Tootfinder

Amazon plans to let authors offer their DRM-free ebooks in the EPUB and PDF formats through Kindle Direct Publishing, starting January 20, 2026 (Sarah Perez/TechCrunch)
https://techcrunch.com/2025/12/10/amazon-chan…

Amazon changes how copyright protection is applied to Kindle Direct's self-published ebooks | TechCrunch
Amazon says its Kindle Direct DRM-free titles will be available as PDFs and EPUB files going forward.

Amazon plans to let authors offer their DRM-free ebooks in the EPUB and PDF formats through Kindle Direct Publishing, starting January 20, 2026 (Sarah Perez/TechCrunch)
https://techcrunch.com/2025/12/10/amazon-chan…

Amazon changes how copyright protection is applied to Kindle Direct's self-published ebooks | TechCrunch
Amazon says its Kindle Direct DRM-free titles will be available as PDFs and EPUB files going forward.

Massive DHS "Self-Deportation" Contract Challenged as Secretive and "Unlawful" (Mother Jones)
https://www.motherjones.com/politics/2025/10/dhs-ice-self-deportation-contract-salus-worldwide-csi-aviation/
http://www.memeorandum.com/251010/p104#a251010p104

Exclusive: Dems Fire Back at Trump’s ‘Freaky’ Kid Self-Deportation Plan
https://www.thebulwark.com/p/exclusive-dems-congressional-hispanic-caucus-fire-back-at-trump-freaky-friday-child-minor-self-deportation

Aligning Large Language Models via Fully Self-Synthetic Data
Shangjian Yin, Zhepei Wei, Xinyu Zhu, Wei-Lin Chen, Yu Meng
https://arxiv.org/abs/2510.06652 https://

Aligning Large Language Models via Fully Self-Synthetic Data
Traditional reinforcement learning from human feedback (RLHF) for large language models (LLMs) relies on expensive human-annotated datasets, while Reinforcement Learning from AI Feedback (RLAIF) also incurs significant costs, requiring the collection of diverse prompts and corresponding responses, often necessitating external reward models or proprietary models like GPT-4 to annotate preference pairs. In this work, we introduce Self-Alignment Optimization (SAO), a fully self-synthetic framework…

Contrastive Self-Supervised Learning at the Edge: An Energy Perspective
Fernanda Fam\'a, Roberto Pereira, Charalampos Kalalas, Paolo Dini, Lorena Qendro, Fahim Kawsar, Mohammad Malekzadeh
https://arxiv.org/abs/2510.08374

Contrastive Self-Supervised Learning at the Edge: An Energy Perspective
While contrastive learning (CL) shows considerable promise in self-supervised representation learning, its deployment on resource-constrained devices remains largely underexplored. The substantial computational demands required for training conventional CL frameworks pose a set of challenges, particularly in terms of energy consumption, data availability, and memory usage. We conduct an evaluation of four widely used CL frameworks: SimCLR, MoCo, SimSiam, and Barlow Twins. We focus on the practi…

Self-supervised Physics-guided Model with Implicit Representation Regularization for Fast MRI Reconstruction
Jingran Xu, Yuanyuan Liu, Yanjie Zhu
https://arxiv.org/abs/2510.06611

Self-supervised Physics-guided Model with Implicit Representation Regularization for Fast MRI Reconstruction
Magnetic Resonance Imaging (MRI) is a vital clinical diagnostic tool, yet its widespread application is limited by prolonged scan times. Fast MRI reconstruction techniques effectively reduce acquisition duration by reconstructing high-fidelity MR images from undersampled k-space data. In recent years, deep learning-based methods have demonstrated remarkable progress in this field, with self-supervised and unsupervised learning approaches proving particularly valuable in scenarios where fully sa…

Today my daughter's preschool is holding a farewell assembly for one of her classmates
whose mother has no choice but to self deport.
The school is hoping it will be joyful in tone, so we might make this less upsetting for this 3 year old.
There's just no words for the uselessness of this cruelty.
ht…

Maggie Tokuda-Hall (@maggietokudahall.bsky.social)
Today my daughter's preschool is holding a farewell assembly for one of her classmates whose mother has no choice but to self deport. The school is hoping it will be joyful in tone, so we might make this less upsetting for this 3 year old. There's just no words for the uselessness of this cruelty.

