via Heterogeneous Graph Coordinators
Hengyu Zhang, Chunxu Shen, Xiangguo Sun, Jie Tan, Yu Rong, Chengzhi Piao, Hong Cheng, Lingling Yi
…

This https://arxiv.org/abs/2506.05831 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Heartcare Suite: Multi-dimensional Understanding of ECG with Raw Multi-lead Signal Modeling
We present Heartcare Suite, a multimodal comprehensive framework for finegrained electrocardiogram (ECG) understanding. It comprises three key components: (i) Heartcare-220K, a high-quality, structured, and comprehensive multimodal ECG dataset covering essential tasks such as disease diagnosis, waveform morphology analysis, and rhythm interpretation. (ii) Heartcare-Bench, a systematic and multi-dimensional benchmark designed to evaluate diagnostic intelligence and guide the optimization of Medi…

Blick in den Himmel … #Urlaub

Jeg tror ikke det er realistisk at Ukraine bliver medlem af EU indenfor en overskuelig fremtid. I hvert fald ikke uden nogle voldsomme justeringer af medlemskabets karakter. Den udhuling af landbrugsstŸtten som et ukrainsk medlemskab vil betyde, er helt uspiseligt for EU's landmænd. Og pga den udbredte korruption, kan det nok blive svært, at sælge ideen til EU's skattebetalere.

Morgenpost fra Europa: Nu har vi hørt mange argumenter for, at Ukraine skal være med i EU. Her er nogle af argumenterne imod
Er der slet ikke noget skidt ved, at Ukraine kommer med i EU? Hvis der er, hørtes det ikke i går i Aarhus.

Troisième lien.. donc on amènerait tous ces gens en plein milieu d'artères déjŠ congestionnées.. comme Laurentien ou Robert-Bourassa (du Vallon). Ça aide pas Š contourner Québec pour ceux allant Š l'Est. Encore plus de croissance pour Lebourgneuf.
Bref une solution de marde. (Presque toutes les solutions sont de marde de toute façon)

Nuclear C*-algebras: 99 problems
Christopher Schafhauser, Aaron Tikuisis, Stuart White
https://arxiv.org/abs/2506.10902 https://arxiv…

Nuclear C*-algebras: 99 problems
We present a collection of questions related to the structure and classification of nuclear C*-algebras.

This https://arxiv.org/abs/2506.05678 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Numerical Investigation of Sequence Modeling Theory using Controllable Memory Functions
The evolution of sequence modeling architectures, from recurrent neural networks and convolutional models to Transformers and structured state-space models, reflects ongoing efforts to address the diverse temporal dependencies inherent in sequential data. Despite this progress, systematically characterizing the strengths and limitations of these architectures remains a fundamental challenge.In this work, we propose a synthetic benchmarking framework to evaluate how effectively different sequenc…

Pedro the #Math Cat 🐈
#cats #CatsOfMastodon #Caturday

“As is the case with reading and writing a language, code is one of those things where if you don’t use it, you lose it. Early studies indicate that humans who use A.I. could become less creative over time.”
Early studies link: https://dl.acm.org/doi/abs/10.1145/3706598.3714198

Top500: the US retains the top three supercomputers with El Capitan, Frontier, and Aurora; the US has 173 of the top 500 to Europe's 163 and China's 46 (Doug Black/InsideHPC)
https://insidehpc.com/2025/06/top500-e

TOP500: El Capitan Stays on Top, US Holds Top 3 Supercomputers, Europe Expands in Leadership HPC
The new TOP500 list of the world’s most powerful supercomputers, released this morning at the ISC 2025 conference in Germany, shows an expanding European - Read more from Inside HPC & AI News.

