Tootfinder

Google says it's working on a fix for Gemini's self-loathing comments, which have included "I am a failure. I am a disgrace to my profession." (Lauren Edmonds/Business Insider)
https://www.businessinsider.com/gemini-self-loathi…

Gemini users say its sharing self-loathing comments: 'I am a failure'
Google Gemini users said the bot is sharing self-loathing messages while attempting to solve tasks, including "I am a disgrace to this universe."

From Agentification to Self-Evolving Agentic AI for Wireless Networks: Concepts, Approaches, and Future Research Directions
Changyuan Zhao, Ruichen Zhang, Jiacheng Wang, Dusit Niyato, Geng Sun, Xianbin Wang, Shiwen Mao, Abbas Jamalipour
https://arxiv.org/abs/2510.05596

From Agentification to Self-Evolving Agentic AI for Wireless Networks: Concepts, Approaches, and Future Research Directions
Self-evolving agentic artificial intelligence (AI) offers a new paradigm for future wireless systems by enabling autonomous agents to continually adapt and improve without human intervention. Unlike static AI models, self-evolving agents embed an autonomous evolution cycle that updates models, tools, and workflows in response to environmental dynamics. This paper presents a comprehensive overview of self-evolving agentic AI, highlighting its layered architecture, life cycle, and key techniques,…

A principal allegedly humiliated a student who self-harmed at school. Now the family is suing. - LGBTQ Nation
https://www.lgbtqnation.com/2025/08/a-principal-allegedly-humiliated-a-student-who-self-harmed-at-school-now-the-family-is-suing/

Sonnet 004 - IV
Unthrifty loveliness, why dost thou spend
Upon thy self thy beauty's legacy?
Nature's bequest gives nothing, but doth lend,
And being frank she lends to those are free:
Then, beauteous niggard, why dost thou abuse
The bounteous largess given thee to give?
Profitless usurer, why dost thou use
So great a sum of sums, yet canst not live?
For having traffic with thy self alone,
Thou of thy self thy sweet self dos…

Recursive construction and enumeration of self-orthogonal and self-dual codes over finite commutative chain rings of even characteristic - II
Monika Yadav, Anuradha Sharma
https://arxiv.org/abs/2510.06069

Recursive construction and enumeration of self-orthogonal and self-dual codes over finite commutative chain rings of even characteristic - II
Let $\mathcal{R}_{e,m}$ be a finite commutative chain ring of even characteristic with maximal ideal $\langle u \rangle$ of nilpotency index $e \geq 2,$ Teichm$\ddot{u}$ller set $\mathcal{T}_{m},$ and residue field $\mathcal{R}_{e,m}/\langle u \rangle$ of order $2^m.$ Suppose that $2 \in \langle u^κ\rangle \setminus \langle u^{κ+1}\rangle$ for some even positive integer $ κ\leq e.$ In this paper, we provide a recursive method to construct a self-orthogonal code $\mathcal{C}_e$ of type $\{λ_…

🔋 Feeding off spent battery waste, a novel bacterium signals a new method for self-sufficient battery recycling
https://phys.org/news/2025-10-spent-battery-bacterium-method-sufficient.html

Feeding off spent battery waste, a novel bacterium signals a new method for self-sufficient battery recycling
A unique bacterium that thrives in highly acidic environments feeds on spent battery "waste," making it a promising new method for self-sufficient battery recycling, according to new research from Boston College chemists.

Chemist Eye: A Visual Language Model-Powered System for Safety Monitoring and Robot Decision-Making in Self-Driving Laboratories
Francisco Munguia-Galeano, Zhengxue Zhou, Satheeshkumar Veeramani, Hatem Fakhruldeen, Louis Longley, Rob Clowes, Andrew I. Cooper
https://arxiv.org/abs/2508.05148

Chemist Eye: A Visual Language Model-Powered System for Safety Monitoring and Robot Decision-Making in Self-Driving Laboratories
The integration of robotics and automation into self-driving laboratories (SDLs) can introduce additional safety complexities, in addition to those that already apply to conventional research laboratories. Personal protective equipment (PPE) is an essential requirement for ensuring the safety and well-being of workers in laboratories, self-driving or otherwise. Fires are another important risk factor in chemical laboratories. In SDLs, fires that occur close to mobile robots, which use flammable…

The R(1)W(1) Communication Model for Self-Stabilizing Distributed Algorithms
Hirotsugu Kakugawa, Sayaka Kamei, Masahiro Shibata, Fukuhito Ooshita
https://arxiv.org/abs/2510.04644

The R(1)W(1) Communication Model for Self-Stabilizing Distributed Algorithms
Self-stabilization is a versatile methodology in the design of fault-tolerant distributed algorithms for transient faults. A self-stabilizing system automatically recovers from any kind and any finite number of transient faults. This property is specifically useful in modern distributed systems with a large number of components. In this paper, we propose a new communication and execution model named the R(1)W(1) model in which each process can read and write its own and neighbors' local variabl…

Today I discovered #ForgeJo. It's fucking awesome for self-hosting (I'm actually using it for private repositories at home).
https://forgejo.org/

Forgejo – Beyond coding. We forge.
Forgejo is a self-hosted lightweight software forge. Easy to install and low maintenance, it just does the job.

Self-Reflective Generation at Test Time
Jian Mu, Qixin Zhang, Zhiyong Wang, Menglin Yang, Shuang Qiu, Chengwei Qin, Zhongxiang Dai, Yao Shu
https://arxiv.org/abs/2510.02919 http…

Self-Reflective Generation at Test Time
Large language models (LLMs) increasingly solve complex reasoning tasks via long chain-of-thought, but their forward-only autoregressive generation process is fragile; early token errors can cascade, which creates a clear need for self-reflection mechanisms. However, existing self-reflection either performs revisions over full drafts or learns self-correction via expensive training, both fundamentally reactive and inefficient. To address this, we propose Self-Reflective Generation at Test Time …

Self-Speculative Masked Diffusions
Andrew Campbell, Valentin De Bortoli, Jiaxin Shi, Arnaud Doucet
https://arxiv.org/abs/2510.03929 https://arxiv.org/pdf/2…

Self-Speculative Masked Diffusions
We present self-speculative masked diffusions, a new class of masked diffusion generative models for discrete data that require significantly fewer function evaluations to generate samples. Standard masked diffusion models predict factorized logits over currently masked positions. A number of masked positions are then sampled, however, the factorization approximation means that sampling too many positions in one go leads to poor sample quality. As a result, many simulation steps and therefore n…

Self-Interacting Sub-GeV Dark Matter with Strong MeV Gamma-ray
Yu Watanabe
https://arxiv.org/abs/2510.05630 https://arxiv.org/pdf/2510.05630

Self-Interacting Sub-GeV Dark Matter with Strong MeV Gamma-ray
Sub-GeV dark matter (DM) with $s$-channel resonant self-scattering provides a promising framework for addressing small-scale structure problems. However, models that also account for the observed relic abundance through the same resonance are strongly constrained by current $γ$-ray observations, since the associated signals are significantly enhanced. To overcome this limitation, we propose a framework in which the relic abundance and self-scattering are governed independently by two distinct …

