Tootfinder

Instance-level Performance Prediction for Long-form Generation Tasks
Chi-Yang Hsu, Alexander Braylan, Yiheng Su, Omar Alonso, Matthew Lease
https://arxiv.org/abs/2509.07309 http…

Instance-level Performance Prediction for Long-form Generation Tasks
We motivate and share a new benchmark for instance-level performance prediction of long-form generation tasks having multi-faceted, fine-grained quality metrics. Our task-, model- and metric-agnostic formulation predicts continuous evaluation metric scores given only black-box model inputs and outputs. Beyond predicting point estimates of metric scores, the benchmark also requires inferring prediction intervals to quantify uncertainty around point estimates. Evaluation spans 11 long-form datase…

SGS-3D: High-Fidelity 3D Instance Segmentation via Reliable Semantic Mask Splitting and Growing
Chaolei Wang, Yang Luo, Jing Du, Siyu Chen, Yiping Chen, Ting Han
https://arxiv.org/abs/2509.05144

SGS-3D: High-Fidelity 3D Instance Segmentation via Reliable Semantic Mask Splitting and Growing
Accurate 3D instance segmentation is crucial for high-quality scene understanding in the 3D vision domain. However, 3D instance segmentation based on 2D-to-3D lifting approaches struggle to produce precise instance-level segmentation, due to accumulated errors introduced during the lifting process from ambiguous semantic guidance and insufficient depth constraints. To tackle these challenges, we propose splitting and growing reliable semantic mask for high-fidelity 3D instance segmentation (SGS…

Does anbyody know about an instance of @…, that is open for registration and federated? I would really like to try it out in the wider #Fediverse.
#Bonfire

Berlin, 1933.

Walking in the #Schwarzwald :
More to come soon (Proudly served from my own Peertube instance without ads)
https://video.franzgraf.de/w/dGxHeu31jaak8fTrQoXHoX

Instance shutdown notice

Whops, the @… crashed today as there's been a new #panoramax instance, for Wales, popping up over night!
It should run again normally tomorrow, it happened as there's a temporary mismatch between statistics that the meta-federation delivers and the actual number of instances 😂
https://mapstodon.space/@panoramax/115343425761616690

One other thing, while we don't claim that our mixed-effects logit model is the perfect way to account for non-independence between languages, we don't think it's correct, as Xia & Lindell assert, to just claim that our results are "counterintuitive", the fix-eff estimates are "unreliable" and that the high model fits are "unrealistic." Whether a mix model better captures the data-generat. process is ultimately an empirical question, not one to be decided by assertion. Take, for instance, our finding that once random effects for either subregion or language family are included, the estimated effect of L1_population reverses direction—from the negative value reported by Xia & Lindell et al. to a positive one.

A deep multiple instance learning approach based on coarse labels for high-resolution land-cover mapping
Gianmarco Perantoni, Lorenzo Bruzzone
https://arxiv.org/abs/2510.06769 h…

A deep multiple instance learning approach based on coarse labels for high-resolution land-cover mapping
The quantity and the quality of the training labels are central problems in high-resolution land-cover mapping with machine-learning-based solutions. In this context, weak labels can be gathered in large quantities by leveraging on existing low-resolution or obsolete products. In this paper, we address the problem of training land-cover classifiers using high-resolution imagery (e.g., Sentinel-2) and weak low-resolution reference data (e.g., MODIS -derived land-cover maps). Inspired by recent w…

Public service announcement:
I am blocking the babka.social instance as the person who runs it (Serge) is a Zionist and a genocide/denier, who conflates being Jewish with being Zionist (“Zionism is a belief that more than 80% of Jews have. Talking about Zionists is talking about Jews.” – https://babka.social/@serge/1151605…

The #gnome #bug reporter still wants to push reports onto bugzilla that has been replaced by their #gitlab instance.
Is that a known issue?
Couldn't find any reference online, how that will change in…

Obviously there's still work to be done in the Wayland session of KDE Plasma 6 on FreeBSD.
Let's see what'd be the best way to 'report' those oddities.
For instance: the volume icon shows and tells a disconnect from the sound service. Nevertheless it's working fine.
Those little niggles 🥳
#freebsd

fediverse: Fediverse network (2018)
An early snapshot of the federation network among web publishers using the ActivityPub protocol. Nodes are instances, and a directed edge exists if an instance follows another instance.
This network has 4860 nodes and 484164 edges.
Tags: Social, Online, Information
https://ne…

Existence and nonexistence of commutativity gadgets for entangled CSPs
Eric Culf, Josse van Dobben de Bruyn, Matthijs Vernooij, Peter Zeman
https://arxiv.org/abs/2509.07835 http…

Existence and nonexistence of commutativity gadgets for entangled CSPs
Commutativity gadgets allow NP-hardness proofs for classical constraint satisfaction problems (CSPs) to be carried over to undecidability proofs for the corresponding entangled CSPs. This has been done, for instance, for NP-complete boolean CSPs and 3-colouring in the work of Culf and Mastel. For many CSPs over larger alphabets, including $k$-colouring when $k \geq 4$, it is not known whether or not commutativity gadgets exist, or if the entangled CSP is decidable. In this paper, we study commu…

CPT breaking in noncommutative Magueijo-Smolin model
S. Mignemi
https://arxiv.org/abs/2510.08024 https://arxiv.org/pdf/2510.08024

CPT breaking in noncommutative Magueijo-Smolin model
We review an instance of noncommutative geometry based on a specific realization of the model of doubly special relativity proposed by Magueijo and Smolin (MS) on noncommutative spacetime. In particular, we discuss the Hopf algebra associated to it, which has not been considered in the literature till now. We show that the momentum sector of this model can be viewed as a particular basis of the \kp model. An interesting property is that the MS Hamiltonian is not invariant under the reversal of …