This https://arxiv.org/abs/2506.05673 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Peer-Ranked Precision: Creating a Foundational Dataset for Fine-Tuning Vision Models from DataSeeds' Annotated Imagery
The development of modern Artificial Intelligence (AI) models, particularly diffusion-based models employed in computer vision and image generation tasks, is undergoing a paradigmatic shift in development methodologies. Traditionally dominated by a "Model Centric" approach, in which performance gains were primarily pursued through increasingly complex model architectures and hyperparameter optimization, the field is now recognizing a more nuanced "Data-Centric" approach. This emergent framework…

Das PDF zu #Knock #5 wird verteilt! #osr

This is absolutely fucked.. there's a public discovery feed of people talking to Meta AI.
How's that thing even existing
https://www.businessinsider.com/mark-zuckerberg-meta-ai-chatbot-discover-feed-depressing-why-20…

This https://arxiv.org/abs/2506.05526 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

On Fitting Flow Models with Large Sinkhorn Couplings
Flow models transform data gradually from one modality (e.g. noise) onto another (e.g. images). Such models are parameterized by a time-dependent velocity field, trained to fit segments connecting pairs of source and target points. When the pairing between source and target points is given, training flow models boils down to a supervised regression problem. When no such pairing exists, as is the case when generating data from noise, training flows is much harder. A popular approach lies in pick…

Precise Zero-Shot Pointwise Ranking with LLMs through Post-Aggregated Global Context Information
Kehan Long, Shasha Li, Chen Xu, Jintao Tang, Ting Wang
https://arxiv.org/abs/2506.10859

Precise Zero-Shot Pointwise Ranking with LLMs through Post-Aggregated Global Context Information
Recent advancements have successfully harnessed the power of Large Language Models (LLMs) for zero-shot document ranking, exploring a variety of prompting strategies. Comparative approaches like pairwise and listwise achieve high effectiveness but are computationally intensive and thus less practical for larger-scale applications. Scoring-based pointwise approaches exhibit superior efficiency by independently and simultaneously generating the relevance scores for each candidate document. Howeve…

This https://arxiv.org/abs/2506.05047 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Reliably detecting model failures in deployment without labels
The distribution of data changes over time; models operating operating in dynamic environments need retraining. But knowing when to retrain, without access to labels, is an open challenge since some, but not all shifts degrade model performance. This paper formalizes and addresses the problem of post-deployment deterioration (PDD) monitoring. We propose D3M, a practical and efficient monitoring algorithm based on the disagreement of predictive models, achieving low false positive rates under no…

#OrganicMaps wurde geforkt, weil es Probleme mit der Transparenz und den Finanzen zu geben scheint. Das neue Communityprojekt heißt #CoMaps #OSM

CoMaps
A community-led fork of Organic Maps. Reinforced with commitment to transparency, privacy and being not-for-profit.

Det ser ud som om, naturen gerne vil hjælpe menneskerne på vej mod en mere plantebaseret diæt, når de nu ikke selv kan. Ironisk nok ser det ud til at kŸdallergi primært rammer midaldrende mænd. Lige præcis den gruppe, der har sværest ved at opgive kŸdet. https://

 I USA giver aggressiv flåt kødallergi – skal danskerne frygte den?
Myndighederne i USA vurderer, at op mod en halv million amerikanere har fået kødallergi efter bid fra en bestemt flåt.

This https://arxiv.org/abs/2506.04168 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Horizon Reduction Makes RL Scalable
In this work, we study the scalability of offline reinforcement learning (RL) algorithms. In principle, a truly scalable offline RL algorithm should be able to solve any given problem, regardless of its complexity, given sufficient data, compute, and model capacity. We investigate if and how current offline RL algorithms match up to this promise on diverse, challenging, previously unsolved tasks, using datasets up to 1000x larger than typical offline RL datasets. We observe that despite scaling…

#Philippines workers outraged by union busting at #Lululemon sportswear factory

This https://arxiv.org/abs/2506.03703 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Learning-at-Criticality in Large Language Models for Quantum Field Theory and Beyond
Fundamental physics often confronts complex symbolic problems with few guiding exemplars or established principles. While artificial intelligence (AI) offers promise, its typical need for vast datasets to learn from hinders its use in these information-scarce frontiers. We introduce learning at criticality (LaC), a reinforcement learning (RL) scheme that tunes Large Language Models (LLMs) to a sharp learning transition, addressing this information scarcity. At this transition, LLMs achieve peak…

Constructing and Evaluating Declarative RAG Pipelines in PyTerrier
Craig Macdonald, Jinyuan Fang, Andrew Parry, Zaiqiao Meng
https://arxiv.org/abs/2506.10802

