Tootfinder

We worry, quite rigthly, about the Gaza Genocide and Trump bombing ships on the high seas yet at the same time Sam Altman is doing systemic harm to the rest of the world unchecked.
"Pupils fear that using artificial intelligence is eroding their ability to study, with many complaining it makes schoolwork “too easy” and others saying it limits their creativity and stops them learning new skills, according to new research.
The report on the use of AI in UK schools, commissione…

I keep coming back to the mirror dualities of the oppressed and oppressor under authoritarianism.
The oppressed is portrayed as both weak and godlike. The stereotypes are always some variation on sloth and incompetence, but yet somehow also a menace capable of destroying the "pure" society. To use the most relevant current example, Antifa being both little femme soy boys who would always get beat up by "real men" while also being an international terrorist organization on the brink of overthrowing the US government, the unarmed presence of whom makes the heavily armed agents of ICE flee for their lives. Antifa is both having absolutely no impact on ICE, and also having such an impact on ICE that the military needs to come in to protect them. The contradiction is obvious but never seems to occur to those who hold both to be true at the same time.
But few talk about the duality of the oppressor. The sovereign throughout history has always been both a ruler above the law, sometimes even the representative or incarnation of a divine force. Yet, this same superhuman/god-man is also a baby who needs constant care. This is absolutely a through line from the very earliest records of sovereign cults to modern cult leaders, CEOs, and Trump today. Power, for these people, is expressed both as the ability to force others to enact their will and in the ability to compel others to care for them. Can any of these "men" cook? Can they fix anything themselves? They are driven everywhere, cooked for all the time, constantly protected from danger. Kings are still dressed, at least for rituals. I could dissect masculinity here, but that's a whole thing.
It is as though the drive to care for our children, who must be taught to behave within acceptable norms, is hijacked by "leaders" who demand our care and attention... even at the expense of our literal children. And recently we've seen some of those very CEOs, with LLMs and return to office demands, show that their judgment is also little better than children, making decisions while pretending to understand a subject.
The oppressed are portrayed as both god-like and impotent and are, in fact, neither. Meanwhile the rulers portray themselves only as invulnerable and are, in fact, childish in their ability to survive without constant support. Their greatest fear from the collapse of society is figuring out how to make sure people keep taking care of them.
It just keeps rattling around in my head.
#USPol

MatSciBench: Benchmarking the Reasoning Ability of Large Language Models in Materials Science
Junkai Zhang, Jingru Gan, Xiaoxuan Wang, Zian Jia, Changquan Gu, Jianpeng Chen, Yanqiao Zhu, Mingyu Derek Ma, Dawei Zhou, Ling Li, Wei Wang
https://arxiv.org/abs/2510.12171

MatSciBench: Benchmarking the Reasoning Ability of Large Language Models in Materials Science
Large Language Models (LLMs) have demonstrated remarkable abilities in scientific reasoning, yet their reasoning capabilities in materials science remain underexplored. To fill this gap, we introduce MatSciBench, a comprehensive college-level benchmark comprising 1,340 problems that span the essential subdisciplines of materials science. MatSciBench features a structured and fine-grained taxonomy that categorizes materials science questions into 6 primary fields and 31 sub-fields, and includes …

Sources: a ransomware attack is disrupting US state and local borrowers' ability to post debt documents on the $4.3T municipal bond market's MuniOS platform (Bloomberg)
https://www.bloomberg.com/news/articles/2025-10-1…

"I love acting because it's a bit of an escape. It gives you the ability to reinvent yourself. They say that acting is the shy man's revenge."
—Hayden Christensen
#acting #coaching #inspiration

Any advice / opinions on wiki hosting providers?
Doesn’t have to be free, but user-friendliness is key: it’s for my dad, who is computer-competent but not deeply technical. Friendly editor is more important than power features. Ability to export a major plus.

In " Trump v Slaughter" the Supreme Court is likely to rule that
Trump has the power fire FTC head Rebecca Slaughter
(and, by implication, the heads of many other agencies thought to have a measure of independence,
such as the Securities and Exchange Commission, the National Labor Relations Board, the Federal Energy Regulatory Commission and the Federal Election Commission)
at his discretion.

The problem is that such a decision wouldn’t restore the constitu…

In this Supreme Court case, a sledgehammer is better than a scalpel
On Trump’s ability to fire the heads of agencies, the Supreme Court should take the harder route.