Crossword: Adaptive Consensus for Dynamic Data-Heavy Workloads
Guanzhou Hu, Yiwei Chen, Andrea Arpaci-Dusseau, Remzi Arpaci-Dusseau
https://arxiv.org/abs/2509.07157 https://

Crossword: Adaptive Consensus for Dynamic Data-Heavy Workloads
We present Crossword, a flexible consensus protocol for dynamic data-heavy workloads, a rising challenge in the cloud where replication payload sizes span a wide spectrum and introduce sporadic bandwidth stress. Crossword applies per-instance erasure coding and distributes coded shards intelligently to reduce critical-path data transfer significantly when desirable. Unlike previous approaches that statically assign shards to servers, Crossword enables an adaptive tradeoff between the assignment…

The Mastodon iOS app now has options that allow quote posting and changing quote post options but my instance doesn't support it and I get amazing error messages like "Error 404" inside the Mastodon iOS app.
This lack of polish is unfortunately why "normal" people think Mastodon is clunky.

Near-optimal Rank Adaptive Inference of High Dimensional Matrices
Fr\'ed\'eric Zheng, Yassir Jedra, Alexandre Proutiere
https://arxiv.org/abs/2510.08117 https://

Near-optimal Rank Adaptive Inference of High Dimensional Matrices
We address the problem of estimating a high-dimensional matrix from linear measurements, with a focus on designing optimal rank-adaptive algorithms. These algorithms infer the matrix by estimating its singular values and the corresponding singular vectors up to an effective rank, adaptively determined based on the data. We establish instance-specific lower bounds for the sample complexity of such algorithms, uncovering fundamental trade-offs in selecting the effective rank: balancing the precis…

How to Reconfigure Your Alliances
Henning Fernau, Kevin Mann
https://arxiv.org/abs/2509.08798 https://arxiv.org/pdf/2509.08798

How to Reconfigure Your Alliances
Different variations of alliances in graphs have been introduced into the graph-theoretic literature about twenty years ago. More broadly speaking, they can be interpreted as groups that collaborate to achieve a common goal, for instance, defending themselves against possible attacks from outside. In this paper, we initiate the study of reconfiguring alliances. This means that, with the understanding of having an interconnection map given by a graph, we look at two alliances of the same size~$k…

MeanFlow-Accelerated Multimodal Video-to-Audio Synthesis via One-Step Generation
Xiaoran Yang, Jianxuan Yang, Xinyue Guo, Haoyu Wang, Ningning Pan, Gongping Huang
https://arxiv.org/abs/2509.06389

MeanFlow-Accelerated Multimodal Video-to-Audio Synthesis via One-Step Generation
A key challenge in synthesizing audios from silent videos is the inherent trade-off between synthesis quality and inference efficiency in existing methods. For instance, flow matching based models rely on modeling instantaneous velocity, inherently require an iterative sampling process, leading to slow inference speeds. To address this efficiency bottleneck, we introduce a MeanFlow-accelerated model that characterizes flow fields using average velocity, enabling one-step generation and thereby …

This is my regular reminder that "peertube.se" is run by The Nordic Resistance Movement, the fascists of the Nordic countries.
That instance has nothing to do with PeerTube itself, it’s just a instance run by scummy fascists who poison free spaces with their hate.
#Fascism #AntiFascism

MATRIX: Mask Track Alignment for Interaction-aware Video Generation
Siyoon Jin, Seongchan Kim, Dahyun Chung, Jaeho Lee, Hyunwook Choi, Jisu Nam, Jiyoung Kim, Seungryong Kim
https://arxiv.org/abs/2510.07310

MATRIX: Mask Track Alignment for Interaction-aware Video Generation
Video DiTs have advanced video generation, yet they still struggle to model multi-instance or subject-object interactions. This raises a key question: How do these models internally represent interactions? To answer this, we curate MATRIX-11K, a video dataset with interaction-aware captions and multi-instance mask tracks. Using this dataset, we conduct a systematic analysis that formalizes two perspectives of video DiTs: semantic grounding, via video-to-text attention, which evaluates whether n…

Standing up at desk, leaving office, never returning #health

Health Experts Recommend Standing Up At Desk, Leaving Office, Never Coming Back
ROCHESTER, MN—In an effort to help working individuals improve their fitness and well-being, experts at the Mayo Clinic issued a new set of health guidelines Thursday recommending that Americans stand up at their desk, leave their office, and never return. “Many Americans spend a minimum of eight hours per day sitting in an office, but we observed significant physical and mental health benefits in subjects after just one instance of standing up, walking out the door, and never coming back t…

OpenMulti: Open-Vocabulary Instance-Level Multi-Agent Distributed Implicit Mapping
Jianyu Dou, Yinan Deng, Jiahui Wang, Xingsi Tang, Yi Yang, Yufeng Yue
https://arxiv.org/abs/2509.01228

OpenMulti: Open-Vocabulary Instance-Level Multi-Agent Distributed Implicit Mapping
Multi-agent distributed collaborative mapping provides comprehensive and efficient representations for robots. However, existing approaches lack instance-level awareness and semantic understanding of environments, limiting their effectiveness for downstream applications. To address this issue, we propose OpenMulti, an open-vocabulary instance-level multi-agent distributed implicit mapping framework. Specifically, we introduce a Cross-Agent Instance Alignment module, which constructs an Instance…

The Keychain Problem: On Minimizing the Opportunity Cost of Uncertainty
Ramiro N. Deo-Campo Vuong, Robert Kleinberg, Aditya Prasad, Eric Xiao, Haifeng Xu
https://arxiv.org/abs/2509.06187

The Keychain Problem: On Minimizing the Opportunity Cost of Uncertainty
In this paper, we introduce a family of sequential decision-making problems, collectively called the Keychain Problem, that involve exploring a set of actions to maximize expected payoff when only a subset of actions are available in each stage. In an instance of the Keychain Problem, a locksmith faces a sequence of choices, each of which involves selecting one key from a specified subset (a keychain) to attempt to open a lock. Given a Bayesian prior on the effectiveness of keys, the locksmith'…

Periodic reminder for people interested in #HomeLab
There is a @… bot that replaces the old gup.pe homelab bot.
Mention it in your homelab posts and it will boost them. Follow it to see all the homelab posts it boosts that may not normally get federated to your instance.