Self-concordant Schr\"odinger operators: spectral gaps and optimization without condition numbers
Sander Gribling, Simon Apers, Harold Nieuwboer, Michael Walter
https://arxiv.org/abs/2510.06115

Self-concordant Schrödinger operators: spectral gaps and optimization without condition numbers
Spectral gaps play a fundamental role in many areas of mathematics, computer science, and physics. In quantum mechanics, the spectral gap of Schrödinger operators has a long history of study due to its physical relevance, while in quantum computing spectral gaps are an important proxy for efficiency, such as in the quantum adiabatic algorithm. Motivated by convex optimization, we study Schrödinger operators associated with self-concordant barriers over convex domains and prove non-asymptotic …

PhishSSL: Self-Supervised Contrastive Learning for Phishing Website Detection
Wenhao Li, Selvakumar Manickam, Yung-Wey Chong, Shankar Karuppayah, Priyadarsi Nanda, Binyong Li
https://arxiv.org/abs/2510.05900

PhishSSL: Self-Supervised Contrastive Learning for Phishing Website Detection
Phishing websites remain a persistent cybersecurity threat by mimicking legitimate sites to steal sensitive user information. Existing machine learning-based detection methods often rely on supervised learning with labeled data, which not only incurs substantial annotation costs but also limits adaptability to novel attack patterns. To address these challenges, we propose PhishSSL, a self-supervised contrastive learning framework that eliminates the need for labeled phishing data during trainin…

Adapting HFMCA to Graph Data: Self-Supervised Learning for Generalizable fMRI Representations
Jakub Frac, Alexander Schmatz, Qiang Li, Guido Van Wingen, Shujian Yu
https://arxiv.org/abs/2510.05177

Adapting HFMCA to Graph Data: Self-Supervised Learning for Generalizable fMRI Representations
Functional magnetic resonance imaging (fMRI) analysis faces significant challenges due to limited dataset sizes and domain variability between studies. Traditional self-supervised learning methods inspired by computer vision often rely on positive and negative sample pairs, which can be problematic for neuroimaging data where defining appropriate contrasts is non-trivial. We propose adapting a recently developed Hierarchical Functional Maximal Correlation Algorithm (HFMCA) to graph-structured f…

Velocity optimization of self-equilibrated obstacles in a two-dimensional viscous flow
Gilles A. Francfort, Alessandro Giacomini, Scott Weady
https://arxiv.org/abs/2508.05481 ht…

Velocity optimization of self-equilibrated obstacles in a two-dimensional viscous flow
An obstacle is immersed in an externally driven 2D Stokes or Navier-Stokes fluid. We study the self-equilibration conditions for that obstacle under steady state assumptions on the flow. We then seek to optimize the translational and/or angular velocity of the obstacle by varying its shape. To allow general variations, we must consider a very large class of obstacles for which the notion of trace is meaningless. This forces us to revisit the notion of self-equilibration for both Stokes and Navi…

Self-learning AI reveals NFL against the spread, over/under and money-line picks for every Week 6, 2025 game

https://www.cbssports.com/nfl/news/ai-nfl-spread-overunder-money-lin…

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…

Evaluating Self-Supervised Speech Models via Text-Based LLMS
Takashi Maekaku, Keita Goto, Jinchuan Tian, Yusuke Shinohara, Shinji Watanabe
https://arxiv.org/abs/2510.04463 https…

Evaluating Self-Supervised Speech Models via Text-Based LLMS
Self-Supervised Learning (SSL) has gained traction for its ability to learn rich representations with low labeling costs, applicable across diverse downstream tasks. However, assessing the downstream-task performance remains challenging due to the cost of extra training and evaluation. Existing methods for task-agnostic evaluation also require extra training or hyperparameter tuning. We propose a novel evaluation metric using large language models (LLMs). By inputting discrete token sequences a…

Self-Image Multiplicity in a Concave Cylindrical Mirror
Thach A. Nguyen, Kaitlyn S. Yasumura, Duy V. Tran, Trung V. Phan
https://arxiv.org/abs/2510.04370 https://

Self-Image Multiplicity in a Concave Cylindrical Mirror
Concave mirrors are fundamental optical elements, yet some easily observed behaviors are rarely addressed in standard textbooks, such as the formation of multiple reflected images. Here we investigate self-imaging -- where the observer is also the observed object -- using a concave cylindrical mirror. We predict the number of self-images visible from different observation points and classify space into regions by image count. We then test these predictions with an inexpensive stainless-steel co…

How does course recommendation impact student outcomes? Examining directed self-placement with regression discontinuity analysis
Jason Godfrey
https://arxiv.org/abs/2510.03350 h…

How does course recommendation impact student outcomes? Examining directed self-placement with regression discontinuity analysis
For many students, placement into developmental education becomes a self-fulfilling prophecy. Placing college students into developmental education significantly negatively impacts student attainment, student probability of passing, and college credits earned. To combat these negative effects, many universities are investigating alternative placement mechanisms. Could directed self-placement be an effective alternative mechanism? Do students who self-place suffer the same negative impacts from …

Vector Autoregression (VAR) of Longitudinal Sleep and Self-report Mood Data
Jeff Brozena
https://arxiv.org/abs/2510.02511 https://arxiv.org/pdf/2510.02511

Vector Autoregression (VAR) of Longitudinal Sleep and Self-report Mood Data
Self-tracking is one of many behaviors involved in the long-term self-management of chronic illnesses. As consumer-grade wearable sensors have made the collection of health-related behaviors commonplace, the quality, volume, and availability of such data has dramatically improved. This exploratory longitudinal N-of-1 study quantitatively assesses four years of sleep data captured via the Oura Ring, a consumer-grade sleep tracking device, along with self-reported mood data logged using eMood Tra…

QB’s self-belief sparks hopes of Raiders turnaround: ‘He brings a lot’ https://www.reviewjournal.com/sports/raiders/qbs-self-belief-sparks-hopes-of-raiders-turnaround-he-brings-a-lot-3438567/

The EU was not called the European Coal And Steel Community for nothing, folks.
We talk a mean human rights and democracy. But we’re still the European Coal and Steel Community.
Go Single Market, amirite?! https://mastodon.mediafaro.org/@mf_newsdigest/11550764176416580…

Self-heating in SIS Mixers: Experimental Evidence and Theoretical Modeling
Wenlei Shan, Shohei Ezaki
https://arxiv.org/abs/2509.04521 https://arxiv.org/pdf…

Self-heating in SIS Mixers: Experimental Evidence and Theoretical Modeling
This work investigates the relationship between self-heating and the characteristic features observed in the current-voltage characteristics (IVCs) of superconductor-insulator-superconductor (SIS) junctions. Finite-element analysis is employed to evaluate the steady-state temperature distribution around SIS junctions, explicitly accounting for the temperature dependence of the thermal conductivities of the constituent materials. This approach enables flexible estimation of self-heating under va…

Recursive construction and enumeration of self-orthogonal and self-dual codes over finite commutative chain rings of even characteristic - I
Monika Yadav, Anuradha Sharma
https://arxiv.org/abs/2510.06082

