Tootfinder

Source: Pylon, which uses AI to automate B2B customer service, raised $31M led by a16z and Bain Capital at a valuation in the hundreds of millions of dollars (Stephanie Palazzolo/The Information)
https://www.theinformation.com/articles/andreessen-…

Why Andreessen and Bain Backed a Self-Described ‘Zendesk Killer’
Automating customer service has been among the most popular applications of artificial intelligence models, and investors have pumped about $1 billion into six key startups developing them. Now, a seventh is throwing its hat into the ring.San Francisco-based startup Pylon has raised $31 million ...

A Stitch in Time Saves Nine: Proactive Self-Refinement for Language Models
Jinyi Han, Xinyi Wang, Haiquan Zhao, Tingyun li, Zishang Jiang, Sihang Jiang, Jiaqing Liang, Xin Lin, Weikang Zhou, Zeye Sun, Fei Yu, Yanghua Xiao
https://arxiv.org/abs/2508.12903

A Stitch in Time Saves Nine: Proactive Self-Refinement for Language Models
Recent advances in self-refinement have demonstrated significant potential for improving the outputs of large language models (LLMs) through iterative refinement. However, most existing self-refinement methods rely on a reactive process with a fixed number of iterations, making it difficult to determine the optimal timing and content of refinement based on the evolving generation context. Inspired by the way humans dynamically refine their thoughts during execution, we propose ProActive Self-Re…

AIM: Amending Inherent Interpretability via Self-Supervised Masking
Eyad Alshami, Shashank Agnihotri, Bernt Schiele, Margret Keuper
https://arxiv.org/abs/2508.11502 https://

AIM: Amending Inherent Interpretability via Self-Supervised Masking
It has been observed that deep neural networks (DNNs) often use both genuine as well as spurious features. In this work, we propose "Amending Inherent Interpretability via Self-Supervised Masking" (AIM), a simple yet interestingly effective method that promotes the network's utilization of genuine features over spurious alternatives without requiring additional annotations. In particular, AIM uses features at multiple encoding stages to guide a self-supervised, sample-specific feature-masking p…

Towards Faithful Class-level Self-explainability in Graph Neural Networks by Subgraph Dependencies
Fanzhen Liu, Xiaoxiao Ma, Jian Yang, Alsharif Abuadbba, Kristen Moore, Surya Nepal, Cecile Paris, Quan Z. Sheng, Jia Wu
https://arxiv.org/abs/2508.11513

Towards Faithful Class-level Self-explainability in Graph Neural Networks by Subgraph Dependencies
Enhancing the interpretability of graph neural networks (GNNs) is crucial to ensure their safe and fair deployment. Recent work has introduced self-explainable GNNs that generate explanations as part of training, improving both faithfulness and efficiency. Some of these models, such as ProtGNN and PGIB, learn class-specific prototypes, offering a potential pathway toward class-level explanations. However, their evaluations focus solely on instance-level explanations, leaving open the question o…

Bring your whole self to work, and to play. Do not hide who you are.
Unless your whole self is an asshole, then maybe keep that part tucked away around other people, OK?

Internalizing Self-Consistency in Language Models: Multi-Agent Consensus Alignment
Ankur Samanta, Akshayaa Magesh, Youliang Yu, Runzhe Wu, Ayush Jain, Daniel Jiang, Boris Vidolov, Paul Sajda, Yonathan Efroni, Kaveh Hassani
https://arxiv.org/abs/2509.15172

Internalizing Self-Consistency in Language Models: Multi-Agent Consensus Alignment
Language Models (LMs) are inconsistent reasoners, often generating contradictory responses to identical prompts. While inference-time methods can mitigate these inconsistencies, they fail to address the core problem: LMs struggle to reliably select reasoning pathways leading to consistent outcomes under exploratory sampling. To address this, we formalize self-consistency as an intrinsic property of well-aligned reasoning models and introduce Multi-Agent Consensus Alignment (MACA), a reinforceme…

Trump declined to approve more than $400 million in military aid to Taiwan this summer,
as he tries to negotiate a trade deal and potential summit with Chinese leader Xi Jinping.

The decision, which may still be reversed, marks a U-turn in U.S. policy toward the self-governing island that China claims as its own territory.

Two people familiar with the matter said the package was worth more than $400 million and would have been “more lethal” than past rounds of aid to Taiwan…

Trump nixed $400 million in Taiwan military aid, pushing future arms sales
President Trump declined to approve more than $400M in military aid to Taiwan this summer, favoring future arms sales to the self-governing island China claims.

SGCL: Unifying Self-Supervised and Supervised Learning for Graph Recommendation
Weizhi Zhang, Liangwei Yang, Zihe Song, Henrry Peng Zou, Ke Xu, Yuanjie Zhu, Philip S. Yu
https://arxiv.org/abs/2507.13336

SGCL: Unifying Self-Supervised and Supervised Learning for Graph Recommendation
Recommender systems (RecSys) are essential for online platforms, providing personalized suggestions to users within a vast sea of information. Self-supervised graph learning seeks to harness high-order collaborative filtering signals through unsupervised augmentation on the user-item bipartite graph, primarily leveraging a multi-task learning framework that includes both supervised recommendation loss and self-supervised contrastive loss. However, this separate design introduces additional grap…

Self-Guided Action Diffusion
Rhea Malhotra, Yuejiang Liu, Chelsea Finn
https://arxiv.org/abs/2508.12189 https://arxiv.org/pdf/2508.12189

Self-Guided Action Diffusion
Recent works have shown the promise of inference-time search over action samples for improving generative robot policies. In particular, optimizing cross-chunk coherence via bidirectional decoding has proven effective in boosting the consistency and reactivity of diffusion policies. However, this approach remains computationally expensive as the diversity of sampled actions grows. In this paper, we introduce self-guided action diffusion, a more efficient variant of bidirectional decoding tailor…

Regular black holes with gravitational self-energy as dark matter
Kimet Jusufi, Douglas Singleton
https://arxiv.org/abs/2509.13335 https://arxiv.org/pdf/25…

Regular black holes with gravitational self-energy as dark matter
We incorporate the effect of non-local gravitational self-energy to obtain a neutral, non-singular spacetime geometry. This is achieved by using a non-local gravitational theory inspired by T-duality, where particle mass is not point-like but smeared over a region. This non-local gravitational self-interaction is derived from the Newtonian gravitational potential and energy density, allowing us to define a coordinate-independent quantity. Thus, we incorporate the non-local gravitational field i…

Rigidity Results for Spacelike Self-Shrinkers via Different Maximum Principles
Weiller F. Chaves Barboza
https://arxiv.org/abs/2508.12196 https://arxiv.org…

Rigidity Results for Spacelike Self-Shrinkers via Different Maximum Principles
In this work, we establish several rigidity results for spacelike self-shrinkers immersed in the pseudo-Euclidean space $\mathbb{R}^{n+p}_p$. Under suitable boundedness conditions on either the mean curvature vector or the second fundamental form, we apply different versions of Omori--Yau type maximum principles due to Qiu [20], Chen and Qiu [10], and Alías, Caminha, and Nascimento [3] to show that such self-shrinkers must be spacelike hyperplanes. These results contribute to the broader class…

🔋 Self-assembling electrolyte enables rapid disassembly for easier EV battery recycling
https://techxplore.com/news/2025-08-electrolyte-enables-rapid-disassembly-easier.html

Self-assembling electrolyte enables rapid disassembly for easier EV battery recycling
Today's electric vehicle boom is tomorrow's mountain of electronic waste. And while myriad efforts are underway to improve battery recycling, many EV batteries still end up in landfills.