Representation theory of the principal equivariant $\mathcal{W}$-algebra and Langlands duality
Damien Simon
https://arxiv.org/abs/2510.06990 https://arxiv.…

Representation theory of the principal equivariant $\mathcal{W}$-algebra and Langlands duality
The object of this article is to study some aspects of the quantum geometric Langlands program in the language of vertex algebras. We investigate the representation theory of the vertex algebra of chiral differential operators on a reductive group $\mathcal{D}_{G}^κ$ for generic levels. For instance we show that the geometric Satake equivalence degenerates. Then, we study the representation theory of the equivariant affine $\mathcal{W}$-algebra $\mathcal{W}_{G}^κ$, defined by Arakawa as the p…

Exploiting Phase Light Modulators for Low-SWaP Real-time Wavefront Correction at High-Resolution
John M. Bass, Jeffrey Y. Chen, Gregory M. Nero, Vijay Nafria, Youngsik Kim, Ivan B. Djordjevic, Yushi Kaneda, Thomas L. Koch, Muralidhar M. Balaji, Yuzuru Takashima, Florian Willomitzer
https://arxiv.org/abs/2509.05896

Exploiting Phase Light Modulators for Low-SWaP Real-time Wavefront Correction at High-Resolution
Wavefront correction and beam tracking are critical in applications such as long-range imaging through turbulence and free-space optical communication. For instance, adaptive optics systems are employed to correct wavefront distortions caused by atmospheric turbulence and optical misalignments, while beam tracking systems maintain alignment between separate devices in free-space communication scenarios. Current state-of-the-art approaches offer several high-performance solutions, each tailored …

A multi-point maximum principle to prove global Harnack inequalities for Schr\"odinger operators
Ben Andrews, Daniel Hauer, Jessica Slegers
https://arxiv.org/abs/2509.07575

A multi-point maximum principle to prove global Harnack inequalities for Schrödinger operators
In this article, we introduce a new methodology to prove global parabolic Harnack inequalities on Riemannian manifolds. We focus on presenting a new proof of the global pointwise Harnack inequality satisfied by positive solutions of the linear Schrödinger equation on a Riemannian manifold $M$ with nonnegative Ricci curvature, where the potential term $V$ is bounded from below. Our approach is based on a multi-point maximum principle argument. Standard proofs of this result (see, for instance, …

Shift Before You Learn: Enabling Low-Rank Representations in Reinforcement Learning
Bastien Dubail, Stefan Stojanovic, Alexandre Prouti\`ere
https://arxiv.org/abs/2509.05193 htt…

Shift Before You Learn: Enabling Low-Rank Representations in Reinforcement Learning
Low-rank structure is a common implicit assumption in many modern reinforcement learning (RL) algorithms. For instance, reward-free and goal-conditioned RL methods often presume that the successor measure admits a low-rank representation. In this work, we challenge this assumption by first remarking that the successor measure itself is not low-rank. Instead, we demonstrate that a low-rank structure naturally emerges in the shifted successor measure, which captures the system dynamics after bypa…

Quantum Theory of Exciton Magnetic Moment: Interaction and Topological Effects
Gurjyot Sethi, Jiawei Ruan, Fang Zhang, Weichen Tang, Chen Hu, Mit Naik, Steven G. Louie
https://arxiv.org/abs/2509.07284 …

Quantum Theory of Exciton Magnetic Moment: Interaction and Topological Effects
Combining magnetometry with optical spectroscopy has uncovered novel quantum phenomena and is emerging as a platform for quantum information science. Yet, the theory of magnetic response of excitons, correlated electron-hole pairs in semiconductors, remains incomplete due to insufficient treatment of electron-hole interaction and topological effects. In biased bilayer graphene, for instance, theoretical predictions of valley g-factor for p-excitons deviate from experiment by nearly an order of …

HAVE: Head-Adaptive Gating and ValuE Calibration for Hallucination Mitigation in Large Language Models
Xin Tong, Zhi Lin, Jingya Wang, Bo Jin
https://arxiv.org/abs/2509.06596 ht…

HAVE: Head-Adaptive Gating and ValuE Calibration for Hallucination Mitigation in Large Language Models
Large Language Models (LLMs) often produce hallucinations in retrieval-augmented or long-context generation, even when relevant evidence is present. This stems from two issues: head importance is treated as input-agnostic, and raw attention weights poorly reflect each token's true contribution. We present HAVE (Head-Adaptive Gating and ValuE Calibration), a parameter-free decoding framework that directly addresses both challenges. HAVE introduces head-adaptive gating, which performs instance-le…

Evaluating Multiple Instance Learning Strategies for Automated Sebocyte Droplet Counting
Maryam Adelipour, Gustavo Carneiro, Jeongkwon Kim
https://arxiv.org/abs/2509.04895 https…

Evaluating Multiple Instance Learning Strategies for Automated Sebocyte Droplet Counting
Sebocytes are lipid-secreting cells whose differentiation is marked by the accumulation of intracellular lipid droplets, making their quantification a key readout in sebocyte biology. Manual counting is labor-intensive and subjective, motivating automated solutions. Here, we introduce a simple attention-based multiple instance learning (MIL) framework for sebocyte image analysis. Nile Red-stained sebocyte images were annotated into 14 classes according to droplet counts, expanded via data augme…

So I had this terrible idea a few years ago to write some infrastructure automation that provisions a new compute instance, sets up secrets storage, configures IAM roles, authorizes the new instance to be able to provision new instance and roles via infra-as-code automation, and then the new instance tears down the instance and roles that created it, before then creating its own new compute instance, etc
Like a self-propagating glider in Conway's Game of Life, except with cloud inf…

I think he is trying to say he is an Avenger without realising he is the supervillain.
Also, does he know that while he is torrenting the world libraries into his bank account, you could set up for $10 a month your own Mastodon instance which is ten times better federated than his 'federated' Threads?