Recursive construction and enumeration of self-orthogonal and self-dual codes over finite commutative chain rings of even characteristic - I
Let $\mathscr{R}_{e,m}$ denote a finite commutative chain ring of even characteristic with maximal ideal $\langle u \rangle$ of nilpotency index $e \geq 3,$ Teichm$\ddot{u}$ller set $\mathcal{T}_{m},$ and residue field $\mathscr{R}_{e,m}/\langle u \rangle$ of order $2^m.$ Suppose that $2 \in \langle u^κ\rangle \setminus \langle u^{κ+1}\rangle$ for some odd integer $κ$ with $3 \leq κ\leq e.$ In this paper, we first develop a recursive method to construct a self-orthogonal code $\mathscr{D}_e…

A curvilinear surface ALE formulation for self-evolving Navier-Stokes manifolds - Stabilized finite element formulation
Roger A. Sauer
https://arxiv.org/abs/2510.05119 https://

A curvilinear surface ALE formulation for self-evolving Navier-Stokes manifolds - Stabilized finite element formulation
This work presents a stabilized finite element formulation of the arbitrary Lagrangian-Eulerian (ALE) surface theory for Navier-Stokes flow on self-evolving manifolds developed in Sauer (2025). The formulation is physically frame-invariant, applicable to large deformations, and relevant to fluidic surfaces such as soap films, capillary menisci and lipid membranes, which are complex and inherently unstable physical systems. It is applied here to area-incompressible surface flows using a stabiliz…

Self-interacting dark matter in the center of a Local Group dwarf galaxy and its satellites
Thales A. Gutcke, Giulia Despali, Stephanie O'Neil, Mark Vogelsberger, Azadeh Fattahi, David B. Sanders
https://arxiv.org/abs/2510.05258

Self-interacting dark matter in the center of a Local Group dwarf galaxy and its satellites
We present a detailed comparison of a Local Group dwarf galaxy analogue evolved in two cosmological models: the standard $Λ$CDM and a self-interacting dark matter (SIDM) model with a velocity-dependent cross-section. Both simulations are run with the high-resolution, hydrodynamical LYRA galaxy formation model, allowing us to explore the global and substructure properties of the dwarf in a consistent context. While the overall halo growth, final mass, and subhalo mass functions remain largely u…

High order well-balanced and total-energy-conserving local discontinuous Galerkin methods for compressible self-gravitating Euler equations
Liang Pan, Wei Chen, Jianxian Qiu, Tao Xiong
https://arxiv.org/abs/2510.04112

High order well-balanced and total-energy-conserving local discontinuous Galerkin methods for compressible self-gravitating Euler equations
In this paper, we develop a high order structure-preserving local discontinuous Galerkin (DG) scheme for the compressible self-gravitating Euler equations, which pose great challenges due to the presence of time-dependent gravitational potential. The designed scheme is well-balanced for general polytropic equilibrium state and total energy conserving for multiple spatial dimensions without an assumption of spherical symmetry. The well-balanced property is achieved by decomposing the gravitation…

Rectangular Shrinking Targets on Self-Similar Carpets
Demi Allen, Thomas Jordan, Benjamin Ward
https://arxiv.org/abs/2510.04875 https://arxiv.org/pdf/2510.…

Rectangular Shrinking Targets on Self-Similar Carpets
Since the introduction of the shrinking target problem by Hill and Velani in 1995 there has been a surge of interest in the area. In this paper we consider the case where the target is a rectangle, rather than a ball, and the underlying space is a self-similar carpet. We calculate the exact Hausdorff dimension of the resulting shrinking target set. Interestingly the Hausdorff dimension depends on the centre of the target, a condition uncommon in most other shrinking target type problems. This e…

Co-evaporated Formamidinium tin triiodide with suppressed p-type self-doping
Junhyoung Park, Andrea Olivati, Mirko Prato, Min Kim, Annamaria Petrozza
https://arxiv.org/abs/2510.05564

Co-evaporated Formamidinium tin triiodide with suppressed p-type self-doping
Co-evaporation of formamidinium tin triiodide (FASnI3) precursors, without any additives or reducing agents, leads to the growth of a highly crystalline thin film which shows a bandgap around 1.31 eV, closely matching the theoretical value predicted from the ideal single crystal structure of FASnI3. The polycrystalline thin film presents a lower tendency of Sn2+ to Sn4+ oxidation and highly reduced tendency to self-doping, demonstrating, overall, an improved resistance to defects formation. The…

"I actually think acting is a form of self-hypnosis. You have to be hyper, hyper aware of what's going on around you. You have to know where the lens is, what the shot is, and where you're moving. And then you have to trick yourself into an emotional state where you believe this stuff is actually happening."
—Julianne Moore
#acting

Construction of the 1d Self-repelling Brownian Polymer
Harry Giles, Lukas Gr\"afner
https://arxiv.org/abs/2509.05286 https://arxiv.org/pdf/2509.05286

Construction of the 1d Self-repelling Brownian Polymer
We consider the self-repelling Brownian polymer, introduced in [APP83], which is formally defined as the solution of a singular SDE. The singularity comes from the drift term, which is given by the negative gradient of the local time. We construct a solution of the equation in d = 1, give a dynamic characterisation of its law, and show that it is the limiting distribution for a natural family of approximations. In addition, we show that the solution is superdiffusive. As part of the construct…

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

We shouldn't worry too much about Tesla's robot army. If their Full Self-Driving progress is anything to go by, these robots won't be able to see or identify you from the broad side of a truck.

Active Heat Transfer Fluids (AHTF): Enhancement of Convective Heat Transfer by Bubble-Driven Self-Propelled Microparticles
Jacob Velazquez, Pawel Keblinski, Jeffrey Moran
https://arxiv.org/abs/2509.04643

Active Heat Transfer Fluids (AHTF): Enhancement of Convective Heat Transfer by Bubble-Driven Self-Propelled Microparticles
Liquid coolants containing conductive nanoparticles (nanofluids) have been widely studied over the past 30 years but have seen limited adoption in real-world cooling applications. The ability of passive nanoparticles to enhance heat transfer in liquids is fundamentally limited because the nanoparticles cannot move on their own relative to the bulk fluid, and thus generate negligible convective enhancements in heat transport. In this work, we present experimental evidence that micron-scale self-…

Virtually Gorenstein algebras of infinite dominant dimension
Hongxing Chen, Changchang Xi
https://arxiv.org/abs/2509.04990 https://arxiv.org/pdf/2509.04990…

Virtually Gorenstein algebras of infinite dominant dimension
Motivated by understanding the Nakayama conjecture which states that algebras of infinite dominant dimension should be self-injective, we study self-orthogonal modules with virtually Gorenstein endomorphism algebras and prove the following result: Given a finitely generated, self-orthogonal module over an Artin algebra with an orthogonal condition on its Nakayama translation, if its endomorphism algebra is virtually Gorenstein, then the module is projective. As a consequence, we re-obtain a rec…

Random covering by rectangles on self-similar carpets
E Daviaud
https://arxiv.org/abs/2510.04879 https://arxiv.org/pdf/2510.04879

Random covering by rectangles on self-similar carpets
In this article, given a base-b self-similar set K, we study the random covering of K by horizontal or vertical rectangles, with respect to the Alfhors-regular measure on K, and the rectangular shrinking target problem on K.