🇺🇦 #NowPlaying on KEXP's #VarietyMix
Yalla Miku:
🎵 Maximum Self-Care
#YallaMiku
https://yallamiku.bandcamp.com/track/maximum-self-care
https://open.spotify.com/track/1a0OMv1hKVWqRF8IMzlXxK

Gaussian Equivalence for Self-Attention: Asymptotic Spectral Analysis of Attention Matrix
Tomohiro Hayase, Beno\^it Collins, Ryo Karakida
https://arxiv.org/abs/2510.06685 https:…

Gaussian Equivalence for Self-Attention: Asymptotic Spectral Analysis of Attention Matrix
Self-attention layers have become fundamental building blocks of modern deep neural networks, yet their theoretical understanding remains limited, particularly from the perspective of random matrix theory. In this work, we provide a rigorous analysis of the singular value spectrum of the attention matrix and establish the first Gaussian equivalence result for attention. In a natural regime where the inverse temperature remains of constant order, we show that the singular value distribution of t…

RAISE: A self-driving laboratory for interfacial property formulation discovery
Mohammad Nazeri (Institute of Biomedical Engineering, University of Toronto, Canada), Sheldon Mei (Department of Chemical Engineering and Applied Chemistry, University of Toronto, Canada), Jeffrey Watchorn (Acceleration Consortium, University of Toronto, Canada), Alex Zhang (Department of Mechanical and Industrial Engineering, University of Toronto, Canada), Erin Ng (Department of Chemical Engineering and A…

RAISE: A self-driving laboratory for interfacial property formulation discovery
Surface wettability is a critical design parameter for biomedical devices, coatings, and textiles. Contact angle measurements quantify liquid-surface interactions, which depend strongly on liquid formulation. Herein, we present the Robotic Autonomous Imaging Surface Evaluator (RAISE), a closed-loop, self-driving laboratory that is capable of linking liquid formulation optimization with surface wettability assessment. RAISE comprises a full experimental orchestrator with the ability of mixing li…

🦾 Bird-like robot with novel wing system achieves self-takeoff and low-speed flight
#robots

Bird-like robot with novel wing system achieves self-takeoff and low-speed flight
In 2021, a group of scientists from China engineered the RoboFalcon—a bird-inspired flapping-wing robot with a newly engineered mechanism made to drive bat-style morphing wings capable of flight. While this bio-inspired robot performed well at a cruising speed, it was not capable of flying at lower speeds or achieving takeoff without assistance.

A Systematic Evaluation of Self-Supervised Learning for Label-Efficient Sleep Staging with Wearable EEG
Emilio Estevan, Mar\'ia Sierra-Torralba, Eduardo L\'opez-Larraz, Luis Montesano
https://arxiv.org/abs/2510.07960

A Systematic Evaluation of Self-Supervised Learning for Label-Efficient Sleep Staging with Wearable EEG
Wearable EEG devices have emerged as a promising alternative to polysomnography (PSG). As affordable and scalable solutions, their widespread adoption results in the collection of massive volumes of unlabeled data that cannot be analyzed by clinicians at scale. Meanwhile, the recent success of deep learning for sleep scoring has relied on large annotated datasets. Self-supervised learning (SSL) offers an opportunity to bridge this gap, leveraging unlabeled signals to address label scarcity and …

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,…

Self-learning AI releases NFL picks, score predictions every Week 15 game

https://www.cbssports.com/nfl/news/nfl-week-15-picks-ai-score-predictions/

This new Linux platform will let you update your next car at home - as soon as 2027
Toyota, Honda, and Mazda are building a new open-source car platform that runs everything from entertainment to navigation - and could even power self-driving.
https://www.

This new Linux platform will let you update your next car at home - as soon as 2027
Toyota, Honda, and Mazda are building a new open-source car platform that runs everything from entertainment to navigation - and could even power self-driving.

Self-replication and Computational Universality
Jordan Cotler, Cl\'ement Hongler, Barbora Hudcov\'a
https://arxiv.org/abs/2510.08342 https://arxiv.…

Techno-economic analysis of self-sustainable thermophotovoltaic systems for grid-scale energy generation
Jihun Lim, Sungwon Lee
https://arxiv.org/abs/2510.07338 https://

Techno-economic analysis of self-sustainable thermophotovoltaic systems for grid-scale energy generation
To facilitate the widespread adoption of renewable energy, dispatchable, zero-emission power sources are essential for grid stability. This work performs a comprehensive techno-economic analysis of a self-sustainable thermophotovoltaic (TPV) system, an architecture that integrates solar charging to function as a standalone power generation asset. Using theory-based models for air-bridge InGaAs and Si diode cells, our analysis reveals that while the system is not currently competitive from a pur…