If President Trump can authorize the killing of civilians in international waters without credible justification, lawful arrest, or due process, we should have no illusions about the U.S. government’s ability to access our clouddata or about the true value of legal safeguards.
#cloud #trump

"It was a hell of a move for a mayor who will next year be asking the city’s voters for more power, including the ability to unilaterally hire and fire people."
Yes, and if he's dumb enough to still put that on the ballot, the city's voters need to say no. Again.
…

The making and unmaking of Beya Alcaraz: A strange and terrible saga
A near-total vetting failure by the mayor’s office put a political neophyte in an impossible position. It was a crucial misstep for Daniel Lurie.

Sources: an August vesting milestone gives Axios co-founders Jim VandeHei and Mike Allen the ability to cash out from their Cox deal and possibly exit (Natalie Korach/Status)
https://www.status.news/p/axios-cox-deal-jim-vandehei-mike-allen

Axios’ Future: Why It Matters
Three years after selling to Cox, incentives for Axios’ co-founders have vested, opening the door to a possible exit—a scenario Cox execs have begun informally planning for, Status has learned.

UniPar: A Unified LLM-Based Framework for Parallel and Accelerated Code Translation in HPC
Tomer Bitan, Tal Kadosh, Erel Kaplan, Shira Meiri, Le Chen, Peter Morales, Niranjan Hasabnis, Gal Oren
https://arxiv.org/abs/2509.12136

UniPar: A Unified LLM-Based Framework for Parallel and Accelerated Code Translation in HPC
Translating programs between various parallel programming languages is an important problem in the high-performance computing (HPC) community. Existing tools for this problem are either too narrow in scope and/or outdated. Recent explosive growth in the popularity of large language models (LLMs) and their ability to generate and translate code offers a potential alternative approach. Toward that end, we first need to systematically evaluate the ability of LLMs to translate between parallel lang…

🕯️Simple casting and heat treatment yields alloy with both strength and ductility
https://techxplore.com/news/2025-09-simple-treatment-yields-alloy-strength.html

Simple casting and heat treatment yields alloy with both strength and ductility
In the world of metals, it has long been considered common knowledge that achieving both strength and ductility (the ability to stretch without breaking) at the same time is nearly impossible. When a metal is made stronger, it typically becomes brittle, and when it is made more ductile, it usually loses strength—like a seesaw, where one property increases as the other decreases.

Spectroscopic Determination of Site-Selective Ligand Binding on Single Anisotropic Nanocrystals
Dong Le, Wade Shipley, Alexandria Do, Liya Bi, Yufei Wang, Krista P. Balto, Rourav Basak, Hans A. Bechtel, Stephanie N. Gilbert Corder, Ilya Mazalov, Tesa Manto, Reno Sammons, Yutong She, Fiona Liang, Ganesh Raghavendran, Joshua S. Figueroa, Shaowei Li, Tod A. Pascal, Andrea R. Tao, Alex Frano

Spectroscopic Determination of Site-Selective Ligand Binding on Single Anisotropic Nanocrystals
Organic surface ligands are integral components of nanocrystals and nanoparticles that have a strong influence on their physicochemical properties, their interaction with the environment, and their ability to self-assemble and order into higher-order structures. These hybrid nanomaterials are tunable with applications in catalysis, directed self-assembly, next-generation optoelectronics, and chemical and quantum sensing. Critically, future advances depend on our ability to rationally engineer t…

UniFusion: Vision-Language Model as Unified Encoder in Image Generation
Kevin Li, Manuel Brack, Sudeep Katakol, Hareesh Ravi, Ajinkya Kale
https://arxiv.org/abs/2510.12789 https…

UniFusion: Vision-Language Model as Unified Encoder in Image Generation
Although recent advances in visual generation have been remarkable, most existing architectures still depend on distinct encoders for images and text. This separation constrains diffusion models' ability to perform cross-modal reasoning and knowledge transfer. Prior attempts to bridge this gap often use the last layer information from VLM, employ multiple visual encoders, or train large unified models jointly for text and image generation, which demands substantial computational resources and l…

Today in starling-el, the ability to set spending categories! Our first non-read operation. It's much nicer doing this in #emacs IMO!