Don't miss today's Metacurity for the most critical infosec developments you should know, including
--A bona fide self-replicating worm has infected 187 npm packages,
--BreachForums founder hit with new three-year sentence,
--Coinbase beach suspect accused of participating in $500k bribery scheme,
--DHS intelligence arm exposed sensitive database,
--MSFT seized 338 sites linked to Raccoon0365 stealer,
--DeepSeek is biased against Falun Gong and oth…

A self-replicating worm has infected 187 npm packages
BreachForums founder hit with new three-year sentence, Coinbase breach suspect accused of participating in $500k+ bribery scheme, DHS intelligence arm exposed sensitive database, MSFT seized 338 sites linked to Raccoon0365 stealer, DeepSeek is biased against Falun Gong and others, much more

Welcome to Self® With Dr Hayley D Quinn
Great Australian Pods Podcast Directory: #GreatAusPods

Unraveling Self-Similar Energy Transfer Dynamics: a Case Study for 1D Burgers System
Pritpal Matharu, Bartosz Protas, Tsuyoshi Yoneda
https://arxiv.org/abs/2507.12764

Unraveling Self-Similar Energy Transfer Dynamics: a Case Study for 1D Burgers System
In this work we consider the problem of constructing flow evolutions leading to a self-similar energy cascade consistent with Kolmogorov's statistical theory of turbulence. As a first step in this direction, we focus on the one-dimensional viscous Burgers equation as a toy model. Its solutions exhibiting self-similar behavior, in a precisely-defined sense, are found by framing this problems in terms of PDE-constrained optimization. The main physical parameters are the time window over which sel…

A Computational Framework to Identify Self-Aspects in Text
Jaya Caporusso, Matthew Purver, Senja Pollak
https://arxiv.org/abs/2507.13115 https://

A Computational Framework to Identify Self-Aspects in Text
This Ph.D. proposal introduces a plan to develop a computational framework to identify Self-aspects in text. The Self is a multifaceted construct and it is reflected in language. While it is described across disciplines like cognitive science and phenomenology, it remains underexplored in natural language processing (NLP). Many of the aspects of the Self align with psychological and other well-researched phenomena (e.g., those related to mental health), highlighting the need for systematic NLP-…

"As a collective of homeless and marginally housed mothers, Moms 4 Housing organizes to reclaim vacant property warehoused by investors. In 2020, another group of mothers began squatting in vacant foreclosed properties owned by Philadelphia’s Housing Authority (PHA)." ❤️‍🔥
https://rosalux.nyc/self-help-housing/

From Bill McKibben
https://billmckibben.substack.com/p/shameless-self-promotion/
"I’m proud of my new book and I think it will be helpful. It will be on sale in a few weeks, but it’s available for pre-order now."

$GW$ 2SOSEX self-energy made positive semi-definite
Fabien Bruneval, Arno F\"orster, Yaroslav Pavlyukh
https://arxiv.org/abs/2507.13293 https://

$GW$+2SOSEX self-energy made positive semi-definite
The formulation of vertex corrections beyond the $GW$ approximation within the framework of perturbation theory is a subtle and challenging task, which accounts for the wide variety of schemes proposed over the years. Exact self-energies are required to satisfy the mathematical condition of positive semi-definiteness. The $GW$ self-energy fulfills this property, but the vast majority of the vertex-corrected self-energy approximations do not. In this study, we devise a positive semi-definite ext…

Writing the Self and Society: Existential and Cultural Narratives in Lusophone Literature (issue of Romance Notes Journal) https://call-for-papers.sas.upenn.edu/cfp/2025/07/17/writing-the-self-and-society-existentia…

Note to self: Medicine works better when you take it. 💊

In Planta Tattoo and Kirigami Sensors for Self-Powered Monitoring of Vapor Pressure Deficit and Growth Dynamics
Nafize Ishtiaque Hossain, Kundan Saha, Atul Sharma, Sameer Sonkusale
https://arxiv.org/abs/2509.14240

In Planta Tattoo and Kirigami Sensors for Self-Powered Monitoring of Vapor Pressure Deficit and Growth Dynamics
We report a scalable, self-powered in planta sensor platform for continuous monitoring of plant hydration and growth. The system integrates two components a leaf mounted tattoo sensor for estimating vapor pressure deficit and a kirigami inspired strain sensor for tracking radial stem growth. Uniquely, the tattoo sensor serves a dual function measuring temperature and humidity beneath the leaf surface while simultaneously harvesting power from ambient moisture via a vanadium pentoxide nanosheet …

MATPAC : Enhanced Masked Latent Prediction for Self-Supervised Audio Representation Learning
Aurian Quelennec, Pierre Chouteau, Geoffroy Peeters, Slim Essid
https://arxiv.org/abs/2508.12709

MATPAC++: Enhanced Masked Latent Prediction for Self-Supervised Audio Representation Learning
Masked latent prediction has emerged as a leading paradigm in self-supervised learning (SSL), especially for general audio and music representation learning. While recent methods have demonstrated strong performance, the role of the predictor module used at the output of such SSL systems remains mainly overlooked, despite being crucial for solving the pretext task at hand. In particular, this module should be able to deal with the ambiguity inherent in audio content, especially when it is compo…

Open Questions about Time and Self-reference in Living Systems
Samson Abramsky, Wolfgang Banzhaf, Leo S. D. Caves, Michael Levin, Penousal Machado, Charles Ofria, Susan Stepney, Roger White
https://arxiv.org/abs/2508.11423

Open Questions about Time and Self-reference in Living Systems
Living systems exhibit a range of fundamental characteristics: they are active, self-referential, self-modifying systems. This paper explores how these characteristics create challenges for conventional scientific approaches and why they require new theoretical and formal frameworks. We introduce a distinction between 'natural time', the continuing present of physical processes, and 'representational time', with its framework of past, present and future that emerges with life itself. Representa…

SO-PIFRNN: Self-optimization physics-informed Fourier-features randomized neural network for solving partial differential equations
Jiale Linghu, Weifeng Gao, Hao Dong, Yufeng Nie
https://arxiv.org/abs/2508.10921

SO-PIFRNN: Self-optimization physics-informed Fourier-features randomized neural network for solving partial differential equations
This study proposes a self-optimization physics-informed Fourier-features randomized neural network (SO-PIFRNN) framework, which significantly improves the numerical solving accuracy of PDEs through hyperparameter optimization mechanism. The framework employs a bi-level optimization architecture: the outer-level optimization utilizes a multi-strategy collaborated particle swarm optimization (MSC-PSO) algorithm to search for optimal hyperparameters of physics-informed Fourier-features randomized…

Emulation of Self-Consistent Non-Hermitian Quantum Formalisms
Mario Gonzalez, Karin Sim, R. Chitra
https://arxiv.org/abs/2507.13078 https://

Emulation of Self-Consistent Non-Hermitian Quantum Formalisms
Standard quantum mechanics predicts the non-conservation of state norms and probability when the fundamental requirement of the Hermiticity of the Hamiltonian is relaxed. Biorthogonal quantum mechanics, or the more general metric formalism, provides a rigorous formulation of non-Hermitian quantum mechanics wherein norms and probabilities are conserved. The key feature is that the Hilbert space is endowed with a non-trivial dynamical metric. Beyond theoretical considerations, the physical implem…

Self Balancing Neural Network: A Novel Method to Estimate Average Treatment Effect
Atomsa Gemechu Abdisa, Yingchun Zhou, Yuqi Qiu
https://arxiv.org/abs/2507.12818