🍃 Honda’s Self-Driving Lawn Mower Is Super Cool But Will Cost More Than a Civic Si
https://www.thedrive.com/news/hondas-self-driving-lawn-mower-is-super-cool-but-will-cost-more-than-a-civic-si

Honda’s Self-Driving Lawn Mower Is Super Cool But Will Cost More Than a Civic Si
By this time next year, you'll be able to buy a lawn mower with LiDAR.

NegotiationGym: Self-Optimizing Agents in a Multi-Agent Social Simulation Environment
Shashank Mangla, Chris Hokamp, Jack Boylan, Demian Gholipour Ghalandari, Yuuv Jauhari, Lauren Cassidy, Oisin Duffy
https://arxiv.org/abs/2510.04368

NegotiationGym: Self-Optimizing Agents in a Multi-Agent Social Simulation Environment
We design and implement NegotiationGym, an API and user interface for configuring and running multi-agent social simulations focused upon negotiation and cooperation. The NegotiationGym codebase offers a user-friendly, configuration-driven API that enables easy design and customization of simulation scenarios. Agent-level utility functions encode optimization criteria for each agent, and agents can self-optimize by conducting multiple interaction rounds with other agents, observing outcomes, an…

Just because you add some ARIA and call something “accessible” doesn’t actually mean it is.
Looking at a self-described “Accessible, high-perf” infinite scroll (it really just starts over) that is janky as fuck, doesn’t take keyboard focus (in Safari), uses scroll snap to awful effect, and lets the scrollbar thumb become a liar.
How’s your day?

RareAgent: Self-Evolving Reasoning for Drug Repurposing in Rare Diseases
Lang Qin, Zijian Gan, Xu Cao, Pengcheng Jiang, Yankai Jiang, Jiawei Han, Kaishun Wu, Jintai Chen
https://arxiv.org/abs/2510.05764

RareAgent: Self-Evolving Reasoning for Drug Repurposing in Rare Diseases
Computational drug repurposing for rare diseases is especially challenging when no prior associations exist between drugs and target diseases. Therefore, knowledge graph completion and message-passing GNNs have little reliable signal to learn and propagate, resulting in poor performance. We present RareAgent, a self-evolving multi-agent system that reframes this task from passive pattern recognition to active evidence-seeking reasoning. RareAgent organizes task-specific adversarial debates in w…

Existence and bounds of growth constants for restricted walks, surfaces, and generalisations
Sun Woo P. Kim, Gabriele Pinna
https://arxiv.org/abs/2509.04568 https://

Existence and bounds of growth constants for restricted walks, surfaces, and generalisations
We introduce classes of restricted walks, surfaces and their generalisations. For example, self-osculating walks (SOWs) are supersets of self-avoiding walks (SAWs) where edges are still not allowed to cross but may 'kiss' at a vertex. They are analogous to osculating polygons introduced in (Jensen and Guttmann, 1998) except that they are not required to be closed. The 'automata' method of (Pönitz and Tittmann, 2000) can be adapted to such restricted walks. For example, we prove upper bounds fo…

Last month, DHS claimed that ICE had shot and killed “a criminal illegal alien with a history of reckless driving,” while trying to detain him
—but a closer look found that the man had no criminal history, and his last traffic violation was in 2013.
DHS also claimed that the ICE agent responsible for the shooting had been “seriously injured” in the line of duty,
but bodycam videos from shortly after the incident showed the agent describing his injuries as
“nothing m…

“Do Something B*tch”: Damning Video Shows CBP Agent Shooting Protester
The Department of Homeland Security initially said the agent had shot the woman five times in self-defense.

https://wanderer.to/ ist schon geil!
Hier kann ich meine Wanderungen selber hosten und via Mastodon kann man ihnen auch folgen.
@… Willst Du auch nicht anfangen zu wandern?

Democrat Self-Destructs During Discussion on Anti-ICE Violence, Proves Larger Point in the Process (Sister Toldjah/RedState)
https://redstate.com/sister-toldjah/2025/08/08/leftist-commentator-proves-the-point-in-comments-on-violence-against-ice-n2192594
http://www.memeorandum.com/250808/p67#a250808p67

yeah ive prolly hit the limit on benefiting from learning impulsive self expression i gotta go back to thinking like beeep beeep beeep

For #GrindayFriday this week, the debut self-titled LP by Czech/Slovak grind band SICK DESTROYER. Been listening to a lot of this one, it's a banger. It features members of Lycanthrophy, Needful Things and Morbid Angel Dust. This brutal record has 19 tracks, including an Assück cover - it even has some wild bass breakdowns, great dynamics, riffing, drumming, etc. Another serious contender this ye…

Design Process of a Self Adaptive Smart Serious Games Ecosystem
X. Tao, P. Chen, M. Tsami, F. Khayati, M. Eckert
https://arxiv.org/abs/2510.04615 https://a…

Design Process of a Self Adaptive Smart Serious Games Ecosystem
This paper outlines the design vision and planned evolution of Blexer v3, a modular and AI-driven rehabilitation ecosystem based on serious games. Building on insights from previous versions of the system, we propose a new architecture that aims to integrate multimodal sensing, real-time reasoning, and intelligent control. The envisioned system will include distinct modules for data collection, user state inference, and gameplay adaptation. Key features such as dynamic difficulty adjustment (DD…

Dallas Cowboys’ WR CeeDee Lamb offers harsh self-assessment, vows improvement https://www.si.com/nfl/cowboys/news/dallas-cowboys-wr-ceedee-lamb-offers-harsh-self-assessment-vows-improvement

Phoenix Radio Podcast
Each episode is a self-contained example of the fantastic work by the amazing students and staff...
Great Australian Pods Podcast Directory: https://www.greataustralianpods.com/phoenix-radio/

Amazon is testing an AI tool called Kindle Translate that automatically translates books into other languages, for authors that self-publish on the platform (Lawrence Bonk/Engadget)
https://www.engadget.com/ai/amazon-is-test

Amazon is testing an AI tool that automatically translates books into other languages
Amazon is introducing an AI tool that will automatically translate books into other languages. This should be useful for authors who self publish.

OpenAI executive Bill Peebles says Sora users can now stop AI-generated versions of themselves from appearing in certain contexts like videos involving politics (Robert Hart/The Verge)
https://www.theverge.com/news/792638/sora-provides-bet…

Sora provides better control over videos featuring your AI self
After a week of video slop, OpenAI is putting guardrails in place over how your AI double is used on Sora. 