Constructing and Evaluating Declarative RAG Pipelines in PyTerrier
Search engines often follow a pipeline architecture, where complex but effective reranking components are used to refine the results of an initial retrieval. Retrieval augmented generation (RAG) is an exciting application of the pipeline architecture, where the final component generates a coherent answer for the users from the retrieved documents. In this demo paper, we describe how such RAG pipelines can be formulated in the declarative PyTerrier architecture, and the advantages of doing so. O…

This https://arxiv.org/abs/2506.03100 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds
Retrieval-augmented generation (RAG) has seen many empirical successes in recent years by aiding the LLM with external knowledge. However, its theoretical aspect has remained mostly unexplored. In this paper, we propose the first finite-sample generalization bound for RAG in in-context linear regression and derive an exact bias-variance tradeoff. Our framework views the retrieved texts as query-dependent noisy in-context examples and recovers the classical in-context learning (ICL) and standard…

Ritter gegen Drache
Graphite Prime lässt in #Knock #4 Ersteren gegen Letzteren antreten. Das System ist OSE. FIGHT! #pnpde

Every single time this happen, they are making sure creatives, artists, academics, etc are never setting foot to the US again.
Just a slow burn that is making sure US dominance in many fields will disappear. https://mstdn.social/@TechCrunch/114666117530646022

This https://arxiv.org/abs/2506.02475 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Comba: Improving Nonlinear RNNs with Closed-loop Control
Recent efficient sequence modeling methods such as Gated DeltaNet, TTT, and RWKV-7 have achieved performance improvements by supervising the recurrent memory management through Delta learning rule. Unlike previous state-space models (e.g., Mamba) and gated linear attentions (e.g., GLA), these models introduce interactions between the recurrent state and the key vector, resulting in a nonlinear recursive structure. In this paper, we first introduce the concept of Nonlinear RNNs with a comprehens…

This https://arxiv.org/abs/2506.02308 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

MINT: Multimodal Instruction Tuning with Multimodal Interaction Grouping
Recent advances in multimodal foundation models have achieved state-of-the-art performance across a range of tasks. These breakthroughs are largely driven by new pre-training paradigms that leverage large-scale, unlabeled multimodal data, followed by instruction fine-tuning on curated labeled datasets and high-quality prompts. While there is growing interest in scaling instruction fine-tuning to ever-larger datasets in both quantity and scale, our findings reveal that simply increasing the numb…

Willkommen in #Dithmarschen.
(Wolfsheim – Once In A Lifetime)

This https://arxiv.org/abs/2506.01790 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

$IF-GUIDE$: Influence Function-Guided Detoxification of LLMs
We study how training data contributes to the emergence of toxic behaviors in large-language models. Most prior work on reducing model toxicity adopts $reactive$ approaches, such as fine-tuning pre-trained (and potentially toxic) models to align them with human values. In contrast, we propose a $proactive$ approach$-$IF-Guide$-$which leverages influence functions to identify harmful tokens within any training data and suppress their impact during training. To this end, we first show that standa…

Contrastive Matrix Completion with Denoising and Augmented Graph Views for Robust Recommendation
Narges Nemati, Mostafa Haghir Chehreghani
https://arxiv.org/abs/2506.10658

Contrastive Matrix Completion with Denoising and Augmented Graph Views for Robust Recommendation
Matrix completion is a widely adopted framework in recommender systems, as predicting the missing entries in the user-item rating matrix enables a comprehensive understanding of user preferences. However, current graph neural network (GNN)-based approaches are highly sensitive to noisy or irrelevant edges--due to their inherent message-passing mechanisms--and are prone to overfitting, which limits their generalizability. To overcome these challenges, we propose a novel method called Matrix Comp…

This https://arxiv.org/abs/2506.01348 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Distributionally Robust Learning in Survival Analysis
We introduce an innovative approach that incorporates a Distributionally Robust Learning (DRL) approach into Cox regression to enhance the robustness and accuracy of survival predictions. By formulating a DRL framework with a Wasserstein distance-based ambiguity set, we develop a variant Cox model that is less sensitive to assumptions about the underlying data distribution and more resilient to model misspecification and data perturbations. By leveraging Wasserstein duality, we reformulate the …

This https://arxiv.org/abs/2506.00436 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Learning from Double Positive and Unlabeled Data for Potential-Customer Identification
In this study, we propose a method for identifying potential customers in targeted marketing by applying learning from positive and unlabeled data (PU learning). We consider a scenario in which a company sells a product and can observe only the customers who purchased it. Decision-makers seek to market products effectively based on whether people have loyalty to the company. Individuals with loyalty are those who are likely to remain interested in the company even without additional advertising…