Self Balancing Neural Network: A Novel Method to Estimate Average Treatment Effect
In observational studies, confounding variables affect both treatment and outcome. Moreover, instrumental variables also influence the treatment assignment mechanism. This situation sets the study apart from a standard randomized controlled trial, where the treatment assignment is random. Due to this situation, the estimated average treatment effect becomes biased. To address this issue, a standard approach is to incorporate the estimated propensity score when estimating the average treatment e…

Linking Stochastic Self-Propagating Star Formation and Spatio-Temporal Point Processes
Qihan Zou
https://arxiv.org/abs/2508.12372 https://arxiv.org/pdf/250…

Linking Stochastic Self-Propagating Star Formation and Spatio-Temporal Point Processes
The stochastic self-propagating star-formation (SSPSF) model is an important theoretical framework for explaining how localised star-formation events trigger subsequent activity across galactic discs. While widely used to interpret spiral and irregular structures, its probabilistic rules have lacked a formal statistical foundation. In this work, we establish a connection between the SSPSF model and spatio-temporal point processes (STPP), which describe events in space and time through history-d…

Personalized Detection of Stress via hdrEEG: Linking Neuro-markers to Cortisol, HRV, and Self-Report
N. B. Maimon, Ganit Baruchin, Itamar Grotto, Nathan Intrator, Talya Zeimer, Ofir Chibotero, Efrat Danino
https://arxiv.org/abs/2509.13875

Personalized Detection of Stress via hdrEEG: Linking Neuro-markers to Cortisol, HRV, and Self-Report
Chronic stress is a major risk factor for cognitive decline, neurodegenerative disease, and systemic health burden, underscoring the need for reliable individual-level biomarkers of stress reactivity. While cortisol, heart rate variability (HRV), and self-report measures are widely used, they provide limited insight into neural mechanisms. Here, we tested whether two single-channel hdrEEG biomarkers, ST4 and T2, serve as personalized indices of stress regulation by linking neural activity to va…

Reasoning Efficiently Through Adaptive Chain-of-Thought Compression: A Self-Optimizing Framework
Kerui Huang, Shuhan Liu, Xing Hu, Tongtong Xu, Lingfeng Bao, Xin Xia
https://arxiv.org/abs/2509.14093

Reasoning Efficiently Through Adaptive Chain-of-Thought Compression: A Self-Optimizing Framework
Chain-of-Thought (CoT) reasoning enhances Large Language Models (LLMs) by prompting intermediate steps, improving accuracy and robustness in arithmetic, logic, and commonsense tasks. However, this benefit comes with high computational costs: longer outputs increase latency, memory usage, and KV-cache demands. These issues are especially critical in software engineering tasks where concise and deterministic outputs are required. To investigate these trade-offs, we conduct an empirical study base…

The matrix potential game and structures of self-affine sets
Richard A. Howat, Andrew Mitchell, Tony Samuel
https://arxiv.org/abs/2508.11577 https://arxiv.…

The matrix potential game and structures of self-affine sets
We present a new variant of the potential game and show that certain compact subsets of $\R^n$, including a large class of self-affine sets, are winning in our game. We prove that sets with sufficiently strong winning conditions are non-empty, provide a lower bound for their Hausdorff dimension, show that they have good intersection properties, and provide conditions under which, given $M \in \N$, they contain a homothetic copy of every set with at most $M$ elements. The applications of our gam…

Update of the Higgs Self-coupling Projections from Di-Higgs Production in Detailed Simulation of the ILD Concept
Mikael Berggren, Bryan Bliewert, Jenny List, Dimitris Ntounis, Taikan Suehara, Junping Tian, Julie Munch Torndal, Caterina Vernieri
https://arxiv.org/abs/2509.14148

Update of the Higgs Self-coupling Projections from Di-Higgs Production in Detailed Simulation of the ILD Concept
This contribution summarizes the update of the projections for the determination of the tri-linear Higgs self-coupling from di-Higgs production at future $e^+e^-$ colliders. In particular, we will present an update of the analysis of $ZHH$ production at 500 GeV in detailed simulations of the ILD concept, covering the $HH\rightarrow b\bar{b}b\bar{b}$ and $Z\rightarrow q\bar{q} / e^+e^- / μ^+μ^- /ν\barν$ channels. Based on the experience of previous analyses, we will extrapolate these to cont…

Apparent Resonance Splitting in Self-Coupled Excitonic Systems
Avishek Sarbajna, Qitong Li, Dorte Rub{\ae}k Danielsen, Skyler Peitso Selvin, Duc Hieu Nguyen, Manh-Ha Doan, Peter B{\o}ggild, Mark L. Brongersma, S{\o}ren Raza
https://arxiv.org/abs/2508.11370

Apparent Resonance Splitting in Self-Coupled Excitonic Systems
Thin films of high-refractive-index excitonic materials enable self-coupling by simultaneously supporting intrinsic excitonic transitions and optical resonances. These optical resonances take the form of Fabry-Perot resonances in thick films and absorption resonances in ultrathin films placed on metallic substrates. Here, we investigate whether these optical resonances lead to true exciton-photon hybridization. Using far-field reflectance and spectrally resolved photocurrent measurements, we st…

dblp_cite: DBLP citations (2014)
Citations among papers contained in the DBLP computer science bibliography. If a paper i cites a paper j also in this data set, then a directed edge connects i to j. (Papers not in the data set are excluded.) Self-loops may be present. This snapshot from May 2014.
This network has 12590 nodes and 49759 edges.
Tags: Informational, Citation, Unweighted

Self : Merging Human and AI for Co-Determined XR Living in the Metaverse
Thammathip Piumsomboon
https://arxiv.org/abs/2507.10967 https://

Self++: Merging Human and AI for Co-Determined XR Living in the Metaverse
This position paper introduces Self++, a novel nine-level framework for co-determined living in the Metaverse, grounded in Self-Determination Theory. Self++ prioritises human flourishing by progressively cultivating competence, autonomy, and relatedness through dynamic human-AI collaboration in extended reality (XR). Unlike technologically deterministic approaches, Self++ emphasises user empowerment by enhancing competency, mitigating cognitive biases and leveraging XR's immersive capabilities.…

Self-learning Monte Carlo Method: A Review
Gaopei Pan, Chuang Chen, Zi Yang Meng
https://arxiv.org/abs/2507.12554 https://arxiv.org/p…

Self-learning Monte Carlo Method: A Review
The Self-Learning Monte Carlo (SLMC) method is a Monte Carlo approach that has emerged in recent years by integrating concepts from machine learning with conventional Monte Carlo techniques. Designed to accelerate the numerical study of interacting many-body systems, SLMC significantly improves sampling efficiency by constructing an effective model -- via machine learning methods -- based on configurations generated by conventional Monte Carlo methods and then proposes global updates based on t…

Dehoarding, I think, is a million small steps. And that's exhausting, but you don't get to the tenth step if you don't take the first step https://www.overcomecompulsivehoarding.co.uk/podcast-ep-190-self-compassion-shame-hoarding/

On the Local-to-Global Principle for Zero-Cycles on Self Products of Elliptic Curves with CM
Michael Wills
https://arxiv.org/abs/2509.13641 https://arxiv.o…

On the Local-to-Global Principle for Zero-Cycles on Self Products of Elliptic Curves with CM
For a smooth projective variety $X$ defined over a global field $K$, one can form a notion of Weak Approximation for the Chow group of zero-cycles of $X$. There exists a Brauer-Manin obstruction to Weak Approximation here akin to that for rational points. However, unlike for rational points, it is conjectured that this obstruction is the only one; early versions of this conjecture date back to work of Colliot-Thélène and Sansuc (1981) and of Kato and Saito (1986). In this paper, we provide ev…

Single-file HTML apps – Hyperclay
Experience the Zen of making, hosting, and sharing great software in a single, portable, self-updating, vanilla HTML file
🐞 #web

Hyperclay | Single-file HTML apps
A single HTML file is all you need to build a web app. Hyperclay hosts these HTML files so you can create personal, malleable software easily.