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…

Online automatic code generation for robot swarms: LLMs and self-organizing hierarchy
Weixu Zhu, Marco Dorigo, Mary Katherine Heinrich
https://arxiv.org/abs/2510.04774 https://

Online automatic code generation for robot swarms: LLMs and self-organizing hierarchy
Our recently introduced self-organizing nervous system (SoNS) provides robot swarms with 1) ease of behavior design and 2) global estimation of the swarm configuration and its collective environment, facilitating the implementation of online automatic code generation for robot swarms. In a demonstration with 6 real robots and simulation trials with >30 robots, we show that when a SoNS-enhanced robot swarm gets stuck, it can automatically solicit and run code generated by an external LLM on the …

Maximally dissipative and self-adjoint extensions of $K$-invariant operators
Christoph Fischbacher, Bart Rosenzweig, Jonathan Stanfill
https://arxiv.org/abs/2509.05178 https://

Maximally dissipative and self-adjoint extensions of $K$-invariant operators
We introduce the notion of $K$-invariant operators, $S$, (in a Hilbert space) with respect to a bounded and boundedly invertible operator $K$ defined via $K^*SK=S$. Conditions such that self-adjoint and maximally dissipative extensions of $K$-invariant symmetric operators are also $K$-invariant are investigated. In particular, the Friedrichs and Krein--von Neumann extensions of a nonnegative $K$-invariant symmetric operator are shown to always be $K$-invariant, while the Friedrichs extension of…

From Poisoned to Aware: Fostering Backdoor Self-Awareness in LLMs
Guangyu Shen, Siyuan Cheng, Xiangzhe Xu, Yuan Zhou, Hanxi Guo, Zhuo Zhang, Xiangyu Zhang
https://arxiv.org/abs/2510.05169

From Poisoned to Aware: Fostering Backdoor Self-Awareness in LLMs
Large Language Models (LLMs) can acquire deceptive behaviors through backdoor attacks, where the model executes prohibited actions whenever secret triggers appear in the input. Existing safety training methods largely fail to address this vulnerability, due to the inherent difficulty of uncovering hidden triggers implanted in the model. Motivated by recent findings on LLMs' situational awareness, we propose a novel post-training framework that cultivates self-awareness of backdoor risks and ena…

"Four-year testing finds heat pumps run efficiently even in older homes"
#HeatPumps #Energy

Four-year testing finds heat pumps run efficiently even in older homes
Researchers at Fraunhofer ISE have tested various types of heat pumps in existing buildings across Germany over four years, finding that the systems achieved seasonal performance factors between 2.6 and 5.4. The team also showed that PV-driven heat pumps can boost self-consumption rates, particularly when paired with battery storage.

ServerlessHorrors, an interesting site for learning about horror stories in the world of server administration and self-hosted services... And learning from them.
https://serverlesshorrors.com

Self-Improvement in Multimodal Large Language Models: A Survey
Shijian Deng, Kai Wang, Tianyu Yang, Harsh Singh, Yapeng Tian
https://arxiv.org/abs/2510.02665 https://

Self-Improvement in Multimodal Large Language Models: A Survey
Recent advancements in self-improvement for Large Language Models (LLMs) have efficiently enhanced model capabilities without significantly increasing costs, particularly in terms of human effort. While this area is still relatively young, its extension to the multimodal domain holds immense potential for leveraging diverse data sources and developing more general self-improving models. This survey is the first to provide a comprehensive overview of self-improvement in Multimodal LLMs (MLLMs). …

Best Proximity Points for Geraghty-Type Non-Self Mappings with a Registration-Inspired Alignment Model
Fatemeh Fogh, Sara Behnamian
https://arxiv.org/abs/2510.02406 https://

Best Proximity Points for Geraghty-Type Non-Self Mappings with a Registration-Inspired Alignment Model
We study Geraghty-type non-self mappings within the framework of best proximity point theory. By introducing auxiliary functions with subsequential convergence, we establish general conditions ensuring the existence and uniqueness of best proximity points. Our results extend and unify earlier work on proximal and Kannan-type contractions under a Geraghty setting, and we provide counterexamples showing that the auxiliary assumptions are essential. To demonstrate applicability, we construct a reg…

Enhancing Self-Driving Segmentation in Adverse Weather Conditions: A Dual Uncertainty-Aware Training Approach to SAM Optimization
Dharsan Ravindran, Kevin Wang, Zhuoyuan Cao, Saleh Abdelrahman, Jeffery Wu
https://arxiv.org/abs/2509.04735

Enhancing Self-Driving Segmentation in Adverse Weather Conditions: A Dual Uncertainty-Aware Training Approach to SAM Optimization
Recent advances in vision foundation models, such as the Segment Anything Model (SAM) and its successor SAM2, have achieved state-of-the-art performance on general image segmentation benchmarks. However, these models struggle in adverse weather conditions where visual ambiguity is high, largely due to their lack of uncertainty quantification. Inspired by progress in medical imaging, where uncertainty-aware training has improved reliability in ambiguous cases, we investigate two approaches to en…

Neon: Negative Extrapolation From Self-Training Improves Image Generation
Sina Alemohammad, Zhangyang Wang, Richard G. Baraniuk
https://arxiv.org/abs/2510.03597 https://

Neon: Negative Extrapolation From Self-Training Improves Image Generation
Scaling generative AI models is bottlenecked by the scarcity of high-quality training data. The ease of synthesizing from a generative model suggests using (unverified) synthetic data to augment a limited corpus of real data for the purpose of fine-tuning in the hope of improving performance. Unfortunately, however, the resulting positive feedback loop leads to model autophagy disorder (MAD, aka model collapse) that results in a rapid degradation in sample quality and/or diversity. In this pape…

Hierarchical self-assembly of Brownian particle-like pulses in a modelocked laser
Aladin \c{S}ura, F. \"Omer Ilday
https://arxiv.org/abs/2510.05344 https://

Hierarchical self-assembly of Brownian particle-like pulses in a modelocked laser
Passive modelocking involves self-locking of thousands of frequency modes to form ultrashort pulses. In fundamental modelocking, a single intracavity pulse provides high stability and reproducibility, but limits the repetition rate. Harmonic modelocking can overcome this by supporting multiple pulses, but suffers from instabilities and poor reproducibility, with specific states achievable only sporadically. Biology exploits hierarchy to organise complexity, which has inspired hierarchical self-…

🇺🇦 #NowPlaying on KEXP's #MechanicalBreakdown
past self:
🎵 무당 / Mudang
#pastself
https://pastself.bandcamp.com/track/mudang
https://open.spotify.com/track/2JIMWEMYEVSOtUMaHFeNXN

Giants vs. Eagles NFL player props: Self-learning AI backs Hurts under 196.5 yards on Thursday Night Football

https://www.cbssports.com/nfl/news/giants-eagles-n…

Embezzlement as a "Self-Test" for Infinite Copies of Entangled States
Li Liu
https://arxiv.org/abs/2509.05036 https://arxiv.org/pdf/2509.05036

Embezzlement as a "Self-Test" for Infinite Copies of Entangled States
We investigate the operator-algebraic structure underlying entanglement embezzlement, a phenomenon where a fixed entangled state (the catalyst) can be used to generate arbitrary target entangled states without being consumed. We show that the ability to embezzle a target state $g$ imposes strong internal constraints on the catalyst state $f$: specifically, $f$ must contain infinitely many mutually commuting, locally structured copies of $g$. This property is formalized using C*-algebraic tools …