Provably data-driven projection method for quadratic programming
Anh Tuan Nguyen, Viet Anh Nguyen
https://arxiv.org/abs/2509.04524 https://arxiv.org/pdf/25…

Provably data-driven projection method for quadratic programming
Projection methods aim to reduce the dimensionality of the optimization instance, thereby improving the scalability of high-dimensional problems. Recently, Sakaue and Oki proposed a data-driven approach for linear programs (LPs), where the projection matrix is learned from observed problem instances drawn from an application-specific distribution of problems. We analyze the generalization guarantee for the data-driven projection matrix learning for convex quadratic programs (QPs). Unlike in LPs…

Vanishing Coefficients of q^{5n r} and q^{7n r} in Certain Infinite q-series Expansions
M. P. Thejitha, Anusree Anand, S. N. Fathima
https://arxiv.org/abs/2510.05929 https://

Vanishing Coefficients of q^{5n+r} and q^{7n+r} in Certain Infinite q-series Expansions
Motivated by the recent work of several authors on vanishing coefficients of the arithmetic progression in certain $q$-series expansion, we study some variants of these $q$-series and prove some comparable results. For instance, if $\sum_{n=0}^{\infty}c_1(n)q^n=\left(\pm q^2,\pm q^3; q^5\right)_\infty^2 \left( q, q^{14}; q^{15}\right)_\infty$, then $c_1(5n+3)=0$.

MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS
Mo Xuan, Zhang yue, Wu Weigang
https://arxiv.org/abs/2509.06362 https://arxiv.org/…

MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS
Model-as-a-Service (MaaS) platforms face diverse Service Level Objective (SLO) requirements stemming from various large language model (LLM) applications, manifested in contextual complexity, first-token latency, and between-token latency. On the other hand, an LLM instance, when configured with different parallelism strategies and inference batch sizes, exhibits distinct performance characteristics and can thus be used to serve different SLO requirements. However, current LLM inference systems…

hurhn. I just spun up a #forgejo instance via #docker container. That was much easier than anticipated. Well done #codeberg / forgejo teams!
Now to migrate all my

現在、mstdn.jpのサーバー情報を返すAPI（古い方 v1）がエラーになっています。
https://mstdn.jp/api/v1/instance
:mastodon_oops:
ちなみに正常に動くpawoo.netだとこんな内容になります。
https://pawoo.net/api/v1…

just discovered https://masto-fe.superseriousbusiness.org/ which you can hook up to a GTS instance but also a mastodon instance, which serves as a nice way to see what mastodon used to look like way back in the day. loving the columns!

just discovered https://masto-fe.superseriousbusiness.org/ which you can hook up to a GTS instance but also a mastodon instance, which serves as a nice way to see what mastodon used to look like way back in the day. loving the columns!

Leveraging Vision Transformers for Enhanced Classification of Emotions using ECG Signals
Pubudu L. Indrasiri, Bipasha Kashyap, Pubudu N. Pathirana
https://arxiv.org/abs/2510.05826

Leveraging Vision Transformers for Enhanced Classification of Emotions using ECG Signals
Biomedical signals provide insights into various conditions affecting the human body. Beyond diagnostic capabilities, these signals offer a deeper understanding of how specific organs respond to an individual's emotions and feelings. For instance, ECG data can reveal changes in heart rate variability linked to emotional arousal, stress levels, and autonomic nervous system activity. This data offers a window into the physiological basis of our emotional states. Recent advancements in the field d…

Hey #Apple #MacAdmins - remember how getting warranty information via API via GSX is so challenging and requires a lot of hoops to jump through?
Guess what's free today in your Apple Business Manager / Apple School Manager instance:
https://developer.apple.com/documentation/appleschoolmanagerapi/applecarecoverage/attributes-data.dictionary
https://developer.apple.com/documentation/appleschoolmanagerapi/get-orgdevice-information
https://developer.apple.com/documentation/apple-school-and-business-manager-api

RE: https://en.osm.town/@seav/115501954665215610
Don’t mind this. I just noticed that our instance finally has quote posting 🎉 and I’m quoting myself to see how this appears on all the clients (like @…

I wonder how hard it would be to fabricate something that might (inadvertently, of course) disrupt the functioning of a drone that was, for instance, flying around a peaceful demonstration? I know it’s a federal felony (punishable by up to 20 years in prison) to shoot them down, or point a laser at them. But maybe something in a pocket, or backpack? So it’s not visible? #askingforafriend…

Well-Separated Pairs Decomposition Revisited
Sariel Har-Peled, Benjamin Raichel, Eliot W. Robson
https://arxiv.org/abs/2509.05997 https://arxiv.org/pdf/250…

Well-Separated Pairs Decomposition Revisited
We revisit the notion of WSPD (i.e., well-separated pairs-decomposition), presenting a new construction of WSPD for any finite metric space, and show that it is asymptotically instance-optimal in size. Next, we describe a new WSPD construction for the weighted unit-distance metric in the plane, and show a bound $O( \varepsilon^{-2} n \log n)$ on its size, improving by a factor of $1/\varepsilon^2$ over previous work. The new construction is arguably simpler and more elegant. We point out that…