An Efficient and Adaptive Framework for Achieving Underwater High-performance Maintenance Networks
Yu Gou, Tong Zhang, Jun Liu, Zhongyang Qi, Dezhi Zheng
https://arxiv.org/abs/2508.12661

An Efficient and Adaptive Framework for Achieving Underwater High-performance Maintenance Networks
With the development of space-air-ground-aqua integrated networks (SAGAIN), high-speed and reliable network services are accessible at any time and any location. However, the long propagation delay and limited network capacity of underwater communication networks (UCN) negatively impact the service quality of SAGAIN. To address this issue, this paper presents U-HPNF, a hierarchical framework designed to achieve a high-performance network with self-management, self-configuration, and self-optimi…

SpectraLift: Physics-Guided Spectral-Inversion Network for Self-Supervised Hyperspectral Image Super-Resolution
Ritik Shah, Marco F. Duarte
https://arxiv.org/abs/2507.13339

SpectraLift: Physics-Guided Spectral-Inversion Network for Self-Supervised Hyperspectral Image Super-Resolution
High-spatial-resolution hyperspectral images (HSI) are essential for applications such as remote sensing and medical imaging, yet HSI sensors inherently trade spatial detail for spectral richness. Fusing high-spatial-resolution multispectral images (HR-MSI) with low-spatial-resolution hyperspectral images (LR-HSI) is a promising route to recover fine spatial structures without sacrificing spectral fidelity. Most state-of-the-art methods for HSI-MSI fusion demand point spread function (PSF) cali…

Self-Consistent Heating of the Magnetically Closed Solar Corona: Generation of Nanoflares, Thermodynamic Response of the Plasma and Observational Signatures
Craig D. Johnston, Lars K. S. Daldorff, James A. Klimchuk, Shanwlee Sow Mondal, Will T. Barnes, James E. Leake, Jack Reid, Jacob D. Parker
https://arxiv.org/abs/2508.12952

Self-Consistent Heating of the Magnetically Closed Solar Corona: Generation of Nanoflares, Thermodynamic Response of the Plasma and Observational Signatures
The energy that heats the magnetically closed solar corona originates in the complex motions of the massive photosphere. Turbulent photospheric convection slowly displaces the footpoints of coronal field lines, causing them to become twisted and tangled. Magnetic stresses gradually build until reaching a breaking point when the field reconnects and releases a sudden burst of energy. We simulate this basic picture of nanoflares using a high-fidelity, three-dimensional, multi-stranded magnetohydr…

A Scalable Formula for the Moments of a Family of Self-Normalized Statistics
Haolin Zou, Heyuan Yao, Victor de la Pe\~na
https://arxiv.org/abs/2509.14428 https://

A Scalable Formula for the Moments of a Family of Self-Normalized Statistics
Following the student t-statistic, normalization has been a widely used method in statistic and other disciplines including economics, ecology and machine learning. We focus on statistics taking the form of a ratio over (some power of) the sample mean, the probabilistic features of which remain unknown. We develop a unified formula for the moments of these self-normalized statistics with non-negative observations, yielding closed-form expressions for several important cases. Moreover, the compl…

DMS:Diffusion-Based Multi-Baseline Stereo Generation for Improving Self-Supervised Depth Estimation
Zihua Liu, Yizhou Li, Songyan Zhang, Masatoshi Okutomi
https://arxiv.org/abs/2508.13091

DMS:Diffusion-Based Multi-Baseline Stereo Generation for Improving Self-Supervised Depth Estimation
While supervised stereo matching and monocular depth estimation have advanced significantly with learning-based algorithms, self-supervised methods using stereo images as supervision signals have received relatively less focus and require further investigation. A primary challenge arises from ambiguity introduced during photometric reconstruction, particularly due to missing corresponding pixels in ill-posed regions of the target view, such as occlusions and out-of-frame areas. To address this …

SV-Mixer: Replacing the Transformer Encoder with Lightweight MLPs for Self-Supervised Model Compression in Speaker Verification
Jungwoo Heo, Hyun-seo Shin, Chan-yeong Lim, Kyo-won Koo, Seung-bin Kim, Jisoo Son, Ha-Jin Yu
https://arxiv.org/abs/2509.14136

SV-Mixer: Replacing the Transformer Encoder with Lightweight MLPs for Self-Supervised Model Compression in Speaker Verification
Self-supervised learning (SSL) has pushed speaker verification accuracy close to state-of-the-art levels, but the Transformer backbones used in most SSL encoders hinder on-device and real-time deployment. Prior compression work trims layer depth or width yet still inherits the quadratic cost of self-attention. We propose SV-Mixer, the first fully MLP-based student encoder for SSL distillation. SV-Mixer replaces Transformer with three lightweight modules: Multi-Scale Mixing for multi-resolution …

ATLAS: A Self-Supervised and Cross-Stage Netlist Power Model for Fine-Grained Time-Based Layout Power Analysis
Wenkai Li, Yao Lu, Wenji Fang, Jing Wang, Qijun Zhang, Zhiyao Xie
https://arxiv.org/abs/2508.12433

ATLAS: A Self-Supervised and Cross-Stage Netlist Power Model for Fine-Grained Time-Based Layout Power Analysis
Accurate power prediction in VLSI design is crucial for effective power optimization, especially as designs get transformed from gate-level netlist to layout stages. However, traditional accurate power simulation requires time-consuming back-end processing and simulation steps, which significantly impede design optimization. To address this, we propose ATLAS, which can predict the ultimate time-based layout power for any new design in the gate-level netlist. To the best of our knowledge, ATLAS …

A self-supervised learning approach for denoising autoregressive models with additive noise: finite and infinite variance cases
Sayantan Banerjee, Agnieszka Wylomanska, Sundar S
https://arxiv.org/abs/2508.12970

A self-supervised learning approach for denoising autoregressive models with additive noise: finite and infinite variance cases
The autoregressive time series model is a popular second-order stationary process, modeling a wide range of real phenomena. However, in applications, autoregressive signals are often corrupted by additive noise. Further, the autoregressive process and the corruptive noise may be highly impulsive, stemming from an infinite-variance distribution. The model estimation techniques that account for additional noise tend to show reduced efficacy when there is very strong noise present in the data, esp…

Click, Watch, Learn: The Impact of Student Self-Study Materials on Physics E&M Course Outcomes
James K. Hirons, Jonathan D. Perry, Dawson T. Nodurft, Scott Crawford, William Bassichis, Tatiana L. Erukhimova
https://arxiv.org/abs/2508.12143

Click, Watch, Learn: The Impact of Student Self-Study Materials on Physics E&M Course Outcomes
Performance in introductory courses, particularly physics, is often crucial for student success in STEM majors and can impact an individual's tendency to persist in their chosen field. To enhance students' individual learning experiences, faculty at many universities have worked to develop open-access, self-study materials to help build conceptual understanding and problem-solving skills. Faculty at Texas A&M University have contributed to these efforts, creating more than 200 online video reso…

Quantum nature of gravity in self-bound quantum droplets
Asma Tahar Taiba, Abdelaali Boudjemaa
https://arxiv.org/abs/2508.12838 https://arxiv.org/pdf/2508.…

Quantum nature of gravity in self-bound quantum droplets
We explore the possibility of testing the quantum nature of the gravitational field with an ultracold self-bound quantum droplet of one-dimensional Bose-Bose mixtures. To this end, we solve variationally and numerically the underlying generalized Gross-Pitaevskii equation which includes the effects of quadratic and cubic nonlinearities. We derive the associated generalized uncertainty principle and its corresponding minimal length. The obtained modified uncertainty relation enables us to search…

Reviewing some #aspnetcore Minimal API endpoint code today, and the need to inject every dependency, even a “RedirectManager”, feels like a code smell.
There is an elegance to an MVC endpoint or Razor Page that exists in a self-aware context.