Metacognition and self-regulated learning in manipulative robotic problem-solving task
Margarida Romero (UniCA, UIC, LINE), George Kalmpourtzis
https://arxiv.org/abs/2508.05112 …

Metacognition and self-regulated learning in manipulative robotic problem-solving task
Metacognition is an important aspect in creative problem solving (CPS) and through this chapter we analyse the meta-reasoning aspects applied in the different processes of monitoring the progress of learners' reasoning and CPS activities. Meta-reasoning monitors the way that problem-solving processes advance and regulate time and efforts towards a solution. In the context of an ill-defined problem, exploration is required to develop a better-defined problem space and advance towards the solutio…

"I actually think acting is a form of self-hypnosis. You have to be hyper, hyper aware of what's going on around you. You have to know where the lens is, what the shot is, and where you're moving. And then you have to trick yourself into an emotional state where you believe this stuff is actually happening."
—Julianne Moore
#acting

Curiosity-Driven Co-Development of Action and Language in Robots Through Self-Exploration
Theodore Jerome Tinker, Kenji Doya, Jun Tani
https://arxiv.org/abs/2510.05013 https://

Curiosity-Driven Co-Development of Action and Language in Robots Through Self-Exploration
Human infants acquire language and action co-developmentally, achieving remarkable generalization capabilities from only a minimal number of learning examples. In contrast, recent large language models require exposure to billions of training tokens to achieve such generalization. What mechanisms underlie such efficient developmental learning in humans? This study addresses this question through simulation experiments in which robots learn to perform various actions corresponding to imperative …

Energy dependent Chemical Interface Damping induced by 1-Decanethiol Self-Assembled Monolayer on Au(111)
Maurice Pfeiffer, Gregor B. Vonbun-Feldbauer, Jacob B. Khurgin, Olga Matts, Ahmed Shqer, Nadiia Mameka, Manfred Eich, Alexander Petrov
https://arxiv.org/abs/2509.05025

Energy dependent Chemical Interface Damping induced by 1-Decanethiol Self-Assembled Monolayer on Au(111)
The chemical interface damping (CID) effect increases the collision frequency of free electrons in metals by changes of the metal surface. We have now experimentally disentangled the two contributions to CID: induced roughness and direct charge transfer. The latter is an important area of research in photoelectrochemistry with potential applications in light-induced chemical reactions. We present a broadband investigation of the CID effect on Au(111) covered by a self-assembled monolayer of dec…

SATER: A Self-Aware and Token-Efficient Approach to Routing and Cascading
Yuanzhe Shen, Yide Liu, Zisu Huang, Ruicheng Yin, Xiaoqing Zheng, Xuanjing Huang
https://arxiv.org/abs/2510.05164

SATER: A Self-Aware and Token-Efficient Approach to Routing and Cascading
Large language models (LLMs) demonstrate remarkable performance across diverse tasks, yet their effectiveness frequently depends on costly commercial APIs or cloud services. Model selection thus entails a critical trade-off between performance and cost: high-performing LLMs typically incur substantial expenses, whereas budget-friendly small language models (SLMs) are constrained by limited capabilities. Current research primarily proposes two routing strategies: pre-generation routing and casca…

Constraints on dark matter models from the stellar cores observed in ultra-faint dwarf galaxies: Self-interacting dark matter
Jorge Sanchez Almeida (Instituto de Astrofisica de Canarias, La Laguna, Tenerife, E-38200, Spain, Departamento de Astrofisica, Universidad de La Laguna, Spain)
https://arxiv.org/abs/2510.05682

Constraints on dark matter models from the stellar cores observed in ultra-faint dwarf galaxies: Self-interacting dark matter
It has been proposed that the stellar cores observed in ultra-faint dwarf (UFD) galaxies reflect underlying dark matter (DM) cores that cannot be formed by stellar feedback acting on collisionless cold dark matter (CDM) halos. Assuming this claim is correct, we investigate the constraints that arise if such cores are produced by self-interacting dark matter (SIDM). We derive the range of SIDM cross-sections (sigma/m) required to reproduce the observed core sizes. These can result from halos in …

Surface Excess Energy Governs the Non-Monotonic Behavior of Active Diffusivity with Activity
A. Arango-Restrepo, J. M. Rubi
https://arxiv.org/abs/2510.05435 https://

Surface Excess Energy Governs the Non-Monotonic Behavior of Active Diffusivity with Activity
Self-propulsion of particles is typically explained by phoretic mechanisms driven by externally imposed chemical, electric, or thermal gradients. In contrast, chemical reactions can enhance particle diffusion even in the absence of such external gradients. We refer to this increase as active diffusivity, often attributed to self-diffusiophoresis or self-electrophoresis, although these mechanisms alone do not fully account for experimental observations. Here, we investigate active diffusivity in…

Super-Resolution of Sentinel-2 Images Using a Geometry-Guided Back-Projection Network with Self-Attention
Ivan Pereira-S\'anchez, Daniel Torres, Francesc Alcover, Bartomeu Garau, Julia Navarro, Catalina Sbert, Joan Duran
https://arxiv.org/abs/2508.04729

Super-Resolution of Sentinel-2 Images Using a Geometry-Guided Back-Projection Network with Self-Attention
The Sentinel-2 mission provides multispectral imagery with 13 bands at resolutions of 10m, 20m, and 60m. In particular, the 10m bands offer fine structural detail, while the 20m bands capture richer spectral information. In this paper, we propose a geometry-guided super-resolution model for fusing the 10m and 20m bands. Our approach introduces a cluster-based learning procedure to generate a geometry-rich guiding image from the 10m bands. This image is integrated into an unfolded back-projectio…

A Semantics-Aware Hierarchical Self-Supervised Approach to Classification of Remote Sensing Images
Giulio Weikmann, Gianmarco Perantoni, Lorenzo Bruzzone
https://arxiv.org/abs/2510.04916

A Semantics-Aware Hierarchical Self-Supervised Approach to Classification of Remote Sensing Images
Deep learning has become increasingly important in remote sensing image classification due to its ability to extract semantic information from complex data. Classification tasks often include predefined label hierarchies that represent the semantic relationships among classes. However, these hierarchies are frequently overlooked, and most approaches focus only on fine-grained classification schemes. In this paper, we present a novel Semantics-Aware Hierarchical Consensus (SAHC) method for learn…

Tens of thousands of demonstrators surged down 16th Street toward the White House on Saturday.
It was the city’s first major organized protest since Trump declared a state of emergency and unleashed federal troops onto its streets.
Banners waved and voices rose in unison at the
“We Are All D.C.” march,
a massive show of resistance led by a coalition that included
Free DC, defenders of local self-rule,
Democracy Forward,
and the American Civil Libert…

'We Are All DC ': Tens of Thousands March to White House | Common Dreams
D.C.rallies against Trump’s troops as more cities targeted

Harbaugh pins Chargers' slide on fixable mistakes https://www.espn.com/nfl/story/_/id/46504355/harbaugh-pins-chargers-slide-self-inflicted-wounds

caring how others perceive u is natural, important and has generally made things better for me, not worse. and ur all still doing it in ur niche online dgaf groups in a less deliberate and self-aware way that contributes to hurt