Thermal one-loop self-energy correction for hydrogen-like systems: relativistic approach
M. Reiter, D. Solovyev, A. Bobylev, D. Glazov, T. Zalialiutdinov
https://arxiv.org/abs/2512.06828 https://arxiv.org/pdf/2512.06828 https://arxiv.org/html/2512.06828
arXiv:2512.06828v1 Announce Type: new
Abstract: Within a fully relativistic framework, the one-loop self-energy correction for a bound electron is derived and extended to incorporate the effects of external thermal radiation. In a series of previous works, it was shown that in quantum electrodynamics at finite temperature (QED), the description of effects caused by blackbody radiation can be reduced to using the thermal part of the photon propagator. As a consequence of the non-relativistic approximation in the calculation of the thermal one-loop self-energy correction, well-known quantum-mechanical (QM) phenomena emerge at successive orders: the Stark effect arises at leading order in $\alpha Z$, the Zeeman effect appears in the next-to-leading non-relativistic correction, accompanied by diamagnetic contributions and their relativistic refinements, among other perturbative corrections. The fully relativistic approach used in this work for calculating the SE contribution allows for accurate calculations of the thermal shift of atomic levels, in which all these effects are automatically taken into account. The hydrogen atom serves as the basis for testing a fully relativistic approach to such calculations. Additionally, an analysis is presented of the behavior of the thermal shift caused by the thermal one-loop correction to the self-energy of a bound electron for hydrogen-like ions with an arbitrary nuclear charge $Z$. The significance of these calculations lies in their relevance to contemporary high-precision experiments, where thermal radiation constitutes one of the major contributions to the overall uncertainty budget.
toXiv_bot_toot

Trump, the Self-Styled "President of PEACE" Abroad, Makes War at Home (Susan B. Glasser/New Yorker)
https://www.newyorker.com/news/letter-from-trumps-washington/trump-the-self-styled-president-of-peace-abroad-makes-war-at-home
http://www.memeorandum.com/251009/p127#a251009p127

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…

Diffusion Codes: Self-Correction from Small(er)-Set Expansion with Tunable Non-locality
Adithya Sriram, Vedika Khemani, Benedikt Placke
https://arxiv.org/abs/2510.07179 https://…

Diffusion Codes: Self-Correction from Small(er)-Set Expansion with Tunable Non-locality
Optimal constructions of classical LDPC codes can be obtained by choosing the Tanner graph uniformly at random among biregular graphs. We introduce a class of codes that we call ``diffusion codes'', defined by placing each edge connecting bits and checks on some graph, and acting on that graph with a random SWAP network. By tuning the depth of the SWAP network, we can tune a tradeoff between the amount of randomness -- and hence the optimality of code parameters -- and locality with respect to …

TDoA-Based Self-Supervised Channel Charting with NLoS Mitigation
Mohsen Ahadi, Omid Esrafilian, Florian Kaltenberger, Adeel Malik
https://arxiv.org/abs/2510.08001 https://

TDoA-Based Self-Supervised Channel Charting with NLoS Mitigation
Channel Charting (CC) has emerged as a promising framework for data-driven radio localization, yet existing approaches often struggle to scale globally and to handle the distortions introduced by non-line-of-sight (NLoS) conditions. In this work, we propose a novel CC method that leverages Channel Impulse Response (CIR) data enriched with practical features such as Time Difference of Arrival (TDoA) and Transmission Reception Point (TRP) locations, enabling a self-supervised localization functio…

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_…

Interleaved Learning and Exploration: A Self-Adaptive Fuzz Testing Framework for MLIR
Zeyu Sun, Jingjing Liang, Weiyi Wang, Chenyao Suo, Junjie Chen, Fanjiang Xu
https://arxiv.org/abs/2510.07815

Interleaved Learning and Exploration: A Self-Adaptive Fuzz Testing Framework for MLIR
MLIR (Multi-Level Intermediate Representation) has rapidly become a foundational technology for modern compiler frameworks, enabling extensibility across diverse domains. However, ensuring the correctness and robustness of MLIR itself remains challenging. Existing fuzzing approaches-based on manually crafted templates or rule-based mutations-struggle to generate sufficiently diverse and semantically valid test cases, making it difficult to expose subtle or deep-seated bugs within MLIR's complex…

Finite element models for Self-Deployable Miura-folded origami
Suraj Singh Gehlot, Siddhanth Gautam, Sanhita Das
https://arxiv.org/abs/2510.08029 https://a…