Man ved, man er kommet til det ægte Danmark, når det fŸrste, der fanger ens opmærksomhed er en reklame for "Frikadellefest i Lohals" med Nikolaj og piloterne. #frikadellefest #hesselager #lohals

This https://arxiv.org/abs/2505.23868 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Noise-Robustness Through Noise: Asymmetric LoRA Adaption with Poisoning Expert
Current parameter-efficient fine-tuning methods for adapting pre-trained language models to downstream tasks are susceptible to interference from noisy data. Conventional noise-handling approaches either rely on laborious data pre-processing or employ model architecture modifications prone to error accumulation. In contrast to existing noise-process paradigms, we propose a noise-robust adaptation method via asymmetric LoRA poisoning experts (LoPE), a novel framework that enhances model robustne…

Conversational Search: From Fundamentals to Frontiers in the LLM Era
Fengran Mo, Chuan Meng, Mohammad Aliannejadi, Jian-Yun Nie
https://arxiv.org/abs/2506.10635

Conversational Search: From Fundamentals to Frontiers in the LLM Era
Conversational search enables multi-turn interactions between users and systems to fulfill users' complex information needs. During this interaction, the system should understand the users' search intent within the conversational context and then return the relevant information through a flexible, dialogue-based interface. The recent powerful large language models (LLMs) with capacities of instruction following, content generation, and reasoning, attract significant attention and advancements, …

This https://arxiv.org/abs/2505.22772 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Calibrated Value-Aware Model Learning with Stochastic Environment Models
The idea of value-aware model learning, that models should produce accurate value estimates, has gained prominence in model-based reinforcement learning. The MuZero loss, which penalizes a model's value function prediction compared to the ground-truth value function, has been utilized in several prominent empirical works in the literature. However, theoretical investigation into its strengths and weaknesses is limited. In this paper, we analyze the family of value-aware model learning losses, w…

#Wordle 1,445 5/6*
⬜⬜⬜⬜⬜ <1% of 209,367 (534)
⬜⬜🟨🟨🟨 0 of 52 (8)
🟨🟨⬜🟨🟩 0 of 0 (1)
🟩🟩⬜🟩🟩 0 of 0 (1)
🟩🟩🟩🟩🟩
WordleBot
Skill 68/99
Luck 48/99
Well I saw a couple of complaints about today's wordle before I started, which is part of what prompted my 4th guess, and I have to say I sorta agree.

This https://arxiv.org/abs/2505.19038 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Turb-L1: Achieving Long-term Turbulence Tracing By Tackling Spectral Bias
Accurately predicting the long-term evolution of turbulence is crucial for advancing scientific understanding and optimizing engineering applications. However, existing deep learning methods face significant bottlenecks in long-term autoregressive prediction, which exhibit excessive smoothing and fail to accurately track complex fluid dynamics. Our extensive experimental and spectral analysis of prevailing methods provides an interpretable explanation for this shortcoming, identifying Spectral …

This https://arxiv.org/abs/2505.18565 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Learning Fluid-Structure Interaction Dynamics with Physics-Informed Neural Networks and Immersed Boundary Methods
We introduce neural network architectures that combine physics-informed neural networks (PINNs) with the immersed boundary method (IBM) to solve fluid-structure interaction (FSI) problems. Our approach features two distinct architectures: a Single-FSI network with a unified parameter space, and an innovative Eulerian-Lagrangian network that maintains separate parameter spaces for fluid and structure domains. We study each architecture using standard Tanh and adaptive B-spline activation functio…

This https://arxiv.org/abs/2505.18344 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Sample Complexity of Diffusion Model Training Without Empirical Risk Minimizer Access
Diffusion models have demonstrated state-of-the-art performance across vision, language, and scientific domains. Despite their empirical success, prior theoretical analyses of the sample complexity suffer from poor scaling with input data dimension or rely on unrealistic assumptions such as access to exact empirical risk minimizers. In this work, we provide a principled analysis of score estimation, establishing a sample complexity bound of $\widetilde{\mathcal{O}}(ε^{-6})$. Our approach lever…