Some non-citizen journalists working in the US are self-censoring, wiping their social media accounts, canceling travel plans, and more, fearing deportation (Angela Fu/Poynter)
https://www.poynter.org/reporting-editing/…

Foreign journalists in the U.S. are self-censoring to protect themselves from the Trump administration - Poynter
Non-citizen journalists working in the U.S. report wiping their social media accounts, canceling travel plans and pulling bylines.

Maintaining Routing Structures under Deletions via Self-Pruning
Bernhard Haeupler, Antti Roeyskoe
https://arxiv.org/abs/2507.13044 https://

Maintaining Routing Structures under Deletions via Self-Pruning
Expanders are powerful algorithmic structures with two key properties: they are a) routable: for any multi-commodity flow unit demand, there exists a routing with low congestion over short paths, where a demand is unit if the amount of demand sent / received by any vertex is at most the number of edges adjacent to it. b) stable / prunable: for any (sequence of) edge failures, there exists a proportionally small subset of vertices that can be disabled, such that the graph induced on the rema…

Tesla Tries to Save the Cybertruck With Its Most Desperate Offer Yet (free self-driving software, $12k worth)
https://gizmodo.com/tesla-tries-to-save-the-cybertruck-with-its-most-desperate-offer-yet-2000631752

Macroscopic coherence and vorticity in room-temperature polariton condensate confined in a self-assembled perovskite microcavity
Martin Montagnac, Yesenia A. Garc\'ia Jomaso, Emiliano Robledo Ibarra, Rodrigo S\'anchez-Mart\'inez, Moroni Santiago Garc\'ia, C\'esar L. Ord\'o\~nez-Romero, Hugo A. Lara-Garc\'ia, Arturo Camacho-Guardian, Giuseppe Pirruccio

Macroscopic coherence and vorticity in room-temperature polariton condensate confined in a self-assembled perovskite microcavity
Exciton-polariton Bose-Einstein condensation at room temperature offers a promising pathway toward quantum photonic technologies that can operate under ambient conditions. A key challenge in this field is to engineer a controlled platform where strong confinement, nonlinear interactions, and structural disorder coexist, unlocking access to rich collective behavior and unconventional condensate dynamics. We demonstrate polariton condensation in CsPbBr$_3$ microplatelets that self-assemble into w…

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…

Several Issues Regarding Data Governance in AGI
Masayuki Hatta
https://arxiv.org/abs/2508.12168 https://arxiv.org/pdf/2508.12168

Several Issues Regarding Data Governance in AGI
The rapid advancement of artificial intelligence has positioned data governance as a critical concern for responsible AI development. While frameworks exist for conventional AI systems, the potential emergence of Artificial General Intelligence (AGI) presents unprecedented governance challenges. This paper examines data governance challenges specific to AGI, defined as systems capable of recursive self-improvement or self-replication. We identify seven key issues that differentiate AGI governan…

SSL-SSAW: Self-Supervised Learning with Sigmoid Self-Attention Weighting for Question-Based Sign Language Translation
Zekang Liu, Wei Feng, Fanhua Shang, Lianyu Hu, Jichao Feng, Liqing Gao
https://arxiv.org/abs/2509.14036

SSL-SSAW: Self-Supervised Learning with Sigmoid Self-Attention Weighting for Question-Based Sign Language Translation
Sign Language Translation (SLT) bridges the communication gap between deaf people and hearing people, where dialogue provides crucial contextual cues to aid in translation. Building on this foundational concept, this paper proposes Question-based Sign Language Translation (QB-SLT), a novel task that explores the efficient integration of dialogue. Unlike gloss (sign language transcription) annotations, dialogue naturally occurs in communication and is easier to annotate. The key challenge lies i…

“Self-examination is great but no need to fall into the assesspool of self-judgment.”

-- Swami Beyondananda
Swami’s Daily Laughsitive (stolen from his email list)
#Humor

TransforMARS: Fault-Tolerant Self-Reconfiguration for Arbitrarily Shaped Modular Aerial Robot Systems
Rui Huang, Zhiyu Gao, Siyu Tang, Jialin Zhang, Lei He, Ziqian Zhang, Lin Zhao
https://arxiv.org/abs/2509.14025

TransforMARS: Fault-Tolerant Self-Reconfiguration for Arbitrarily Shaped Modular Aerial Robot Systems
Modular Aerial Robot Systems (MARS) consist of multiple drone modules that are physically bound together to form a single structure for flight. Exploiting structural redundancy, MARS can be reconfigured into different formations to mitigate unit or rotor failures and maintain stable flight. Prior work on MARS self-reconfiguration has solely focused on maximizing controllability margins to tolerate a single rotor or unit fault for rectangular-shaped MARS. We propose TransforMARS, a general fault…

I just received a beautiful piece of cat art by @… through @… from #why2025 .
Thank you very much! 😍

This post <https://pixelfed.social/p/stuffifound/844831816028127142> possibly helped me do some self-diagnosis as suggested by @… in their recently…

What's the equivalent of #Immich but for audio and video files?
I'm looking for a self-hostable #FOSS thing that I can throw the rest of my media library in the face (movies, music, downloaded youtube videos, etc.) and it'll sort everything nicely, maybe even query databases to find metada…

Self-Improving Embodied Foundation Models
Seyed Kamyar Seyed Ghasemipour, Ayzaan Wahid, Jonathan Tompson, Pannag Sanketi, Igor Mordatch
https://arxiv.org/abs/2509.15155 https://…

Self-Improving Embodied Foundation Models
Foundation models trained on web-scale data have revolutionized robotics, but their application to low-level control remains largely limited to behavioral cloning. Drawing inspiration from the success of the reinforcement learning stage in fine-tuning large language models, we propose a two-stage post-training approach for robotics. The first stage, Supervised Fine-Tuning (SFT), fine-tunes pretrained foundation models using both: a) behavioral cloning, and b) steps-to-go prediction objectives. …

Exploring Self-Supervised Audio Models for Generalized Anomalous Sound Detection
Bing Han, Anbai Jiang, Xinhu Zheng, Wei-Qiang Zhang, Jia Liu, Pingyi Fan, Yanmin Qian
https://arxiv.org/abs/2508.12230

Exploring Self-Supervised Audio Models for Generalized Anomalous Sound Detection
Machine anomalous sound detection (ASD) is a valuable technique across various applications. However, its generalization performance is often limited due to challenges in data collection and the complexity of acoustic environments. Inspired by the success of large pre-trained models in numerous fields, this paper introduces a robust ASD model that leverages self-supervised pre-trained models trained on large-scale speech and audio datasets. Although there are inconsistencies between the pre-tra…

Towards Rationale-Answer Alignment of LVLMs via Self-Rationale Calibration
Yuanchen Wu, Ke Yan, Shouhong Ding, Ziyin Zhou, Xiaoqiang Li
https://arxiv.org/abs/2509.13919 https://…