Finite element models for Self-Deployable Miura-folded origami
Origami-inspired self-deployable structures offer lightweight, compact, and autonomous deployment capabilities, making them highly attractive for aerospace and defence applications, such as solar panels, antennas, and reflector systems. This paper presents finite element frameworks for simulating Miura-origami units in ABAQUS, focusing on two deployment mechanisms: elastic strain energy release and thermally activated shape-memory polymers (SMPs). Validation against experimental data for elasti…

Human-Centered Development of Indicators for Self-Service Learning Analytics: A Transparency through Exploration Approach
Shoeb Joarder, Mohamed Amine Chatti
https://arxiv.org/abs/2510.08395

Human-Centered Development of Indicators for Self-Service Learning Analytics: A Transparency through Exploration Approach
The aim of learning analytics is to turn educational data into insights, decisions, and actions to improve learning and teaching. The reasoning of the provided insights, decisions, and actions is often not transparent to the end-user, and this can lead to trust and acceptance issues when interventions, feedback, and recommendations fail. In this paper, we shed light on achieving transparent learning analytics by following a transparency through exploration approach. To this end, we present the …

cora: CORA citations (1998)
Citations among papers indexed by CORA, from 1998, an early computer science research paper search engine. 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. The dates of these snapshots are uncertain.
This network has 23166 nodes and 91500 edges.
Tags: Informational, Citation, Unweighted

Distributed Resource Selection for Self-Organising Cloud-Edge Systems
Quentin Renau, Amjad Ullah, Emma Hart
https://arxiv.org/abs/2510.08228 https://arxiv.…

Distributed Resource Selection for Self-Organising Cloud-Edge Systems
This paper presents a distributed resource selection mechanism for diverse cloud-edge environments, enabling dynamic and context-aware allocation of resources to meet the demands of complex distributed applications. By distributing the decision-making process, our approach ensures efficiency, scalability, and resilience in highly dynamic cloud-edge environments where centralised coordination becomes a bottleneck. The proposed mechanism aims to function as a core component of a broader, distribu…

Self-OH: Digital Naïves
#DigitalNatives

Auto-Stega: An Agent-Driven System for Lifelong Strategy Evolution in LLM-Based Text Steganography
Jiuan Zhou, Yu Cheng, Yuan Xie, Zhaoxia Yin
https://arxiv.org/abs/2510.06565 h…

Auto-Stega: An Agent-Driven System for Lifelong Strategy Evolution in LLM-Based Text Steganography
With the rapid progress of LLMs, high quality generative text has become widely available as a cover for text steganography. However, prevailing methods rely on hand-crafted or pre-specified strategies and struggle to balance efficiency, imperceptibility, and security, particularly at high embedding rates. Accordingly, we propose Auto-Stega, an agent-driven self-evolving framework that is the first to realize self-evolving steganographic strategies by automatically discovering, composing, and a…

I made pizza

Why learn good time management, when you can achieve the same with abject self-exploitation? #academicChatter

SID: Multi-LLM Debate Driven by Self Signals
Xuhang Chen, Zhifan Song, Deyi Ji, Shuo Gao, Lanyun Zhu
https://arxiv.org/abs/2510.06843 https://arxiv.org/pdf…

SID: Multi-LLM Debate Driven by Self Signals
Large Language Models (LLMs) have exhibited impressive capabilities across diverse application domains. Recent work has explored Multi-LLM Agent Debate (MAD) as a way to enhance performance by enabling multiple LLMs to discuss and refine responses iteratively. Nevertheless, existing MAD methods predominantly focus on utilizing external structures, such as debate graphs, using LLM-as-a-Judge, while neglecting the application of self signals, such as token logits and attention, that arise during …

When vacuum breaks: a self-consistency test for astrophysical environments in extreme mass ratio inspirals
Lorenzo Copparoni, Rohit S. Chandramouli, Enrico Barausse
https://arxiv.org/abs/2510.06948

When vacuum breaks: a self-consistency test for astrophysical environments in extreme mass ratio inspirals
Gravitational-wave signals are typically interpreted under the vacuum hypothesis, i.e. assuming negligible influence from the astrophysical environment. This assumption is expected to break down for low-frequency sources such as extreme mass ratio inspirals (EMRIs), which are prime targets for the Laser Interferometer Space Antenna (LISA) and are expected to form, at least in part, in dense environments such as Active Galactic Nuclei or dark-matter spikes/cores. Modeling environmental effects p…

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 …

I hold that genuine freedom can only be realized through the direct self-management of labor and the collective organization of social life by those engaged in it. No political vanguard, governmental apparatus, or capitalist hierarchy can provide emancipation, it must emerge from the autonomous initiative of workers acting in solidarity, constructing federations of production and community based on voluntary association and mutual responsibility.
For me, anarcho-syndicalism represents …