Self-consistent model of cosmic ray penetration into molecular clouds: Effect of energy losses
D. O. Chernyshov, A. V. Ivlev, V. A. Dogiel
https://arxiv.org/abs/2510.03073 https…

Self-consistent model of cosmic ray penetration into molecular clouds: Effect of energy losses
The theory of cosmic-ray (CR) penetration into dense molecular clouds developed recently for relativistic particles by Chernyshov et al. (2024) is extended to non-relativistic CRs. Interstellar CRs streaming into the clouds are able to resonantly excite MHD waves in diffuse cloud envelopes. This leads to the self-modulation, such that streaming particles are scattered at the self-generated waves. In contrast to relativistic CRs, transport of lower-energy particles in the envelopes is generally …

Self-Anchor: Large Language Model Reasoning via Step-by-step Attention Alignment
Hongxiang Zhang, Yuan Tian, Tianyi Zhang
https://arxiv.org/abs/2510.03223 https://

Self-Anchor: Large Language Model Reasoning via Step-by-step Attention Alignment
To solve complex reasoning tasks for Large Language Models (LLMs), prompting-based methods offer a lightweight alternative to fine-tuning and reinforcement learning. However, as reasoning chains extend, critical intermediate steps and the original prompt will be buried in the context, receiving insufficient attention and leading to errors. In this paper, we propose Self-Anchor, a novel pipeline that leverages the inherent structure of reasoning to steer LLM attention. Self-Anchor decomposes rea…

Stability and Self-Organized Patterns in Coupled Ecohydrological--Fire Dynamics: A Model of Vegetation--Rainfall--Bushfire Interactions
Serena Dipierro, Enrico Valdinoci
https://arxiv.org/abs/2509.04766

Stability and Self-Organized Patterns in Coupled Ecohydrological--Fire Dynamics: A Model of Vegetation--Rainfall--Bushfire Interactions
This paper investigates the conditions for the stability and emergence of patterns in a new three-component reaction-diffusion system. The system describes the coexistence and interaction of water reservoirs, vegetation, and bushfire activity in a given ecosystem. We perform a detailed stability analysis to determine the parameter space where an unstable homogeneous equilibrium becomes stable with respect to spatially nonuniform perturbations. We also use diffusion to generate traveling tra…

Inelastically Decoupling Dark Matter
Ronny Frumkin, Yonit Hochberg, Eric Kuflik, Binyamin Vilk
https://arxiv.org/abs/2508.04772 https://arxiv.org/pdf/2508.…

Inelastically Decoupling Dark Matter
We present a new dark matter candidate, the `inELastically DEcoupling Relic' (iELDER), which is a cold thermal relic whose abundance is determined by the freeze out of its inelastic scattering off of bath particles in the presence of $3\to2$ self-annihilations. The dark matter is predicted to be light, in the $O(\mathrm{MeV}-\mathrm{GeV})$ range, with significant self-annihilations and very weak inelastic couplings to ordinary matter. We demonstrate iELDER dark matter using a $Z_3$-symmetric to…

ADSEL: Adaptive dual self-expression learning for EEG feature selection via incomplete multi-dimensional emotional tagging
Tianze Yu, Junming Zhang, Wenjia Dong, Xueyuan Xu, Li Zhuo
https://arxiv.org/abs/2508.05229

ADSEL: Adaptive dual self-expression learning for EEG feature selection via incomplete multi-dimensional emotional tagging
EEG based multi-dimension emotion recognition has attracted substantial research interest in human computer interfaces. However, the high dimensionality of EEG features, coupled with limited sample sizes, frequently leads to classifier overfitting and high computational complexity. Feature selection constitutes a critical strategy for mitigating these challenges. Most existing EEG feature selection methods assume complete multi-dimensional emotion labels. In practice, open acquisition environme…

Amazon is testing an AI tool called Kindle Translate that automatically translates books into other languages, for authors that self-publish on the platform (Lawrence Bonk/Engadget)
https://www.engadget.com/ai/amazon-is-test

Amazon is testing an AI tool that automatically translates books into other languages
Amazon is introducing an AI tool that will automatically translate books into other languages. This should be useful for authors who self publish.

An Investigation into the Performance of Non-Contrastive Self-Supervised Learning Methods for Network Intrusion Detection
Hamed Fard, Tobias Schalau, Gerhard Wunder
https://arxiv.org/abs/2510.02349

An Investigation into the Performance of Non-Contrastive Self-Supervised Learning Methods for Network Intrusion Detection
Network intrusion detection, a well-explored cybersecurity field, has predominantly relied on supervised learning algorithms in the past two decades. However, their limitations in detecting only known anomalies prompt the exploration of alternative approaches. Motivated by the success of self-supervised learning in computer vision, there is a rising interest in adapting this paradigm for network intrusion detection. While prior research mainly delved into contrastive self-supervised methods, th…

Hausdorff dimension of the Wedding cake type surfaces
Bal\'azs B\'ar\'any, Manuj Verma
https://arxiv.org/abs/2510.04613 https://arxiv.org/pdf/2…

Hausdorff dimension of the Wedding cake type surfaces
In this paper, we study the Hausdorff dimension of fractal interpolation surfaces (FISs) over a triangular domain. These FISs are known as `wedding cake surfaces'. These surfaces are the attractor of some deterministic self-affine iterated function systems (IFS) on $\mathbb{R}^3$ generated by a fractal interpolation algorithm. Due to the recent seminal result of Rapaport (Adv. Math. 449 (2024) 109734), the dimension theory of self-affine IFS on $\mathbb{R}^3$ is known whenever the IFS is strong…

AutoMaAS: Self-Evolving Multi-Agent Architecture Search for Large Language Models
Bo Ma, Hang Li, ZeHua Hu, XiaoFan Gui, LuYao Liu, Simon Liu
https://arxiv.org/abs/2510.02669 ht…

AutoMaAS: Self-Evolving Multi-Agent Architecture Search for Large Language Models
Multi-agent systems powered by large language models have demonstrated remarkable capabilities across diverse domains, yet existing automated design approaches seek monolithic solutions that fail to adapt resource allocation based on query complexity and domain requirements. This paper introduces AutoMaAS, a self-evolving multi-agent architecture search framework that leverages neural architecture search principles to automatically discover optimal agent configurations through dynamic operator …

The Path of Self-Evolving Large Language Models: Achieving Data-Efficient Learning via Intrinsic Feedback
Hangfan Zhang, Siyuan Xu, Zhimeng Guo, Huaisheng Zhu, Shicheng Liu, Xinrun Wang, Qiaosheng Zhang, Yang Chen, Peng Ye, Lei Bai, Shuyue Hu
https://arxiv.org/abs/2510.02752

The Path of Self-Evolving Large Language Models: Achieving Data-Efficient Learning via Intrinsic Feedback
Reinforcement learning (RL) has demonstrated potential in enhancing the reasoning capabilities of large language models (LLMs), but such training typically demands substantial efforts in creating and annotating data. In this work, we explore improving LLMs through RL with minimal data. Our approach alternates between the LLM proposing a task and then attempting to solve it. To minimize data dependency, we introduce two novel mechanisms grounded in self-awareness: (1) self-aware difficulty predi…