👾 Unsupervised Instance Segmentation with Superpixels
#cs #arxiv

Unsupervised Instance Segmentation with Superpixels
Instance segmentation is essential for numerous computer vision applications, including robotics, human-computer interaction, and autonomous driving. Currently, popular models bring impressive performance in instance segmentation by training with a large number of human annotations, which are costly to collect. For this reason, we present a new framework that efficiently and effectively segments objects without the need for human annotations. Firstly, a MultiCut algorithm is applied to self-sup…

A Computer-Assisted Proof of the Optimal Density Bound for Pinwheel Covering
Akitoshi Kawamura, Yusuke Kobayashi
https://arxiv.org/abs/2510.06533 https://a…

A Computer-Assisted Proof of the Optimal Density Bound for Pinwheel Covering
In the covering version of the pinwheel scheduling problem, a daily task must be assigned to agents under the constraint that agent $i$ can perform the task at most once in any $a_i$-day interval. In this paper, we determine the optimal constant $α^* = 1.264\ldots {}$ such that every instance with $\sum_{i} \frac{1}{a_i} \ge α^*$ is schedulable. This resolves an open problem posed by Soejima and Kawamura (2020). Our proof combines Kawamura's (2024) techniques for the packing version with new …

New version of Android "Android 16 QPR1" is now out, that's supposed to be a minor quarterly release. No idea if they fixed all the bugs I've been finding. But they've changed the UI around. Again. For instance the icons showing WiFi and cellular signal strength have changed.
Maybe it's better, maybe it's worse, but I grow weary of these changes. Some images here.

bluesky to mastodon instance name ideas:
bluestadon
mastosky
greengrass
ThirdTimesTheCharm
JaysWish

NGL, all this shit with Jay (the CEO of BlueSky) has got me thinking REAL hard about finally spinning up a GoToSocial instance for myself on my Synology.

Overlap-aware segmentation for topological reconstruction of obscured objects
J. Schueler, H. M. Ara\'ujo, S. N. Balashov, J. E. Borg, C. Brew, F. M. Brunbauer, C. Cazzaniga, A. Cottle, D. Edgeman, C. D. Frost, F. Garcia, D. Hunt, M. Kastriotou, P. Knights, H. Kraus, A. Lindote, M. Lisowska, D. Loomba, E. Lopez Asamar, P. A. Majewski, T. Marley, C. McCabe, L. Millins, R. Nandakumar, T. Neep, F. Neves, K. Nikolopoulos, E. Oliveri, A. Roy, T. J. Sumner, E. Tilly, W. Thompson, M. A. V…

Overlap-aware segmentation for topological reconstruction of obscured objects
The separation of overlapping objects presents a significant challenge in scientific imaging. While deep learning segmentation-regression algorithms can predict pixel-wise intensities, they typically treat all regions equally rather than prioritizing overlap regions where attribution is most ambiguous. Recent advances in instance segmentation show that weighting regions of pixel overlap in training can improve segmentation boundary predictions in regions of overlap, but this idea has not yet be…

Cloudflare says attackers gained access to a Salesforce instance it uses for internal customer case management, as part of the Salesloft Drift breach (Sergiu Gatlan/BleepingComputer)
https://www.bleepingcomputer.com/news/secu

The Philadelphia Citizen, a decade-old nonprofit dedicated to solutions journalism, acquires Philadelphia Magazine, another instance of nonprofit consolidation (Sophie Culpepper/Nieman Lab)
https://www.niemanlab.org/2025/11/in-philadelphia-a-y…

Beginning to wonder about moving to a new instance in the indefinite vaguely near future, since IOCX admins seem to be a bit behind the curve (we're still on mastodon 4.3.7).
I poked them but havent heard back or even seen any posts from them in a while, which makes me wonder if I'm living on a ghost ship.
Anyone have suggestions on one that's generally friendly to cool EE research, OSS/OSH, infosec, etc stuff?

Scaling #Postgres
https://www.pgedge.com/blog/scaling-postgres

Messing the whole weekend with the WordPress instance of a friend. He's been using an old plugin for multiple languages. The plugin is abandoned since 2015 and doesn't support newer PHP versions. Wordpress and the other plugins is about to no longer support the old PHP version.
At first I thought about writing a conversion tool to another plugin. Spend some considerable time setting up a test environment as well. Eventually it turns out group of people forked the problematic p…

LMILAtt: A Deep Learning Model for Depression Detection from Social Media Users Enhanced by Multi-Instance Learning Based on Attention Mechanism
Yukun Yang
https://arxiv.org/abs/2509.26145

LMILAtt: A Deep Learning Model for Depression Detection from Social Media Users Enhanced by Multi-Instance Learning Based on Attention Mechanism
Depression is a major global public health challenge and its early identification is crucial. Social media data provides a new perspective for depression detection, but existing methods face limitations such as insufficient accuracy, insufficient utilization of time series features, and high annotation costs. To this end, this study proposes the LMILAtt model, which innovatively integrates Long Short-Term Memory autoencoders and attention mechanisms: firstly, the temporal dynamic features of us…

“What we seem to have here is yet another instance of a massive corporate entity capitulating to the emperor’s wishes in advance, but this one is particularly frustrating because there is less for the average consumer like you and me to do about it.” https://apple.news/AIOs-uVO9S62q7E2-cg0v2A

The Physics of Data and Tasks: Theories of Locality and Compositionality in Deep Learning
Alessandro Favero
https://arxiv.org/abs/2510.06106 https://arxiv.…

The Physics of Data and Tasks: Theories of Locality and Compositionality in Deep Learning
Deep neural networks have achieved remarkable success, yet our understanding of how they learn remains limited. These models can learn high-dimensional tasks, which is generally statistically intractable due to the curse of dimensionality. This apparent paradox suggests that learnable data must have an underlying latent structure. What is the nature of this structure? How do neural networks encode and exploit it, and how does it quantitatively impact performance - for instance, how does general…

Decent folks may want to block this libertarian, pro-genocide instance.
(libertarian.communitynetwork.space)
https://libertarian.communitynetwork.space/objects/0b38de6a-3cbe-4113-8fbb-25b17b6e5dfe

Korsier (@korsier@libertarian.communitynetwork.space)
@aral Well, she didn't learn her lesson the first time.