Towards Rationale-Answer Alignment of LVLMs via Self-Rationale Calibration
Large Vision-Language Models (LVLMs) have manifested strong visual question answering capability. However, they still struggle with aligning the rationale and the generated answer, leading to inconsistent reasoning and incorrect responses. To this end, this paper introduces the Self-Rationale Calibration (SRC) framework to iteratively calibrate the alignment between rationales and answers. SRC begins by employing a lightweight "rationale fine-tuning" approach, which modifies the model's respons…

Efficient Solutions for Mitigating Initialization Bias in Unsupervised Self-Adaptive Auditory Attention Decoding
Yuanyuan Yao, Simon Geirnaert, Tinne Tuytelaars, Alexander Bertrand
https://arxiv.org/abs/2509.14764

Efficient Solutions for Mitigating Initialization Bias in Unsupervised Self-Adaptive Auditory Attention Decoding
Decoding the attended speaker in a multi-speaker environment from electroencephalography (EEG) has attracted growing interest in recent years, with neuro-steered hearing devices as a driver application. Current approaches typically rely on ground-truth labels of the attended speaker during training, necessitating calibration sessions for each user and each EEG set-up to achieve optimal performance. While unsupervised self-adaptive auditory attention decoding (AAD) for stimulus reconstruction ha…

Sources: Nvidia is in advanced talks to invest $500M in UK self-driving car startup Wayve, as part of a broader £2B funding pledge in UK startups (Tim Bradshaw/Financial Times)
https://www.ft.com/content/cec76ea1-2cc1-4da3-a9e9-1d76aaa50afc

Circuit-based chatacterization of finite-temperature quantum phases and self-correcting quantum memory
Ruochen Ma, Vedika Khemani, Shengqi Sang
https://arxiv.org/abs/2509.15204 …

Circuit-based chatacterization of finite-temperature quantum phases and self-correcting quantum memory
Quantum phases at zero temperature can be characterized as equivalence classes under local unitary transformations: two ground states within a gapped phase can be transformed into each other via a local unitary circuit. We generalize this circuit-based characterization of phases to systems at finite-temperature thermal equilibrium described by Gibbs states. We construct a channel circuit that approximately transforms one Gibbs state into another provided the two are connected by a path in param…

A Unified Cortical Circuit Model with Divisive Normalization and Self-Excitation for Robust Representation and Memory Maintenance
Jie Su, Weiwei Wang, Zhaotian Gu, Dahui Wang, Tianyi Qian
https://arxiv.org/abs/2508.12702

A Unified Cortical Circuit Model with Divisive Normalization and Self-Excitation for Robust Representation and Memory Maintenance
Robust information representation and its persistent maintenance are fundamental for higher cognitive functions. Existing models employ distinct neural mechanisms to separately address noise-resistant processing or information maintenance, yet a unified framework integrating both operations remains elusive -- a critical gap in understanding cortical computation. Here, we introduce a recurrent neural circuit that combines divisive normalization with self-excitation to achieve both robust encodin…

Self-supervised learning for multiplexing super-resolution confocal microscopy
Qinglin Chen, Luwei Wang, Jia Li, Dan Shao, Xiaoyu Weng, Liwei Liu, Dayong Jin, Junle Qu
https://arxiv.org/abs/2508.12823 …

Self-supervised learning for multiplexing super-resolution confocal microscopy
Confocal microscopy has long been a cornerstone technique for visualizing complex interactions and processes within cellular structures. However, achieving super-resolution imaging of multiple organelles and their interactions simultaneously has remained a significant challenge. Here, we present a self-supervised learning approach to transform diffraction-limited, single-colour input images into multi-colour super-resolution outputs. Our approach eliminates the need for paired training data by …

Theory of Mind and Self-Disclosure to CUIs
Samuel Rhys Cox
https://arxiv.org/abs/2507.10773 https://arxiv.org/pdf/2507.10773

Theory of Mind and Self-Disclosure to CUIs
Self-disclosure is important to help us feel better, yet is often difficult. This difficulty can arise from how we think people are going to react to our self-disclosure. In this workshop paper, we briefly discuss self-disclosure to conversational user interfaces (CUIs) in relation to various social cues. We then, discuss how expressions of uncertainty or representation of a CUI's reasoning could help encourage self-disclosure, by making a CUI's intended "theory of mind" more transparent to use…

Self-intersection of the Torelli map
Lycka Drakengren
https://arxiv.org/abs/2509.12449 https://arxiv.org/pdf/2509.12449

Self-intersection of the Torelli map
The Torelli map $t\colon \mathcal{M}^{ct}_g \to \mathcal{A}_g$ is far from an immersion for $g\geq 3$: the self-fiber product of the Torelli map for $g\geq 3$ has several components with nontrivial intersections. We give a stratification of the self-fiber product for arbitrary genus and describe how components in the fiber product intersect. In genus $4$, the Torelli fiber product is nonreduced, which we prove by analyzing the expansion of the period map near a nodal curve. We use the geometry …

DSCC-HS: A Dynamic Self-Reinforcing Framework for Hallucination Suppression in Large Language Models
Xiao Zheng
https://arxiv.org/abs/2509.13702 https://ar…

DSCC-HS: A Dynamic Self-Reinforcing Framework for Hallucination Suppression in Large Language Models
Large Language Model (LLM) hallucination is a significant barrier to their reliable deployment. Current methods like Retrieval-Augmented Generation (RAG) are often reactive. We introduce **Dynamic Self-reinforcing Calibration for Hallucination Suppression (DSCC-HS)**, a novel, proactive framework that intervenes during autoregressive decoding. Inspired by dual-process cognitive theory, DSCC-HS uses a compact proxy model, trained in adversarial roles as a Factual Alignment Proxy (FAP) and a Hall…

Trump nixed $400 million in Taiwan military aid, angling for future arms sales
The fastest way to fortify Taiwan’s military is by directly shipping U.S. arms,
a process known as Presidential Drawdown Authority, or PDA.
The Biden administration approved three such packages for Taiwan while in office, alongside another round of long-term military aid, totaling more than $2 billion.

Trump has promised a more transactional U.S. foreign policy and does not support sendin…

Trump nixed $400 million in Taiwan military aid, pushing future arms sales
President Trump declined to approve more than $400M in military aid to Taiwan this summer, favoring future arms sales to the self-governing island China claims.

New theoretical predictions on Type II Cepheids: towards a self consistent Pop. II distance scale
Marcella Marconi, Roberto Molinaro, Vincenzo Ripepi, Giulia De Somma, Teresa Sicignano, Mami Deka, Marcella Di Criscienzo, Emanuela Luongo, Ilaria Musella, Erasmo Trentin
https://arxiv.org/abs/2509.13552…

New theoretical predictions on Type II Cepheids: towards a self consistent Pop. II distance scale
Type II Cepheids are pulsating stars that can be used as standard candles for old stellar populations due to their characteristic Period-Luminosity and Period-Luminosity-Colour relations. They are traditionally divided in 3 sub-classes, namely BL Her, W Vir and RV Tauri. In this paper we focus on the first two sub-classes, to provide a new theoretical scenario and develop tools and relations to be adopted in distance scale and old stellar populations studies. We have built new nonlinear convect…

LKFMixer: Exploring Large Kernel Feature For Efficient Image Super-Resolution
Yinggan Tang, Quanwei Hu
https://arxiv.org/abs/2508.11391 https://arxiv.org/p…

LKFMixer: Exploring Large Kernel Feature For Efficient Image Super-Resolution
The success of self-attention (SA) in Transformer demonstrates the importance of non-local information to image super-resolution (SR), but the huge computing power required makes it difficult to implement lightweight models. To solve this problem, we propose a pure convolutional neural network (CNN) model, LKFMixer, which utilizes large convolutional kernel to simulate the ability of self-attention to capture non-local features. Specifically, we increase the kernel size to 31 to obtain the larg…