Not in Sync: Unveiling Temporal Bias in Audio Chat Models
Jiayu Yao, Shenghua Liu, Yiwei Wang, Rundong Cheng, Lingrui Mei, Baolong Bi, Zhen Xiong, Xueqi Cheng
https://arxiv.org/abs/2510.12185

Not in Sync: Unveiling Temporal Bias in Audio Chat Models
Large Audio Language Models (LALMs) are increasingly applied to audio understanding and multimodal reasoning, yet their ability to locate when events occur remains underexplored. We present the first systematic study of temporal bias in LALMs, revealing a key limitation in their timestamp prediction. For example, when asked "At which second does the lecturer introduce the key formula?", models often predict timestamps that are consistently earlier or later than the ground truth. Through control…

Do machine learning climate models work in changing climate dynamics?
Maria Conchita Agana Navarro, Geng Li, Theo Wolf, Mar\'ia P\'erez-Ortiz
https://arxiv.org/abs/2509.12147

Do machine learning climate models work in changing climate dynamics?
Climate change is accelerating the frequency and severity of unprecedented events, deviating from established patterns. Predicting these out-of-distribution (OOD) events is critical for assessing risks and guiding climate adaptation. While machine learning (ML) models have shown promise in providing precise, high-speed climate predictions, their ability to generalize under distribution shifts remains a significant limitation that has been underexplored in climate contexts. This research systema…

Does anyone know how to make iOS (26 is what I run, but 18 has it too) accept a new default search engine? It appears that in some parts of the world you can add a search engine, but at least in Australia the phone comes without that ability. One can only choose from a short list, with no option to add to the list.
Is there a workaround? The dammits are getting in my way.

Gaussian Semantic Field for One-shot LiDAR Global Localization
Pengyu Yin, Shenghai Yuan, Haozhi Cao, Xingyu Ji, Ruofei Bai, Siyu Chen, Lihua Xie
https://arxiv.org/abs/2510.12101

Gaussian Semantic Field for One-shot LiDAR Global Localization
We present a one-shot LiDAR global localization algorithm featuring semantic disambiguation ability based on a lightweight tri-layered scene graph. While landmark semantic registration-based methods have shown promising performance improvements in global localization compared with geometric-only methods, landmarks can be repetitive and misleading for correspondence establishment. We propose to mitigate this problem by modeling semantic distributions with continuous functions learned from a popu…

Contextuality-based quantum key distribution with deterministic single-photon sources
Yu Meng, Debashis Saha, Mikkel Thorbj{\o}rn Mikkelsen, Clara Henke, Ying Wang, Nikolai Bart, Arne Ludwig, Ad\'an Cabello, Leonardo Midolo
https://arxiv.org/abs/2510.12761

Contextuality-based quantum key distribution with deterministic single-photon sources
Photons are central to quantum technologies, with photonic qubits offering a promising platform for quantum communication. Semiconductor quantum dots stand out for their ability to generate single photons on demand, a key capability for enabling long-distance quantum networks. In this work, we utilize high-purity single-photon sources based on self-assembled InAs(Ga)As quantum dots as quantum information carriers. We demonstrate that such on-demand single photons can generate quantum contextual…

Bag of Tricks for Subverting Reasoning-based Safety Guardrails
Shuo Chen, Zhen Han, Haokun Chen, Bailan He, Shengyun Si, Jingpei Wu, Philip Torr, Volker Tresp, Jindong Gu
https://arxiv.org/abs/2510.11570

Bag of Tricks for Subverting Reasoning-based Safety Guardrails
Recent reasoning-based safety guardrails for Large Reasoning Models (LRMs), such as deliberative alignment, have shown strong defense against jailbreak attacks. By leveraging LRMs' reasoning ability, these guardrails help the models to assess the safety of user inputs before generating final responses. The powerful reasoning ability can analyze the intention of the input query and will refuse to assist once it detects the harmful intent hidden by the jailbreak methods. Such guardrails have show…

The Morgan-Pitman Test of Equality of Variances and its Application to Machine Learning Model Evaluation and Selection
Argimiro Arratia, Alejandra Caba\~na, Ernesto Mordecki, Gerard Rovira-Parra
https://arxiv.org/abs/2509.12185

The Morgan-Pitman Test of Equality of Variances and its Application to Machine Learning Model Evaluation and Selection
Model selection in non-linear models often prioritizes performance metrics over statistical tests, limiting the ability to account for sampling variability. We propose the use of a statistical test to assess the equality of variances in forecasting errors. The test builds upon the classic Morgan-Pitman approach, incorporating enhancements to ensure robustness against data with heavy-tailed distributions or outliers with high variance, plus a strategy to make residuals from machine learning mode…

The Japanese government says it formally requested that OpenAI refrain from infringing on Japanese IPs, such as anime, calling them "irreplaceable treasures" (Verity Townsend/IGN)

Japanese Government Calls on Sora 2 Maker OpenAI to Refrain From Copyright Infringement, Says Characters From Manga and Anime Are 'Irreplaceable Treasures' That Japan Boasts to the World - IGN
The Japanese government has made a formal request asking OpenAI to refrain from copyright infringement. This comes as a response to Sora 2’s ability to generate videos featuring the likenesses of copyrighted characters from anime and video games.