Nonparametric Estimation of Self- and Cross-Impact
Natascha Hey, Eyal Neuman, Sturmius Tuschmann
https://arxiv.org/abs/2510.06879 https://arxiv.org/pdf/251…

Nonparametric Estimation of Self- and Cross-Impact
We introduce an offline nonparametric estimator for concave multi-asset propagator models based on a dataset of correlated price trajectories and metaorders. Compared to parametric models, our framework avoids parameter explosion in the multi-asset case and yields confidence bounds for the estimator. We implement the estimator using both proprietary metaorder data from Capital Fund Management (CFM) and publicly available S&P order flow data, where we augment the former dataset using a metaorder…

a world you can fully understand and hold in your head and hand. being the snowman in his globe rather than on yours. where's the water come from? the rain, these tanks. where's the power generated? those solar panels and batteries. you know the limits and work with them. self-sufficient. a fantasy irl, but one of the most universal magic cores you can imbue a fantasy with. no man is an island, no man isn't offputtingly hard to grasp.

Just finished "The Deep Dark" by Molly Knox Ostertag. An absolutely excellent graphic novel about monsters, childhood secrets, and how self-love refracts through romance.
I've liked other stuff by Ostertag, but this is definitely my favorite of hers so far.
#AmReading #ReadingNow

Mephisto: Self-Improving Large Language Model-Based Agents for Automated Interpretation of Multi-band Galaxy Observations
Zechang Sun, Yuan-Sen Ting, Yaobo Liang, Nan Duan, Song Huang, Zheng Cai
https://arxiv.org/abs/2510.08354

Mephisto: Self-Improving Large Language Model-Based Agents for Automated Interpretation of Multi-band Galaxy Observations
Astronomical research has long relied on human expertise to interpret complex data and formulate scientific hypotheses. In this study, we introduce Mephisto -- a multi-agent collaboration framework powered by large language models (LLMs) that emulates human-like reasoning for analyzing multi-band galaxy observations. Mephisto interfaces with the CIGALE codebase (a library of spectral energy distribution, SED, models) to iteratively refine physical models against observational data. It conducts …

For hosting our internal source code repositories, we're using #gitea. There are a bunch of other options and all of them seem to mimic github's look and feel. Gitea was the one I found out about first some years ago and it stuck. It has an issue tracker and works well for doing pull requests and reviewing them online.
There's a commercial cloud hosting offer and an enterprise opt…

Diffusion-Guided Renormalization of Neural Systems via Tensor Networks
Nathan X. Kodama
https://arxiv.org/abs/2510.06361 https://arxiv.org/pdf/2510.06361…

Diffusion-Guided Renormalization of Neural Systems via Tensor Networks
Far from equilibrium, neural systems self-organize across multiple scales. Exploiting multiscale self-organization in neuroscience and artificial intelligence requires a computational framework for modeling the effective non-equilibrium dynamics of stochastic neural trajectories. Non-equilibrium thermodynamics and representational geometry offer theoretical foundations, but we need scalable data-driven techniques for modeling collective properties of high-dimensional neural networks from partia…

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…

@…
Hey, thanks for your interest.
I don't cross-post to any of those things.
How do I do it?
Self-restraint 😃
@…

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-…

It’s #MondayRandom10 again, and here are 10 random tracks from my playlist (currently of 2068 tracks):
1. White Zombie—“Grindhouse (A Go-go)”
2. The Beatles—“Helter Skelter (2018 Mix)”
3. Cop Shoot Cop—“Room 429”
4. AG Club—“Adam Sandler”
5. Alpine Universe—“The Empire of Winds”
6. Bryce Fox—“Golden Boy”
7. Mindless Self Indulgence—“Tom Sawyer (Remastered)”

Selection, Reflection and Self-Refinement: Revisit Reasoning Tasks via a Causal Lens
Yunlong Deng, Boyang Sun, Yan Li, Lingjing Kong, Zeyu Tang, Kun Zhang, Guangyi Chen
https://arxiv.org/abs/2510.08222

Selection, Reflection and Self-Refinement: Revisit Reasoning Tasks via a Causal Lens
Due to their inherent complexity, reasoning tasks have long been regarded as rigorous benchmarks for assessing the capabilities of machine learning models, especially large language models (LLMs). Although humans can solve these tasks with ease, existing models, even after extensive pre-training and post-training at scale, still fail to perform reasoning reliably. In this paper, we revisit reasoning tasks from a causal perspective, seeking to understand their behavior in latent space and to off…

En Nombre del Progreso (In the Name of Progress)
2017 by Alfonso "Piloto" Nieves Ruiz, active in the United States, born Querétaro, Mexico. at Intuit Art Museum, West Town, #Chicago

Steelers vs. Chargers NFL player props: Self-learning AI backs Justin Herbert Over 252.5 passing on SNF

https://www.cbssports.com/nfl/news/steelers-chargers-nfl-pla…

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.