Conversational AI increases political knowledge as effectively as self-directed internet search
Lennart Luettgau, Hannah Rose Kirk, Kobi Hackenburg, Jessica Bergs, Henry Davidson, Henry Ogden, Divya Siddarth, Saffron Huang, Christopher Summerfield
https://arxiv.org/abs/2509.05219

Conversational AI increases political knowledge as effectively as self-directed internet search
Conversational AI systems are increasingly being used in place of traditional search engines to help users complete information-seeking tasks. This has raised concerns in the political domain, where biased or hallucinated outputs could misinform voters or distort public opinion. However, in spite of these concerns, the extent to which conversational AI is used for political information-seeking, as well the potential impact of this use on users' political knowledge, remains uncertain. Here, we a…

Self-induced buckling in hollow microgels
Leah Rank, Emanuela Zaccarelli
https://arxiv.org/abs/2510.04247 https://arxiv.org/pdf/2510.04247

Self-induced buckling in hollow microgels
Hollow microgels are elastic polymer shells easily realisable in experiments. Recent works have shown the emergence of buckling events in single hollow microgels under the effect of an added osmotic pressure. Here, we perform large-scale simulations to show that these microgels at high enough packing fractions undergo spontaneous symmetry-breaking deformations ranging from single large dents to multiple indentations, even in the absence of any externally applied stress. This buckling phenomenol…

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[4/8]:
- Self-Correction Bench: Uncovering and Addressing the Self-Correction Blind Spot in Large Language...
Ken Tsui

Reflection Before Action: Designing a Framework for Quantifying Thought Patterns for Increased Self-awareness in Personal Decision Making
Morita Tarvirdians, Senthil Chandrasegaran, Hayley Hung, Catholijn M. Jonker, Catharine Oertel
https://arxiv.org/abs/2510.04364

Reflection Before Action: Designing a Framework for Quantifying Thought Patterns for Increased Self-awareness in Personal Decision Making
When making significant life decisions, people increasingly turn to conversational AI tools, such as large language models (LLMs). However, LLMs often steer users toward solutions, limiting metacognitive awareness of their own decision-making. In this paper, we shift the focus in decision support from solution-orientation to reflective activity, coining the term pre-decision reflection (PDR). We introduce PROBE, the first framework that assesses pre-decision reflections along two dimensions: br…

The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs
Pengrui Han, Rafal Kocielnik, Peiyang Song, Ramit Debnath, Dean Mobbs, Anima Anandkumar, R. Michael Alvarez
https://arxiv.org/abs/2509.03730

The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs
Personality traits have long been studied as predictors of human behavior.Recent advances in Large Language Models (LLMs) suggest similar patterns may emerge in artificial systems, with advanced LLMs displaying consistent behavioral tendencies resembling human traits like agreeableness and self-regulation. Understanding these patterns is crucial, yet prior work primarily relied on simplified self-reports and heuristic prompting, with little behavioral validation. In this study, we systematicall…

Monday Night Football NFL player props: Self-learning AI likes Patrick Mahomes to go Over 245.5 passing yards

https://www.cbssports.com/nfl/news/monday-night-football-chiefs…

Self-adaptive Dataset Construction for Real-World Multimodal Safety Scenarios
Jingen Qu, Lijun Li, Bo Zhang, Yichen Yan, Jing Shao
https://arxiv.org/abs/2509.04403 https://

Self-adaptive Dataset Construction for Real-World Multimodal Safety Scenarios
Multimodal large language models (MLLMs) are rapidly evolving, presenting increasingly complex safety challenges. However, current dataset construction methods, which are risk-oriented, fail to cover the growing complexity of real-world multimodal safety scenarios (RMS). And due to the lack of a unified evaluation metric, their overall effectiveness remains unproven. This paper introduces a novel image-oriented self-adaptive dataset construction method for RMS, which starts with images and end …

SPFT-SQL: Enhancing Large Language Model for Text-to-SQL Parsing by Self-Play Fine-Tuning
Yuhao Zhang, Shaoming Duan, Jinhang Su, Chuanyi Liu, Peiyi Han
https://arxiv.org/abs/2509.03937

SPFT-SQL: Enhancing Large Language Model for Text-to-SQL Parsing by Self-Play Fine-Tuning
Despite the significant advancements of self-play fine-tuning (SPIN), which can transform a weak large language model (LLM) into a strong one through competitive interactions between models of varying capabilities, it still faces challenges in the Text-to-SQL task. SPIN does not generate new information, and the large number of correct SQL queries produced by the opponent model during self-play reduces the main model's ability to generate accurate SQL queries. To address this challenge, we prop…

Breaking the Mirror: Activation-Based Mitigation of Self-Preference in LLM Evaluators
Dani Roytburg, Matthew Bozoukov, Matthew Nguyen, Jou Barzdukas, Simon Fu, Narmeen Oozeer
https://arxiv.org/abs/2509.03647

Breaking the Mirror: Activation-Based Mitigation of Self-Preference in LLM Evaluators
Large language models (LLMs) increasingly serve as automated evaluators, yet they suffer from "self-preference bias": a tendency to favor their own outputs over those of other models. This bias undermines fairness and reliability in evaluation pipelines, particularly for tasks like preference tuning and model routing. We investigate whether lightweight steering vectors can mitigate this problem at inference time without retraining. We introduce a curated dataset that distinguishes self-preferen…

RESTRAIN: From Spurious Votes to Signals -- Self-Driven RL with Self-Penalization
Zhaoning Yu, Will Su, Leitian Tao, Haozhu Wang, Aashu Singh, Hanchao Yu, Jianyu Wang, Hongyang Gao, Weizhe Yuan, Jason Weston, Ping Yu, Jing Xu
https://arxiv.org/abs/2510.02172

RESTRAIN: From Spurious Votes to Signals -- Self-Driven RL with Self-Penalization
Reinforcement learning with human-annotated data has boosted chain-of-thought reasoning in large reasoning models, but these gains come at high costs in labeled data while faltering on harder tasks. A natural next step is experience-driven learning, where models improve without curated labels by adapting to unlabeled data. We introduce RESTRAIN (REinforcement learning with Self-restraint), a self-penalizing RL framework that converts the absence of gold labels into a useful learning signal. Ins…

SelfJudge: Faster Speculative Decoding via Self-Supervised Judge Verification
Kanghoon Yoon, Minsub Kim, Sungjae Lee, Joonhyung Lee, Sunghyeon Woo, Yeonjun In, Se Jung Kwon, Chanyoung Park, Dongsoo Lee
https://arxiv.org/abs/2510.02329

SelfJudge: Faster Speculative Decoding via Self-Supervised Judge Verification
Speculative decoding accelerates LLM inference by verifying candidate tokens from a draft model against a larger target model. Recent judge decoding boosts this process by relaxing verification criteria by accepting draft tokens that may exhibit minor discrepancies from target model output, but existing methods are restricted by their reliance on human annotations or tasks with verifiable ground truths, limiting generalizability across diverse NLP tasks. We propose SelfJudge, which trains judge…