Because there's not enough evidence to charge them with a crime ... https://www.threads.com/@aaron.rupar/post/DQRkrYSCcsK

Aaron Rupar (@aaron.rupar) on Threads
Rand Paul: "In the one instance you're killed on sight. On the other instance, if you're captured, we just say, 'Oh well, we're gonna send you back to your country.' It doesn't make any sense."

The DOGE team at SSA might have violated FISMA and other laws by not following security protocols as spelled out in NIST's SP 800-53, which are mandatory for all government agencies.
It's no surprise then that a whistleblower is warning that we have lost the ability to see who is accessing 300 million Americans' most sensitive information after DOGE moved SSA data to their own Amazon cloud instance.
Thanks to John Skinner, former project lead for 18F, for his expert i…

Whistleblower: DOGE put Social Security database covering 300 million Americans on insecure cloud
The complaint accuses DOGE of bypassing security protocols to move Americans’ sensitive personal data outside federal oversight and onto an insecure AWS cloud instance, potentially violating established security practices and several laws.

RIP #WTF
https://lemmy-status.org/endpoints/_lemmy-wtf

Series C, Episode 04 - Dawn of the Gods
CALIPH: Welcome to Krandor, my friends. An artificial planet, which is the palace of the Lord Thaarn, Master of the Universe. I am the Caliph of Krandor. Among other things, it is my duty as the Lord Thaarn's chief executive, to negotiate a purchase price for your ship. We, uh, usually use this for rounding up runaway slaves. Oh, quite inappropriate in this instance, but it was nearest at the time. I do hope you understand.
TARRANT: We…

Crosslisted article(s) found for physics.comp-ph. https://arxiv.org/list/physics.comp-ph/new
[1/1]:
- Instance-Wise Adaptive Sampling for Dataset Construction in Approximating Inverse Problem Solutions
Jiequn Han, Kui Ren, Nathan Soedjak

The Role of Acoustic Instability in Cosmic-Ray Self-Confinement
Antonio Capanema, Pasquale Blasi, Emanuele Sobacchi
https://arxiv.org/abs/2510.04635 https://

The Role of Acoustic Instability in Cosmic-Ray Self-Confinement
Over the past decades, there has been growing observational and theoretical evidence that cosmic-ray-induced instabilities play an important role in both acceleration and transport of cosmic rays (CRs). For instance, the efficient acceleration of charged particles at supernova remnant shocks requires rapidly growing instabilities, so much so that none of the proposed processes seem sufficient to warrant acceleration to PeV energies. In this work, we investigate whether an acoustic instability t…

Why for all of us to take to heart?
Because we all need to remember that there are people in our circles for whom existence is resistance, which makes every single day a fight.
And we need to remember that it •matters• when we forcefully speak up for the humanity of others — or simply treat somebody who is vulnerable with basic decency and steadfast respect, in spite of the whole damned world.
And some days some little instance of one of those things — speaking up, decency, respect — that just feels like almost nothing in the moment might be the most important thing we do all day, and we won’t even know it.

Learning Global Representation from Queries for Vectorized HD Map Construction
Shoumeng Qiu, Xinrun Li, Yang Long, Xiangyang Xue, Varun Ojha, Jian Pu
https://arxiv.org/abs/2510.06969

Learning Global Representation from Queries for Vectorized HD Map Construction
The online construction of vectorized high-definition (HD) maps is a cornerstone of modern autonomous driving systems. State-of-the-art approaches, particularly those based on the DETR framework, formulate this as an instance detection problem. However, their reliance on independent, learnable object queries results in a predominantly local query perspective, neglecting the inherent global representation within HD maps. In this work, we propose \textbf{MapGR} (\textbf{G}lobal \textbf{R}epresent…

Co-Seg: Mutual Prompt-Guided Collaborative Learning for Tissue and Nuclei Segmentation
Qing Xu, Wenting Duan, Zhen Chen
https://arxiv.org/abs/2509.06740 https://

Co-Seg: Mutual Prompt-Guided Collaborative Learning for Tissue and Nuclei Segmentation
Histopathology image analysis is critical yet challenged by the demand of segmenting tissue regions and nuclei instances for tumor microenvironment and cellular morphology analysis. Existing studies focused on tissue semantic segmentation or nuclei instance segmentation separately, but ignored the inherent relationship between these two tasks, resulting in insufficient histopathology understanding. To address this issue, we propose a Co-Seg framework for collaborative tissue and nuclei segmenta…

I really want the quote post feature already on my instance so I can diss myself

Fair metric distortion for matching with preferences
Jabari Hastings, Prasanna Ramakrishnan
https://arxiv.org/abs/2510.05460 https://arxiv.org/pdf/2510.054…

Fair metric distortion for matching with preferences
We consider the matching problem in the metric distortion framework. There are $n$ agents and $n$ items occupying points in a shared metric space, and the goal is to design a matching mechanism that outputs a low-cost matching between the agents and items, using only agents' ordinal rankings of the candidates by distance. A mechanism has distortion $α$ if it always outputs a matching whose cost is within a factor of $α$ of the optimum, in every instance regardless of the metric space. Typic…

UrbanTwin: High-Fidelity Synthetic Replicas of Roadside Lidar Datasets
Muhammad Shahbaz, Shaurya Agarwal
https://arxiv.org/abs/2509.06781 https://arxiv.org…