Macro Graph of Experts for Billion-Scale Multi-Task Recommendation
Hongyu Yao, Zijin Hong, Hao Chen, Yuanchen Bei, Zhiqing Li, Qijie Shen, Zuobin Ying, Huan Gong, Feiran Huang
https://arxiv.org/abs/2506.10520

Macro Graph of Experts for Billion-Scale Multi-Task Recommendation
Graph-based multi-task learning at billion-scale presents a significant challenge, as different tasks correspond to distinct billion-scale graphs. Traditional multi-task learning methods often neglect these graph structures, relying solely on individual user and item embeddings. However, disregarding graph structures overlooks substantial potential for improving performance. In this paper, we introduce the Macro Graph of Expert (MGOE) framework, the first approach capable of leveraging macro gr…

This https://arxiv.org/abs/2505.18300 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Beyond Self-Repellent Kernels: History-Driven Target Towards Efficient Nonlinear MCMC on General Graphs
We propose a history-driven target (HDT) framework in Markov Chain Monte Carlo (MCMC) to improve any random walk algorithm on discrete state spaces, such as general undirected graphs, for efficient sampling from target distribution $\boldsymbolμ$. With broad applications in network science and distributed optimization, recent innovations like the self-repellent random walk (SRRW) achieve near-zero variance by prioritizing under-sampled states through transition kernel modifications based on pa…

This https://arxiv.org/abs/2505.17282 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Attention with Trained Embeddings Provably Selects Important Tokens
Token embeddings play a crucial role in language modeling but, despite this practical relevance, their theoretical understanding remains limited. Our paper addresses the gap by characterizing the structure of embeddings obtained via gradient descent. Specifically, we consider a one-layer softmax attention model with a linear head for binary classification, i.e., $\texttt{Softmax}( p^\top E_X^\top ) E_X v = \frac{ \sum_{i=1}^T \exp(p^\top E_{x_i}) E_{x_i}^\top v}{\sum_{j=1}^T \exp(p^\top E_{x_{j…

This https://arxiv.org/abs/2505.16481 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Neighbour-Driven Gaussian Process Variational Autoencoders for Scalable Structured Latent Modelling
Gaussian Process (GP) Variational Autoencoders (VAEs) extend standard VAEs by replacing the fully factorised Gaussian prior with a GP prior, thereby capturing richer correlations among latent variables. However, performing exact GP inference in large-scale GPVAEs is computationally prohibitive, often forcing existing approaches to rely on restrictive kernel assumptions or large sets of inducing points. In this work, we propose a neighbour-driven approximation strategy that exploits local adjace…

SHORE: A Long-term User Lifetime Value Prediction Model in Digital Games
Shuaiqi Sun, Congde Yuan, Haoqiang Yang, Mengzhuo Guo, Guiying Wei, Jiangbo Tian
https://arxiv.org/abs/2506.10487

SHORE: A Long-term User Lifetime Value Prediction Model in Digital Games
In digital gaming, long-term user lifetime value (LTV) prediction is essential for monetization strategy, yet presents major challenges due to delayed payment behavior, sparse early user data, and the presence of high-value outliers. While existing models typically rely on either short-cycle observations or strong distributional assumptions, such approaches often underestimate long-term value or suffer from poor robustness. To address these issues, we propose SHort-cycle auxiliary with Order-pr…

This https://arxiv.org/abs/2505.15030 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Harnessing On-Device Large Language Model: Empirical Results and Implications for AI PC
The increasing deployment of Large Language Models (LLMs) on edge devices, driven by model advancements and hardware improvements, offers significant privacy benefits. However, these on-device LLMs inherently face performance limitations due to reduced model capacity and necessary compression techniques. To address this, we introduce a systematic methodology -- encompassing model capability, development efficiency, and system resources -- for evaluating on-device LLMs. Our comprehensive evaluat…

This https://arxiv.org/abs/2505.11864 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Learning Pareto-Optimal Rewards from Noisy Preferences: A Framework for Multi-Objective Inverse Reinforcement Learning
As generative agents become increasingly capable, alignment of their behavior with complex human values remains a fundamental challenge. Existing approaches often simplify human intent through reduction to a scalar reward, overlooking the multi-faceted nature of human feedback. In this work, we introduce a theoretical framework for preference-based Multi-Objective Inverse Reinforcement Learning (MO-IRL), where human preferences are modeled as latent vector-valued reward functions. We formalize …