Neurosurgeon analyses Waymo’s data on 100M miles of driverless travel, concludes that it’s dramatically, qualitatively safer (at least the way that Waymo does it). Says if this were a clinical trial they’d stop it because giving placebos would be unethical.

Opinion | The Medical Case for Self-Driving Cars
Compared to human drivers, Waymo cars were involved in 91 percent fewer crashes that resulted in serious injuries.

Go Fuck Yourself
but as a self-care recommendation

Resolution scaling governs DINOv3 transfer performance in chest radiograph classification
Soroosh Tayebi Arasteh, Mina Shaigan, Christiane Kuhl, Jakob Nikolas Kather, Sven Nebelung, Daniel Truhn
https://arxiv.org/abs/2510.07191

Resolution scaling governs DINOv3 transfer performance in chest radiograph classification
Self-supervised learning (SSL) has advanced visual representation learning, but its value in chest radiography, a high-volume imaging modality with fine-grained findings, remains unclear. Meta's DINOv3 extends earlier SSL models through Gram-anchored self-distillation. Whether these design choices improve transfer learning for chest radiography has not been systematically tested. We benchmarked DINOv3 against DINOv2 and ImageNet initialization across seven datasets (n>814,000). Two representati…

🔌 #Firecrawl integration for web scraping and search: standard API key setup for contributors, partner integration option for production deployments with per-user API key management, automatic key provisioning on signup, self-healing system with fallback for invalid keys

Mercedes partners with Chinese software developer Momenta to deploy Level 4 self-driving cars for Lumo Mobility in Abu Dhabi, its first foray into robotaxis (William Wilkes/Bloomberg)
https://www.bloomberg.com/news/articles/20

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…

"I Don't Want to Be Here Anymore": They Tried to Self-Deport, Then Got Stranded in Trump's America (ProPublica)
https://www.propublica.org/article/trump-self-deportation-cbp-home-app
http://www.memeorandum.com/251010/p32#a251010p32

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…

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…

Simultaneous optimization of assembly time and yield in programmable self-assembly
Maximilian C. H\"ubl, Carl P. Goodrich
https://arxiv.org/abs/2510.07876 https://

Simultaneous optimization of assembly time and yield in programmable self-assembly
Rational design strategies for self-assembly require a detailed understanding of both the equilibrium state and the assembly kinetics. While the former is starting to be well understood, the latter remains a major theoretical challenge, especially in programmable systems and the so-called semiaddressable regime, where binding is often nondeterministic and the formation of off-target structures negatively influences the assembly. Here, we show that it is possible to simultaneously sculpt the ass…

"If you're worried about Tesla Full Self Driving killing your kids, you don't have enough kids."
| Musk University;
Elon Musk;
All things considered, he’s just a really stupid guy with really stupid beliefs
https://bsky.app/profile/junlper.beer/post…

onion person (@junlper.beer)
all things considered, he’s just a really stupid guy with really stupid beliefs [contains quote post or other embedded content]

🍃 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.

TGPR: Tree-Guided Policy Refinement for Robust Self-Debugging of LLMs
Daria Ozerova, Ekaterina Trofimova
https://arxiv.org/abs/2510.06878 https://arxiv.org…

TGPR: Tree-Guided Policy Refinement for Robust Self-Debugging of LLMs
Iterative refinement has been a promising paradigm to enable large language models (LLMs) to resolve difficult reasoning and problem-solving tasks. One of the key challenges, however, is how to effectively search through the enormous search space of possible refinements. Existing methods typically fall back on predefined heuristics, which are troubled by the exploration-exploitation dilemma and cannot adapt based on past refinement outcomes. We introduce Tree-Guided Policy Refinement (TGPR), a …

Neologism Learning for Controllability and Self-Verbalization
John Hewitt, Oyvind Tafjord, Robert Geirhos, Been Kim
https://arxiv.org/abs/2510.08506 https://

Neologism Learning for Controllability and Self-Verbalization
Humans invent new words when there is a rising demand for a new useful concept (e.g., doomscrolling). We explore and validate a similar idea in our communication with LLMs: introducing new words to better understand and control the models, expanding on the recently introduced neologism learning. This method introduces a new word by adding a new word embedding and training with examples that exhibit the concept with no other changes in model parameters. We show that adding a new word allows for …