UrbanTwin: High-Fidelity Synthetic Replicas of Roadside Lidar Datasets
This article presents UrbanTwin datasets - high-fidelity, realistic replicas of three public roadside lidar datasets: LUMPI, V2X-Real-IC, and TUMTraf-I. Each UrbanTwin dataset contains 10K annotated frames corresponding to one of the public datasets. Annotations include 3D bounding boxes, instance segmentation labels, and tracking IDs for six object classes, along with semantic segmentation labels for nine classes. These datasets are synthesized using emulated lidar sensors within realistic dig…

looking to #selfhost a #mastodon instance, anyone know any good options? #fediverse

Leveraging Analog Neutral Atom Quantum Computers for Diversified Pricing in Hybrid Column Generation Frameworks
C\'edrick Perron, Yves B\'erub\'e-Lauzi\`ere, Victor Drouin-Touchette
https://arxiv.org/abs/2510.04946

Leveraging Analog Neutral Atom Quantum Computers for Diversified Pricing in Hybrid Column Generation Frameworks
In this work, we develop new pulse designs and embedding strategies to improve the analog quantum subroutines of hybrid column generation (CG) algorithms based on neutral-atoms quantum computers (NAQCs). These strategies are designed to improve the quality and diversity of the samples generated. We apply these to an important combinatorial optimization (CO) problem in logistics, namely the fleet assignment. Depending on the instance tested, our quantum protocol has a performance that is either …

Video-Based MPAA Rating Prediction: An Attention-Driven Hybrid Architecture Using Contrastive Learning
Dipta Neogi, Nourash Azmine Chowdhury, Muhammad Rafsan Kabir, Mohammad Ashrafuzzaman Khan
https://arxiv.org/abs/2509.06826

Video-Based MPAA Rating Prediction: An Attention-Driven Hybrid Architecture Using Contrastive Learning
The rapid growth of visual content consumption across platforms necessitates automated video classification for age-suitability standards like the MPAA rating system (G, PG, PG-13, R). Traditional methods struggle with large labeled data requirements, poor generalization, and inefficient feature learning. To address these challenges, we employ contrastive learning for improved discrimination and adaptability, exploring three frameworks: Instance Discrimination, Contextual Contrastive Learning, …

Topological Protection in a Landau Flat Band at $\nu=7/11$, a Candidate Filling Factor for Unconventional Correlations
Waseem Hussain, Haoyun Huang, Loren N. Pfeiffer, Kenneth W. West, Kirk. W. Baldwin, G\'abor A. Cs\'athy
https://arxiv.org/abs/2510.05265

Topological Protection in a Landau Flat Band at $ν=7/11$, a Candidate Filling Factor for Unconventional Correlations
Strong interactions in Landau flat bands are known to stabilize correlated states that do not form in other types of flat bands. We report hallmarks of topological protection at the Landau level filling factor v=7/11 in a two-dimensional electron system. The $ν=7/11$ filling factor is the particle-hole conjugate of $ν=4/11$, a filling factor intensely studied for the possibility of realizing unconventional electronic correlations. Our data establishes a new instance for an unusual fractional …

little known fediverse tip: you can follow @PeerTube@<peertube instance> to get a feed of all videos on that instance! for instance, @…'s PeerTube instance is @…

fediverse: Fediverse network (2018)
An early snapshot of the federation network among web publishers using the ActivityPub protocol. Nodes are instances, and a directed edge exists if an instance follows another instance.
This network has 4860 nodes and 484164 edges.
Tags: Social, Online, Information
https://ne…

Steady-State Spread Bounds for Graph Diffusion via Laplacian Regularisation
Ardavan Rahimian
https://arxiv.org/abs/2510.04924 https://arxiv.org/pdf/2510.04…

Steady-State Spread Bounds for Graph Diffusion via Laplacian Regularisation
We study how far a diffusion process on a graph can drift from a designed starting pattern when that pattern is produced using Laplacian regularisation. Under standard stability conditions for undirected, entrywise nonnegative graphs, we give a closed-form, instance-specific upper bound on the steady-state spread, measured as the relative change between the final and initial profiles. The bound separates two effects: (i) an irreducible term determined by the graph's maximum node degree, and (ii…

WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning
Gagan Mundada, Yash Vishe, Amit Namburi, Xin Xu, Zachary Novack, Julian McAuley, Junda Wu
https://arxiv.org/abs/2509.04744

WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning
Recent advances in Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities across various vision-language tasks. However, their reasoning abilities in the multimodal symbolic music domain remain largely unexplored. We introduce WildScore, the first in-the-wild multimodal symbolic music reasoning and analysis benchmark, designed to evaluate MLLMs' capacity to interpret real-world music scores and answer complex musicological queries. Each instance in WildScore is sourc…

Learning from Majority Label: A Novel Problem in Multi-class Multiple-Instance Learning
Shiku Kaito, Shinnosuke Matsuo, Daiki Suehiro, Ryoma Bise
https://arxiv.org/abs/2509.04023

Learning from Majority Label: A Novel Problem in Multi-class Multiple-Instance Learning
The paper proposes a novel multi-class Multiple-Instance Learning (MIL) problem called Learning from Majority Label (LML). In LML, the majority class of instances in a bag is assigned as the bag-level label. The goal of LML is to train a classification model that estimates the class of each instance using the majority label. This problem is valuable in a variety of applications, including pathology image segmentation, political voting prediction, customer sentiment analysis, and environmental m…

Formal Framework for Quantum Advantage
Harry Buhrman, Niklas Galke, Konstantinos Meichanetzidis
https://arxiv.org/abs/2510.01953 https://arxiv.org/pdf/2510…