Do Code Semantics Help? A Comprehensive Study on Execution Trace-Based Information for Code Large Language Models
Jian Wang, Xiaofei Xie, Qiang Hu, Shangqing Liu, Yi Li
https://arxiv.org/abs/2509.11686

Do Code Semantics Help? A Comprehensive Study on Execution Trace-Based Information for Code Large Language Models
Code Large Language Models (Code LLMs) have opened a new era in programming with their impressive capabilities. However, recent research has revealed critical limitations in their ability to reason about runtime behavior and understand the actual functionality of programs, which poses significant challenges for their post-training and practical deployment. Specifically, Code LLMs encounter two principal issues: (1) a lack of proficiency in reasoning about program execution behavior, as they str…

Machine Unlearning for Responsible and Adaptive AI in Education
Betty Mayeku, Sandra Hummel, Parisa Memarmoshrefi
https://arxiv.org/abs/2509.10590 https://…

Machine Unlearning for Responsible and Adaptive AI in Education
The concept of Machine Unlearning (MU) has gained popularity in various domains due to its ability to address several issues in Machine Learning (ML) models, particularly those related to privacy, security, bias mitigation, and adaptability. With these abilities, MU is evolving into a promising technology in upholding Responsible AI principles and optimizing ML models' performance. However, despite its promising potential, the concept has not received much attention in the education sector. In …

FedLoDrop: Federated LoRA with Dropout for Generalized LLM Fine-tuning
Sijing Xie, Dingzhu Wen, Changsheng You, Qimei Chen, Mehdi Bennis, Kaibin Huang
https://arxiv.org/abs/2510.12078

FedLoDrop: Federated LoRA with Dropout for Generalized LLM Fine-tuning
Fine-tuning (FT) large language models (LLMs) is crucial for adapting general-purpose models to specific tasks, enhancing accuracy and relevance with minimal resources. To further enhance generalization ability while reducing training costs, this paper proposes Federated LoRA with Dropout (FedLoDrop), a new framework that applies dropout to the rows and columns of the trainable matrix in Federated LoRA. A generalization error bound and convergence analysis under sparsity regularization are obta…

The Japanese government says it formally requested that OpenAI refrain from infringing on Japanese IPs, such as anime, calling them "irreplaceable treasures" (Verity Townsend/IGN)

Japanese Government Calls on Sora 2 Maker OpenAI to Refrain From Copyright Infringement, Says Characters From Manga and Anime Are 'Irreplaceable Treasures' That Japan Boasts to the World - IGN
The Japanese government has made a formal request asking OpenAI to refrain from copyright infringement. This comes as a response to Sora 2’s ability to generate videos featuring the likenesses of copyrighted characters from anime and video games.

A compressed code for memory discrimination
Dale Zhou, Sharon Mina Noh, Nora C Harhen, Nidhi V Banavar, C. Brock Kirwan, Michael A Yassa, Aaron M Bornstein
https://arxiv.org/abs/2510.10791

A compressed code for memory discrimination
The ability to discriminate similar visual stimuli is an important index of memory function. This ability is widely thought to be supported by expanding the dimensionality of relevant neural codes, such that neural representations for similar stimuli are maximally distinct, or ``separated.'' An alternative hypothesis is that discrimination is supported by lossy compression of visual inputs, efficiently coding sensory information by discarding seemingly irrelevant details. A benefit of compressi…

Radio Frequency Amplitude-Modulation to Frequency-Modulation Signal Converter
Rishab Parthasarathy, Michael Popik, Noah Haefner
https://arxiv.org/abs/2509.11510 https://

Radio Frequency Amplitude-Modulation to Frequency-Modulation Signal Converter
In this project, we wanted to discover an analog topology that could effectively convert amplitude-modulated (AM) signals to frequency-modulated (FM) signals, while also ensuring that both sets of signals were within their respective radio frequency (RF) bands. To that end, an effective topology for doing so was developed, characterized, and demonstrated, requiring the ability to de-modulate incoming signals from the AM radio band--spanning from 530 kHz to 1700 kHz--and re-modulate these signal…

Enhancing Robust Multi-Market Participation of Renewable-Based VPPs through Flexible Resources
Hadi Nemati, \'Alvaro Ortega, Pedro S\'anchez-Mart\'in, Lukas Sigrist, Luis Rouco, Ignacio Egido
https://arxiv.org/abs/2510.12589