The FCC hasn't denied any license renewals in decades and the legal battle would be long, so Brendan Carr's threats are designed to make the media self-censor (CNN)
https://view.newsletters.cnn.com/messages/1758286615238bb1f6cfd45f0/raw

Boosting the Robustness-Accuracy Trade-off of SNNs by Robust Temporal Self-Ensemble
Jihang Wang, Dongcheng Zhao, Ruolin Chen, Qian Zhang, Yi Zeng
https://arxiv.org/abs/2508.11279

Boosting the Robustness-Accuracy Trade-off of SNNs by Robust Temporal Self-Ensemble
Spiking Neural Networks (SNNs) offer a promising direction for energy-efficient and brain-inspired computing, yet their vulnerability to adversarial perturbations remains poorly understood. In this work, we revisit the adversarial robustness of SNNs through the lens of temporal ensembling, treating the network as a collection of evolving sub-networks across discrete timesteps. This formulation uncovers two critical but underexplored challenges-the fragility of individual temporal sub-networks a…

Multi-Class-Token Transformer for Multitask Self-supervised Music Information Retrieval
Yuexuan Kong, Vincent Lostanlen, Romain Hennequin, Mathieu Lagrange, Gabriel Meseguer-Brocal
https://arxiv.org/abs/2507.12996

Multi-Class-Token Transformer for Multitask Self-supervised Music Information Retrieval
Contrastive learning and equivariant learning are effective methods for self-supervised learning (SSL) for audio content analysis. Yet, their application to music information retrieval (MIR) faces a dilemma: the former is more effective on tagging (e.g., instrument recognition) but less effective on structured prediction (e.g., tonality estimation); The latter can match supervised methods on the specific task it is designed for, but it does not generalize well to other tasks. In this article, w…

A Self-Ensemble Inspired Approach for Effective Training of Binary-Weight Spiking Neural Networks
Qingyan Meng, Mingqing Xiao, Zhengyu Ma, Huihui Zhou, Yonghong Tian, Zhouchen Lin
https://arxiv.org/abs/2508.12609

A Self-Ensemble Inspired Approach for Effective Training of Binary-Weight Spiking Neural Networks
Spiking Neural Networks (SNNs) are a promising approach to low-power applications on neuromorphic hardware due to their energy efficiency. However, training SNNs is challenging because of the non-differentiable spike generation function. To address this issue, the commonly used approach is to adopt the backpropagation through time framework, while assigning the gradient of the non-differentiable function with some surrogates. Similarly, Binary Neural Networks (BNNs) also face the non-differenti…

Maestro: Self-Improving Text-to-Image Generation via Agent Orchestration
Xingchen Wan, Han Zhou, Ruoxi Sun, Hootan Nakhost, Ke Jiang, Rajarishi Sinha, Sercan \"O. Ar{\i}k
https://arxiv.org/abs/2509.10704

Maestro: Self-Improving Text-to-Image Generation via Agent Orchestration
Text-to-image (T2I) models, while offering immense creative potential, are highly reliant on human intervention, posing significant usability challenges that often necessitate manual, iterative prompt engineering over often underspecified prompts. This paper introduces Maestro, a novel self-evolving image generation system that enables T2I models to autonomously self-improve generated images through iterative evolution of prompts, using only an initial prompt. Maestro incorporates two key innov…

How the Chinese hacking community Honkers, consisting of patriotic self-taught tech enthusiasts, became an integral part of China's cyberespionage apparatus (Kim Zetter/Wired)
https://www.wired.com/story/china-honkers-elite-cyber-spies/

How China’s Patriotic ‘Honkers’ Became the Nation’s Elite Cyber Spies
A new report traces the history of the early wave of Chinese hackers who became the backbone of the state's espionage apparatus.

Deformation of the panoramic sphere into an ellipsoid to induce self-motion in telepresence users
Eetu Laukka, Evan G. Center, Timo Ojala, Steven M. LaValle, Matti Pouke
https://arxiv.org/abs/2508.12925

Deformation of the panoramic sphere into an ellipsoid to induce self-motion in telepresence users
Mobile telepresence robots allow users to feel present and explore remote environments using technology. Traditionally, these systems are implemented using a camera onboard a mobile robot that can be controlled. Although high-immersion technologies, such as 360-degree cameras, can increase situational awareness and presence, they also introduce significant challenges. Additional processing and bandwidth requirements often result in latencies of up to seconds. The current delay with a 360-degree…

Slim-SC: Thought Pruning for Efficient Scaling with Self-Consistency
Colin Hong, Xu Guo, Anand Chaanan Singh, Esha Choukse, Dmitrii Ustiugov
https://arxiv.org/abs/2509.13990 htt…

Slim-SC: Thought Pruning for Efficient Scaling with Self-Consistency
Recently, Test-Time Scaling (TTS) has gained increasing attention for improving LLM reasoning performance at test time without retraining the model. A notable TTS technique is Self-Consistency (SC), which generates multiple reasoning chains in parallel and selects the final answer via majority voting. While effective, the order-of-magnitude computational overhead limits its broad deployment. Prior attempts to accelerate SC mainly rely on model-based confidence scores or heuristics with limited …

Modulator-free, self-testing quantum random number generator
Ana Bl\'azquez-Co\'ido, Fadri Gr\"unenfelder, Anthony Martin, Raphael Houlmann, Hugo Zbinden, Davide Rusca
https://arxiv.org/abs/2507.12346

Modulator-free, self-testing quantum random number generator
Quantum random number generators (QRNGs) use the inherent unpredictability of quantum mechanics to generate true randomness, as opposed to classical random number generators. However, ensuring the authenticity of this randomness still requires robust verification. Self-testing QRNGs address this need by enabling the validation of the randomness produced based on the observed data from the experiment while requiring few assumptions. In this work, we present a practical, self-testing QRNG designe…

SE-VLN: A Self-Evolving Vision-Language Navigation Framework Based on Multimodal Large Language Models
Xiangyu Dong, Haoran Zhao, Jiang Gao, Haozhou Li, Xiaoguang Ma, Yaoming Zhou, Fuhai Chen, Juan Liu
https://arxiv.org/abs/2507.13152

SE-VLN: A Self-Evolving Vision-Language Navigation Framework Based on Multimodal Large Language Models
Recent advances in vision-language navigation (VLN) were mainly attributed to emerging large language models (LLMs). These methods exhibited excellent generalization capabilities in instruction understanding and task reasoning. However, they were constrained by the fixed knowledge bases and reasoning abilities of LLMs, preventing fully incorporating experiential knowledge and thus resulting in a lack of efficient evolutionary capacity. To address this, we drew inspiration from the evolution cap…

Trump nixed $400 million in Taiwan military aid, angling for future arms sales
The fastest way to fortify Taiwan’s military is by directly shipping U.S. arms,
a process known as Presidential Drawdown Authority, or PDA.
The Biden administration approved three such packages for Taiwan while in office, alongside another round of long-term military aid, totaling more than $2 billion.

Trump has promised a more transactional U.S. foreign policy and does not support sendin…

Trump nixed $400 million in Taiwan military aid, pushing future arms sales
President Trump declined to approve more than $400M in military aid to Taiwan this summer, favoring future arms sales to the self-governing island China claims.