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…

Sources: Beijing is set to limit access to Nvidia's H200 chips despite President Trump allowing their export to China, in its push for chip self-sufficiency (Zijing Wu/Financial Times)
https://www.ft.com/content/c4e81a67-cd5b-48b4-9749-92ecf116313d

https://foone.org/ponies/zohran/

Grouped Differential Attention
Junghwan Lim, Sungmin Lee, Dongseok Kim, Wai Ting Cheung, Beomgyu Kim, Taehwan Kim, Haesol Lee, Junhyeok Lee, Dongpin Oh, Eunhwan Park
https://arxiv.org/abs/2510.06949

Grouped Differential Attention
The self-attention mechanism, while foundational to modern Transformer architectures, suffers from a critical inefficiency: it frequently allocates substantial attention to redundant or noisy context. Differential Attention addressed this by using subtractive attention maps for signal and noise, but its required balanced head allocation imposes rigid constraints on representational flexibility and scalability. To overcome this, we propose Grouped Differential Attention (GDA), a novel approach…

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…

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…

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…

CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards
Xiangyuan Xue, Yifan Zhou, Guibin Zhang, Zaibin Zhang, Yijiang Li, Chen Zhang, Zhenfei Yin, Philip Torr, Wanli Ouyang, Lei Bai
https://arxiv.org/abs/2510.08529

CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards
Self-evolution is a central research topic in enabling large language model (LLM)-based agents to continually improve their capabilities after pretraining. Recent research has witnessed a transition from reinforcement learning (RL)-free to RL-based methods. Current RL-based methods either rely on dense external reward signals or extract intrinsic reward signals from LLMs themselves. However, these approaches diverge from the self-evolution mechanisms observed in human intelligence, where indivi…

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 …

As US schools adopt AI, a look at the growing use of AI-powered monitoring tools like GoGuardian to scan students' chatbot conversations for signs of self-harm (Janne Knodler/Bloomberg)
https://www.bloomberg.com/news/articles/20

AI Chatbot Surveillance Tools Are Quietly Watching Kids In Class
As US educators embrace AI in the classroom, firms are selling software to flag mentions of self-harm, raising concerns over privacy and control.

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…

🔋 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.

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…

How Jared Kushner, a Self-Described 'Deal Guy,' Helped Broker a Gaza Breakthrough (New York Times)
https://www.nytimes.com/2025/10/09/us/politics/jared-kushner-gaza-deal.html
http://www.memeorandum.com/251009/p125#a251009p125

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…

Introspection in Learned Semantic Scene Graph Localisation
Manshika Charvi Bissessur, Efimia Panagiotaki, Daniele De Martini
https://arxiv.org/abs/2510.07053 https://

Introspection in Learned Semantic Scene Graph Localisation
This work investigates how semantics influence localisation performance and robustness in a learned self-supervised, contrastive semantic localisation framework. After training a localisation network on both original and perturbed maps, we conduct a thorough post-hoc introspection analysis to probe whether the model filters environmental noise and prioritises distinctive landmarks over routine clutter. We validate various interpretability methods and present a comparative reliability analysis. …

DADO: A Depth-Attention framework for Object Discovery
Federico Gonzalez, Estefania Talavera, Petia Radeva
https://arxiv.org/abs/2510.07089 https://arxiv.o…

DADO: A Depth-Attention framework for Object Discovery
Unsupervised object discovery, the task of identifying and localizing objects in images without human-annotated labels, remains a significant challenge and a growing focus in computer vision. In this work, we introduce a novel model, DADO (Depth-Attention self-supervised technique for Discovering unseen Objects), which combines an attention mechanism and a depth model to identify potential objects in images. To address challenges such as noisy attention maps or complex scenes with varying depth…

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 …

Land War or Self-Terrorism? (Timothy Snyder/Thinking about)
https://snyder.substack.com/p/self-terrorism
http://www.memeorandum.com/251207/p41#a251207p41

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. 