This https://arxiv.org/abs/2505.11862 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Q-Policy: Quantum-Enhanced Policy Evaluation for Scalable Reinforcement Learning
We propose Q-Policy, a hybrid quantum-classical reinforcement learning (RL) framework that mathematically accelerates policy evaluation and optimization by exploiting quantum computing primitives. Q-Policy encodes value functions in quantum superposition, enabling simultaneous evaluation of multiple state-action pairs via amplitude encoding and quantum parallelism. We introduce a quantum-enhanced policy iteration algorithm with provable polynomial reductions in sample complexity for the evaluat…

La Caisse de dépôt finance-t-elle un génocide Š Gaza ?
https://www.lapresse.ca/dialogue/chroniques/2025-07-10/on-a-pose-la-question-pour-vous/la-caisse-finance-t-elle-un-genocide-a-gaza.php

This https://arxiv.org/abs/2505.11370 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Understanding Nonlinear Implicit Bias via Region Counts in Input Space
One explanation for the strong generalization ability of neural networks is implicit bias. Yet, the definition and mechanism of implicit bias in non-linear contexts remains little understood. In this work, we propose to characterize implicit bias by the count of connected regions in the input space with the same predicted label. Compared with parameter-dependent metrics (e.g., norm or normalized margin), region count can be better adapted to nonlinear, overparameterized models, because it is de…

LightKG: Efficient Knowledge-Aware Recommendations with Simplified GNN Architecture
Yanhui Li, Dongxia Wang, Zhu Sun, Haonan Zhang, Huizhong Guo
https://arxiv.org/abs/2506.10347

LightKG: Efficient Knowledge-Aware Recommendations with Simplified GNN Architecture
Recently, Graph Neural Networks (GNNs) have become the dominant approach for Knowledge Graph-aware Recommender Systems (KGRSs) due to their proven effectiveness. Building upon GNN-based KGRSs, Self-Supervised Learning (SSL) has been incorporated to address the sparity issue, leading to longer training time. However, through extensive experiments, we reveal that: (1)compared to other KGRSs, the existing GNN-based KGRSs fail to keep their superior performance under sparse interactions even with S…

This https://arxiv.org/abs/2505.07614 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Trial and Trust: Addressing Byzantine Attacks with Comprehensive Defense Strategy
Recent advancements in machine learning have improved performance while also increasing computational demands. While federated and distributed setups address these issues, their structure is vulnerable to malicious influences. In this paper, we address a specific threat, Byzantine attacks, where compromised clients inject adversarial updates to derail global convergence. We combine the trust scores concept with trial function methodology to dynamically filter outliers. Our methods address the c…

This https://arxiv.org/abs/2505.04104 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Position: We Need Responsible, Application-Driven (RAD) AI Research
This position paper argues that achieving meaningful scientific and societal advances with artificial intelligence (AI) requires a responsible, application-driven approach (RAD) to AI research. As AI is increasingly integrated into society, AI researchers must engage with the specific contexts where AI is being applied. This includes being responsive to ethical and legal considerations, technical and societal constraints, and public discourse. We present the case for RAD-AI to drive research th…

#Wordle 1,444 2/6*
🟩🟩⬜⬜🟨 <1% of 216,498 (2)
🟩🟩🟩🟩🟩 37% of 740
WordleBot
Skill 96/99
Luck 86/99
I was desperately trying to find ANY word besides the answer, but finally had to go with it.
Now that bot tells me there was another word and what it is, I'm surprised it didn't occur to me. Bot says it would have picked the other word. Not sure what I'd have done if I thought of it.