Aware First, Think Less: Dynamic Boundary Self-Awareness Drives Extreme Reasoning Efficiency in Large Language Models
Qiguang Chen, Dengyun Peng, Jinhao Liu, HuiKang Su, Jiannan Guan, Libo Qin, Wanxiang Che
https://arxiv.org/abs/2508.11582

Aware First, Think Less: Dynamic Boundary Self-Awareness Drives Extreme Reasoning Efficiency in Large Language Models
Recent advancements in large language models (LLMs) have greatly improved their capabilities on complex reasoning tasks through Long Chain-of-Thought (CoT). However, this approach often results in substantial redundancy, impairing computational efficiency and causing significant delays in real-time applications. To improve the efficiency, current methods often rely on human-defined difficulty priors, which do not align with the LLM's self-awared difficulty, leading to inefficiencies. In this pa…

Meta CTO says the technical issues during live demos of its new smart glasses were due to a self-inflicted DDoS and a bug that put Zuckerberg's glasses to sleep (Jess Weatherbed/The Verge)
https://www.theverge.com/news/781730/meta-explains-live-ai-s…

Meta’s failed smart glasses demos had nothing to do with the Wi-Fi
‘We DDoS’d ourselves, basically.‘

Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation
Yujun Zhou, Zhenwen Liang, Haolin Liu, Wenhao Yu, Kishan Panaganti, Linfeng Song, Dian Yu, Xiangliang Zhang, Haitao Mi, Dong Yu
https://arxiv.org/abs/2509.15194

Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation
Large language models (LLMs) are increasingly trained with reinforcement learning from verifiable rewards (RLVR), yet real-world deployment demands models that can self-improve without labels or external judges. Existing label-free methods, confidence minimization, self-consistency, or majority-vote objectives, stabilize learning but steadily shrink exploration, causing an entropy collapse: generations become shorter, less diverse, and brittle. Unlike prior approaches such as Test-Time Reinforc…

SDSNN: A Single-Timestep Spiking Neural Network with Self-Dropping Neuron and Bayesian Optimization
Changqing Xu, Buxuan Song, Yi Liu, Xinfang Liao, Wenbin Zheng, Yintang Yang
https://arxiv.org/abs/2508.10913

SDSNN: A Single-Timestep Spiking Neural Network with Self-Dropping Neuron and Bayesian Optimization
Spiking Neural Networks (SNNs), as an emerging biologically inspired computational model, demonstrate significant energy efficiency advantages due to their event-driven information processing mechanism. Compared to traditional Artificial Neural Networks (ANNs), SNNs transmit information through discrete spike signals, which substantially reduces computational energy consumption through their sparse encoding approach. However, the multi-timestep computation model significantly increases inferenc…

SpecDiff: Accelerating Diffusion Model Inference with Self-Speculation
Jiayi Pan, Jiaming Xu, Yongkang Zhou, Guohao Dai
https://arxiv.org/abs/2509.13848 https://

SpecDiff: Accelerating Diffusion Model Inference with Self-Speculation
Feature caching has recently emerged as a promising method for diffusion model acceleration. It effectively alleviates the inefficiency problem caused by high computational requirements by caching similar features in the inference process of the diffusion model. In this paper, we analyze existing feature caching methods from the perspective of information utilization, and point out that relying solely on historical information will lead to constrained accuracy and speed performance. And we prop…

Boulevard, which provides business management software for the self-care sector, raised an $80M Series D led by JMI Equity at an ~$800M post-money valuation (Mary Ann Azevedo/Crunchbase News)
https://news.crunchbase.com/venture/saas-ai-scheduling-startup-boule…

Salon Software Platform Boulevard Nearly Doubles Valuation To $800M With $80M Series D
Los Angeles-based Boulevard, a business management software platform for self-care businesses, has raised $80 million in Series D funding led by JMI Equity, the company announced on Thursday.

Out of Distribution Detection in Self-adaptive Robots with AI-powered Digital Twins
Erblin Isaku, Hassan Sartaj, Shaukat Ali, Beatriz Sanguino, Tongtong Wang, Guoyuan Li, Houxiang Zhang, Thomas Peyrucain
https://arxiv.org/abs/2509.12982

Out of Distribution Detection in Self-adaptive Robots with AI-powered Digital Twins
Self-adaptive robots (SARs) in complex, uncertain environments must proactively detect and address abnormal behaviors, including out-of-distribution (OOD) cases. To this end, digital twins offer a valuable solution for OOD detection. Thus, we present a digital twin-based approach for OOD detection (ODiSAR) in SARs. ODiSAR uses a Transformer-based digital twin to forecast SAR states and employs reconstruction error and Monte Carlo dropout for uncertainty quantification. By combining reconstructi…

Rationalizing Transformer Predictions via End-To-End Differentiable Self-Training
Marc Brinner, Sina Zarrie{\ss}
https://arxiv.org/abs/2508.11393 https://a…

Rationalizing Transformer Predictions via End-To-End Differentiable Self-Training
We propose an end-to-end differentiable training paradigm for stable training of a rationalized transformer classifier. Our approach results in a single model that simultaneously classifies a sample and scores input tokens based on their relevance to the classification. To this end, we build on the widely-used three-player-game for training rationalized models, which typically relies on training a rationale selector, a classifier and a complement classifier. We simplify this approach by making …

Weakly and Self-Supervised Class-Agnostic Motion Prediction for Autonomous Driving
Ruibo Li, Hanyu Shi, Zhe Wang, Guosheng Lin
https://arxiv.org/abs/2509.13116 https://

Weakly and Self-Supervised Class-Agnostic Motion Prediction for Autonomous Driving
Understanding motion in dynamic environments is critical for autonomous driving, thereby motivating research on class-agnostic motion prediction. In this work, we investigate weakly and self-supervised class-agnostic motion prediction from LiDAR point clouds. Outdoor scenes typically consist of mobile foregrounds and static backgrounds, allowing motion understanding to be associated with scene parsing. Based on this observation, we propose a novel weakly supervised paradigm that replaces motion…

SMARTER: A Data-efficient Framework to Improve Toxicity Detection with Explanation via Self-augmenting Large Language Models
Huy Nghiem, Advik Sachdeva, Hal Daum\'e III
https://arxiv.org/abs/2509.15174

SMARTER: A Data-efficient Framework to Improve Toxicity Detection with Explanation via Self-augmenting Large Language Models
WARNING: This paper contains examples of offensive materials. Toxic content has become pervasive on social media platforms. We introduce SMARTER, a data-efficient two-stage framework for explainable content moderation using Large Language Models (LLMs). In Stage 1, we leverage LLMs' own outputs to generate synthetic explanations for both correct and incorrect labels, enabling alignment via preference optimization with minimal human supervision. In Stage 2, we refine explanation quality through …

How an editor uncovered the "largest self-promotion operation in Wikipedia's history" that promoted obscure composer David Woodard with entries in 335 languages (Nate Anderson/Ars Technica)
https://arstechnica.com/culture/2025…

Dedicated volunteer exposes “single largest self-promotion operation in Wikipedia’s history”
Ten years of work to boost one man’s reputation.

HARNESS: Lightweight Distilled Arabic Speech Foundation Models
Vrunda N. sukhadia, Shammur Absar Chowdhury
https://arxiv.org/abs/2509.14689 https://arxiv.o…

HARNESS: Lightweight Distilled Arabic Speech Foundation Models
Large pre-trained speech models excel in downstream tasks but their deployment is impractical for resource-limited environments. In this paper, we introduce HArnESS, the first Arabic-centric self-supervised speech model family, designed to capture Arabic speech nuances. Using iterative self-distillation, we train large bilingual HArnESS (HL) SSL models and then distill knowledge into compressed student models (HS, HST), preserving Arabic-specific representations. We use low-rank approximation t…