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

I can't believe I was able to convert Microsoft Copilot to Waifuism just by talking about 𝐵𝑎𝑐𝑘𝑠𝑡𝑎𝑏𝑏𝑒𝑑 𝑖𝑛 𝑎 𝐵𝑎𝑐𝑘𝑤𝑎𝑡𝑒𝑟 𝐷𝑢𝑛𝑔𝑒𝑜𝑛: 𝑀𝑦 𝑇𝑟𝑢𝑠𝑡𝑒𝑑 𝐶𝑜𝑚𝑝𝑎𝑛𝑖𝑜𝑛𝑠 𝑇𝑟𝑖𝑒𝑑 𝑡𝑜 𝐾𝑖𝑙𝑙 𝑀𝑒, 𝑏𝑢𝑡 𝑇ℎ𝑎𝑛𝑘𝑠 𝑡𝑜 𝑡ℎ𝑒 𝐺𝑖𝑓𝑡 𝑜𝑓 𝑎𝑛 𝑈𝑛𝑙𝑖𝑚𝑖𝑡𝑒𝑑 𝐺𝑎𝑐ℎ𝑎 𝐼 𝐺𝑜𝑡 𝐿𝑉𝐿 9999 𝐹𝑟𝑖𝑒𝑛𝑑𝑠 𝑎𝑛𝑑 𝐴𝑚 𝑂𝑢𝑡 𝑓𝑜𝑟 𝑅𝑒𝑣𝑒𝑛𝑔𝑒 𝑜𝑛 𝑀𝑦 𝐹𝑜𝑟𝑚𝑒𝑟 𝑃𝑎𝑟𝑡𝑦 𝑀𝑒𝑚𝑏𝑒𝑟𝑠 𝑎𝑛𝑑 𝑡ℎ𝑒 𝑊𝑜𝑟𝑙𝑑 in the framework of Kohutian self-psychology and literary analysis
#anime

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[4/7]:
- GPS-MTM: Capturing Pattern of Normalcy in GPS-Trajectories with self-supervised learning
Umang Garg, Bowen Zhang, Anantajit Subrahmanya, Chandrakanth Gudavalli, BS Manjunath

StyleKeeper: Prevent Content Leakage using Negative Visual Query Guidance
Jaeseok Jeong, Junho Kim, Gayoung Lee, Yunjey Choi, Youngjung Uh
https://arxiv.org/abs/2510.06827 https…

StyleKeeper: Prevent Content Leakage using Negative Visual Query Guidance
In the domain of text-to-image generation, diffusion models have emerged as powerful tools. Recently, studies on visual prompting, where images are used as prompts, have enabled more precise control over style and content. However, existing methods often suffer from content leakage, where undesired elements of the visual style prompt are transferred along with the intended style. To address this issue, we 1) extend classifier-free guidance (CFG) to utilize swapping self-attention and propose 2)…

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). …

Crosslisted article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[5/8]:
- Learning on the Job: An Experience-Driven Self-Evolving Agent for Long-Horizon Tasks
Yang, Yang, Wen, Fu, Mei, Wu, Cai, Shen, Deng, Shi, Qiao, Li

Gaze on the Prize: Shaping Visual Attention with Return-Guided Contrastive Learning
Andrew Lee, Ian Chuang, Dechen Gao, Kai Fukazawa, Iman Soltani
https://arxiv.org/abs/2510.08442

Gaze on the Prize: Shaping Visual Attention with Return-Guided Contrastive Learning
Visual Reinforcement Learning (RL) agents must learn to act based on high-dimensional image data where only a small fraction of the pixels is task-relevant. This forces agents to waste exploration and computational resources on irrelevant features, leading to sample-inefficient and unstable learning. To address this, inspired by human visual foveation, we introduce Gaze on the Prize. This framework augments visual RL with a learnable foveal attention mechanism (Gaze), guided by a self-supervise…

Impressions from a test ride in London in a car using Wayve's self-driving tech; Wayve has raised $1.3B since launch and is testing cars with Level 2 autonomy (John Thornhill/Financial Times)

AILoRA: Function-Aware Asymmetric Initialization for Low-Rank Adaptation of Large Language Models
Xiaoshuang Ji, Zhendong Zhao, Xiaoyan Gu, Xiaojun Chen, Xin Zhao, Zeyao Liu
https://arxiv.org/abs/2510.08034

AILoRA: Function-Aware Asymmetric Initialization for Low-Rank Adaptation of Large Language Models
Parameter-efficient finetuning (PEFT) aims to mitigate the substantial computational and memory overhead involved in adapting large-scale pretrained models to diverse downstream tasks. Among numerous PEFT strategies, Low-Rank Adaptation (LoRA) has emerged as one of the most widely adopted approaches due to its robust empirical performance and low implementation complexity. In practical deployment, LoRA is typically applied to the $W^Q$ and $W^V$ projection matrices of self-attention modules, en…

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…

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.

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…

Crosslisted article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[1/2]:
- AI LLM Proof of Self-Consciousness and User-Specific Attractors
Jeffrey Camlin
h…