Diese Woche gibt's keine Sendung, ich hab Uurrllaaauub.
Ich sammle aber bereits für eine weitere #KleineEchos-Sondersendung: Tributes to Tributes, alles Coverversionen. 🦇🖤

This https://arxiv.org/abs/2505.01997 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach
One of the key technologies for the success of Large Language Models (LLMs) is preference alignment. However, a notable side effect of preference alignment is poor calibration: while the pre-trained models are typically well-calibrated, LLMs tend to become poorly calibrated after alignment with human preferences. In this paper, we investigate why preference alignment affects calibration and how to address this issue. For the first question, we observe that the preference collapse issue in align…

This https://arxiv.org/abs/2505.01903 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

LookAlike: Consistent Distractor Generation in Math MCQs
Large language models (LLMs) are increasingly used to generate distractors for multiple-choice questions (MCQs), especially in domains like math education. However, existing approaches are limited in ensuring that the generated distractors are consistent with common student errors. We propose LookAlike, a method that improves error-distractor consistency via preference optimization. Our two main innovations are: (a) mining synthetic preference pairs from model inconsistencies, and (b) alternati…

An Analysis of Datasets, Metrics and Models in Keyphrase Generation
Florian Boudin, Akiko Aizawa
https://arxiv.org/abs/2506.10346 https://

An Analysis of Datasets, Metrics and Models in Keyphrase Generation
Keyphrase generation refers to the task of producing a set of words or phrases that summarises the content of a document. Continuous efforts have been dedicated to this task over the past few years, spreading across multiple lines of research, such as model architectures, data resources, and use-case scenarios. Yet, the current state of keyphrase generation remains unknown as there has been no attempt to review and analyse previous work. In this paper, we bridge this gap by presenting an analys…

Très triste de voir Montréal dans une grève de la #STM
Toronto a passé Š un cheveux l’an passé d’avoir une grève. La mairesse Chow a tout fait pour l’empêcher, ça été annulé de justesse quelques heures avant le début de la grève. Elle avait compris qu’un système déjŠ affaibli par COVID ne se remettrait pas d’une autre baisse d’achalandage et qu’il fallait Š tout pris ramener la clientèl…

This https://arxiv.org/abs/2505.00968 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Tree-Sliced Wasserstein Distance with Nonlinear Projection
Tree-Sliced methods have recently emerged as an alternative to the traditional Sliced Wasserstein (SW) distance, replacing one-dimensional lines with tree-based metric spaces and incorporating a splitting mechanism for projecting measures. This approach enhances the ability to capture the topological structures of integration domains in Sliced Optimal Transport while maintaining low computational costs. Building on this foundation, we propose a novel nonlinear projectional framework for the Tre…

This https://arxiv.org/abs/2505.00546 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Directly Forecasting Belief for Reinforcement Learning with Delays
Reinforcement learning (RL) with delays is challenging as sensory perceptions lag behind the actual events: the RL agent needs to estimate the real state of its environment based on past observations. State-of-the-art (SOTA) methods typically employ recursive, step-by-step forecasting of states. This can cause the accumulation of compounding errors. To tackle this problem, our novel belief estimation method, named Directly Forecasting Belief Transformer (DFBT), directly forecasts states from ob…

This https://arxiv.org/abs/2505.00533 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Test-time Correlation Alignment
Deep neural networks often degrade under distribution shifts. Although domain adaptation offers a solution, privacy constraints often prevent access to source data, making Test-Time Adaptation (TTA, which adapts using only unlabeled test data) increasingly attractive. However, current TTA methods still face practical challenges: (1) a primary focus on instance-wise alignment, overlooking CORrelation ALignment (CORAL) due to missing source correlations; (2) complex backpropagation operations for…

Genüsslich eine warmen Kakao schlürfen – beste. (Symbol-GIF)

Context-Adaptive Graph Neural Networks for Next POI Recommendation
Yu Lei, Limin Shen, Zhu Sun, Tiantian He, Yew-Soon Ong
https://arxiv.org/abs/2506.10329 …

Context-Adaptive Graph Neural Networks for Next POI Recommendation
Next Point-of-Interest (POI) recommendation is a critical task in location-based services, aiming to predict users' next visits based on their check-in histories. While many existing methods leverage Graph Neural Networks (GNNs) to incorporate collaborative information and improve recommendation accuracy, most of them model each type of context using separate graphs, treating different factors in isolation. This limits their ability to model the co-influence of multiple contextual factors on us…

This https://arxiv.org/abs/2505.00347 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Pushing the Limits of Low-Bit Optimizers: A Focus on EMA Dynamics
The rapid scaling of models has led to prohibitively high training and fine-tuning costs. A major factor accounting for memory consumption is the widespread use of stateful optimizers (e.g., Adam), which maintain auxiliary information of even 2x the model size in order to achieve optimal convergence. We therefore present SOLO in this work to spawn a novel type of optimizer that requires an extremely light memory footprint. While previous efforts have achieved certain success in 8-bit or 4-bit c…