Formal Framework for Quantum Advantage
Motivated by notions of quantum heuristics and by average-case rather than worst-case algorithmic analysis, we define quantum computational advantage in terms of individual problem instances. Inspired by the classical notions of Kolmogorov complexity and instance complexity, we define their quantum versions. This allows us to define queasy instances of computational problems, like e.g. Satisfiability and Factoring, as those whose quantum instance complexity is significantly smaller than their c…

fediverse: Fediverse network (2018)
An early snapshot of the federation network among web publishers using the ActivityPub protocol. Nodes are instances, and a directed edge exists if an instance follows another instance.
This network has 4860 nodes and 484164 edges.
Tags: Social, Online, Information
https://ne…

There are a couple of anonymous cowards on Mastodon telling people that all Palestinians you see here are fake and that the Internet there doesn’t work at all and spamming the #fediblock hashtag to get my Mastodon instance defederated so they can silence me and the work we are doing with @…

Gaza Verified
We’ve personally had video conversations on Signal with the people from Gaza whose Mastodon accounts on the fediverse are listed here and we verify that their accounts are genuine. – Joy & Aral Balkan

MICACL: Multi-Instance Category-Aware Contrastive Learning for Long-Tailed Dynamic Facial Expression Recognition
Feng-Qi Cui, Zhen Lin, Xinlong Rao, Anyang Tong, Shiyao Li, Fei Wang, Changlin Chen, Bin Liu
https://arxiv.org/abs/2509.04344

MICACL: Multi-Instance Category-Aware Contrastive Learning for Long-Tailed Dynamic Facial Expression Recognition
Dynamic facial expression recognition (DFER) faces significant challenges due to long-tailed category distributions and complexity of spatio-temporal feature modeling. While existing deep learning-based methods have improved DFER performance, they often fail to address these issues, resulting in severe model induction bias. To overcome these limitations, we propose a novel multi-instance learning framework called MICACL, which integrates spatio-temporal dependency modeling and long-tailed contr…

fediverse: Fediverse network (2018)
An early snapshot of the federation network among web publishers using the ActivityPub protocol. Nodes are instances, and a directed edge exists if an instance follows another instance.
This network has 4860 nodes and 484164 edges.
Tags: Social, Online, Information
https://ne…

SL-SLR: Self-Supervised Representation Learning for Sign Language Recognition
Ariel Basso Madjoukeng, J\'er\^ome Fink, Pierre Poitier, Edith Belise Kenmogne, Benoit Frenay
https://arxiv.org/abs/2509.05188

SL-SLR: Self-Supervised Representation Learning for Sign Language Recognition
Sign language recognition (SLR) is a machine learning task aiming to identify signs in videos. Due to the scarcity of annotated data, unsupervised methods like contrastive learning have become promising in this field. They learn meaningful representations by pulling positive pairs (two augmented versions of the same instance) closer and pushing negative pairs (different from the positive pairs) apart. In SLR, in a sign video, only certain parts provide information that is truly useful for its r…

Towards PerSense : Advancing Training-Free Personalized Instance Segmentation in Dense Images
Muhammad Ibraheem Siddiqui, Muhammad Umer Sheikh, Hassan Abid, Kevin Henry, Muhammad Haris Khan
https://arxiv.org/abs/2508.14660

Towards PerSense++: Advancing Training-Free Personalized Instance Segmentation in Dense Images
Segmentation in dense visual scenes poses significant challenges due to occlusions, background clutter, and scale variations. To address this, we introduce PerSense, an end-to-end, training-free, and model-agnostic one-shot framework for Personalized instance Segmentation in dense images. PerSense employs a novel Instance Detection Module (IDM) that leverages density maps (DMs) to generate instance-level candidate point prompts, followed by a Point Prompt Selection Module (PPSM) that filters fa…

Instance-Aware Robust Consistency Regularization for Semi-Supervised Nuclei Instance Segmentation
Zenan Lin, Wei Li, Jintao Chen, Zihao Wu, Wenxiong Kang, Changxin Gao, Liansheng Wang, Jin-Gang Yu
https://arxiv.org/abs/2510.09329

Instance-Aware Robust Consistency Regularization for Semi-Supervised Nuclei Instance Segmentation
Nuclei instance segmentation in pathological images is crucial for downstream tasks such as tumor microenvironment analysis. However, the high cost and scarcity of annotated data limit the applicability of fully supervised methods, while existing semi-supervised methods fail to adequately regularize consistency at the instance level, lack leverage of the inherent prior knowledge of pathological structures, and are prone to introducing noisy pseudo-labels during training. In this paper, we propo…

C$^2$MIL: Synchronizing Semantic and Topological Causalities in Multiple Instance Learning for Robust and Interpretable Survival Analysis
Min Cen, Zhenfeng Zhuang, Yuzhe Zhang, Min Zeng, Baptiste Magnier, Lequan Yu, Hong Zhang, Liansheng Wang
https://arxiv.org/abs/2509.20152

C$^2$MIL: Synchronizing Semantic and Topological Causalities in Multiple Instance Learning for Robust and Interpretable Survival Analysis
Graph-based Multiple Instance Learning (MIL) is widely used in survival analysis with Hematoxylin and Eosin (H\&E)-stained whole slide images (WSIs) due to its ability to capture topological information. However, variations in staining and scanning can introduce semantic bias, while topological subgraphs that are not relevant to the causal relationships can create noise, resulting in biased slide-level representations. These issues can hinder both the interpretability and generalization of the …

VisioFirm: Cross-Platform AI-assisted Annotation Tool for Computer Vision
Safouane El Ghazouali, Umberto Michelucci
https://arxiv.org/abs/2509.04180 https://

VisioFirm: Cross-Platform AI-assisted Annotation Tool for Computer Vision
AI models rely on annotated data to learn pattern and perform prediction. Annotation is usually a labor-intensive step that require associating labels ranging from a simple classification label to more complex tasks such as object detection, oriented bounding box estimation, and instance segmentation. Traditional tools often require extensive manual input, limiting scalability for large datasets. To address this, we introduce VisioFirm, an open-source web application designed to streamline imag…