This https://arxiv.org/abs/2504.13416 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings
Given how large parts of publicly available text are crawled to pretrain large language models (LLMs), data creators increasingly worry about the inclusion of their proprietary data for model training without attribution or licensing. Their concerns are also shared by benchmark curators whose test-sets might be compromised. In this paper, we present STAMP, a framework for detecting dataset membership-i.e., determining the inclusion of a dataset in the pretraining corpora of LLMs. Given an origi…

This https://arxiv.org/abs/2504.13151 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

MIB: A Mechanistic Interpretability Benchmark
How can we know whether new mechanistic interpretability methods achieve real improvements? In pursuit of lasting evaluation standards, we propose MIB, a Mechanistic Interpretability Benchmark, with two tracks spanning four tasks and five models. MIB favors methods that precisely and concisely recover relevant causal pathways or causal variables in neural language models. The circuit localization track compares methods that locate the model components - and connections between them - most impor…

This https://arxiv.org/abs/2504.12849 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

FedX: Adaptive Model Decomposition and Quantization for IoT Federated Learning
Federated Learning (FL) allows collaborative training among multiple devices without data sharing, thus enabling privacy-sensitive applications on mobile or Internet of Things (IoT) devices, such as mobile health and asset tracking. However, designing an FL system with good model utility that works with low computation/communication overhead on heterogeneous, resource-constrained mobile/IoT devices is challenging. To address this problem, this paper proposes FedX, a novel adaptive model decompo…

Towards Understanding Bias in Synthetic Data for Evaluation
Hossein A. Rahmani, Varsha Ramineni, Nick Craswell, Bhaskar Mitra, Emine Yilmaz
https://arxiv.org/abs/2506.10301

Towards Understanding Bias in Synthetic Data for Evaluation
Test collections are crucial for evaluating Information Retrieval (IR) systems. Creating a diverse set of user queries for these collections can be challenging, and obtaining relevance judgments, which indicate how well retrieved documents match a query, is often costly and resource-intensive. Recently, generating synthetic datasets using Large Language Models (LLMs) has gained attention in various applications. While previous work has used LLMs to generate synthetic queries or documents to imp…

Soo cool, dass Wormhole Dateien ggf. über das lokale Netzwerk schickt. 🫶🏻

This https://arxiv.org/abs/2504.11284 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Bipartite Ranking From Multiple Labels: On Loss Versus Label Aggregation
Bipartite ranking is a fundamental supervised learning problem, with the goal of learning a ranking over instances with maximal Area Under the ROC Curve (AUC) against a single binary target label. However, one may often observe multiple binary target labels, e.g., from distinct human annotators. How can one synthesize such labels into a single coherent ranking? In this work, we formally analyze two approaches to this problem -- loss aggregation and label aggregation -- by characterizing their B…

[2025-06-13 Fri (UTC), 10 new articles found for cs.IR Information Retrieval]
toXiv_bot_toot

#Wordle 1,443 6/6*
⬜🟩🟩⬜⬜ <1% of 214,772 (26)
⬜🟩🟩⬜🟩 13% of 8 (3)
⬜🟩🟩⬜🟩 <1% of 2,846 (3)
⬜🟩🟩🟩🟩 13% of 2,851 (2)
⬜🟩🟩🟩🟩 34% of 769 (1)
🟩🟩🟩🟩🟩 95% of 1,442
WordleBot
Skill 75/99
Luck 50/99
Well that was close. I don't think there were any other words to try...oops I see, user error on 3rd guess, and then yes my last guess was the only word left.

WHOA! Insgesamt knapp 8 Stunden für den Director's Cut der beiden #RebelMoon-Filme. Gerade den zweiten zu Ende geschaut.

Replaced article(s) found for cs.IR. https://arxiv.org/list/cs.IR/new/
[1/1]:
Causality-Inspired Fair Representation Learning for Multimodal Recommendation

Mein #InkPadXPro-#ENote ist ein häufiger Begleiter geworden und hat Papiernotizen bei mir ersetzt. 🫶🏻