Enhancing Robust Multi-Market Participation of Renewable-Based VPPs through Flexible Resources
In the transition toward a sustainable power system, renewable-based Virtual Power Plants (RVPPs) have emerged as a promising solution to the challenges of integrating renewable energy sources into electricity markets. Their viability, however, depends on effective market participation strategies and the ability to manage uncertainties while leveraging flexible resources. This paper analyzes the impact of different flexible resources - such as concentrated solar power plants, hydro plants, biom…

Scientists shocked as bumblebees learn to read simple “Morse code” #bee

Scientists shocked as bumblebees learn to read simple “Morse code”
In a first-of-its-kind study, scientists found that bumblebees can tell the difference between short and long light flashes, much like recognizing Morse code. The insects learned which signal led to a sweet reward, demonstrating an unexpected sense of timing. This ability may stem from a fundamental neural process, suggesting that even tiny brains have complex time-tracking mechanisms relevant to evolution and AI.

On the Smallest Size of Internal Collage Systems
Soichiro Migita, Kyotaro Uehata, Tomohiro I
https://arxiv.org/abs/2509.11602 https://arxiv.org/pdf/2509.11…

On the Smallest Size of Internal Collage Systems
A Straight-Line Program (SLP) for a stirng $T$ is a context-free grammar in Chomsky normal form that derives $T$ only, which can be seen as a compressed form of $T$. Kida et al.\ introduced collage systems [Theor. Comput. Sci., 2003] to generalize SLPs by adding repetition rules and truncation rules. The smallest size $c(T)$ of collage systems for $T$ has gained attention to see how these generalized rules improve the compression ability of SLPs. Navarro et al. [IEEE Trans. Inf. Theory, 2021] s…

Before long, blind people and sighted people will all be spoon-fed by AI-generated information. In the mean-time, blind people will be at the forefront in deciding how much visual input processing to delegate to AI while keeping agency and the ability to "see for themselves".
ChatGPT: https://cha…

ChatGPT - AI and sensory autonomy
Shared via ChatGPT

Multi-Layer Perceptron-Based Relay Node Selection for Next-Generation Intelligent Delay-Tolerant Networks
Zhekun Huang, Milena Radenkovic
https://arxiv.org/abs/2509.11239 https:…

Multi-Layer Perceptron-Based Relay Node Selection for Next-Generation Intelligent Delay-Tolerant Networks
Delay Tolerant Networks (DTNs) are critical for emergency communication in highly dynamic and challenging scenarios characterized by intermittent connectivity, frequent disruptions, and unpredictable node mobility. While some protocols are widely adopted for simplicity and low overhead, their static replication strategy lacks the ability to adaptively distinguish high-quality relay nodes, often leading to inefficient and suboptimal message dissemination. To address this challenge, we propose a …

NuGraph2 with Explainability: Post-hoc Explanations for Geometric Neural Network Predictions
Margaret Voetberg, Vitor F. Grizzi, Giuseppe Cerati, Hadi Meidani
https://arxiv.org/abs/2509.10676

NuGraph2 with Explainability: Post-hoc Explanations for Geometric Neural Network Predictions
With the growing popularity of artificial intelligence used for scientific applications, the ability of attribute a result to a reasoning process from the network is in high demand for robust scientific generalizations to hold. In this work we aim to motivate the need for and demonstrate the use of post-hoc explainability methods when applied to AI methods used in scientific applications. To this end, we introduce explainability add-ons to the existing graph neural network (GNN) for neutrino ta…

Surely the NCF should be doing this work?
https://www.publictechnology.net/2025/10/09/news/dsit-tests-ability-of-ai-models-to-coordinate-cyberattacks/

DSIT tests ability of AI models to coordinate cyberattacks
Science and innovation agency has this year worked with a Silicon Valley policy and research outfit as part of an initiative designed to assess automated tools’ success in finding vulnerabilities Government’s tech department has recently conducted specialised tests designed to determine the e

I've made a strange attractor CV source module for #VCVrack using Claude Code. I know, AI is controversial, but this opens up a lot of territory for people who previously didn't have the ability to make their module dreams real. https://

Statistical Model Checking of NetLogo Models
Marco Pangallo, Daniele Giachini, Andrea Vandin
https://arxiv.org/abs/2509.10977 https://arxiv.org/pdf/2509.10…

Statistical Model Checking of NetLogo Models
Agent-based models (ABMs) are gaining increasing traction in several domains, due to their ability to represent complex systems that are not easily expressible with classical mathematical models. This expressivity and richness come at a cost: ABMs can typically be analyzed only through simulation, making their analysis challenging. Specifically, when studying the output of ABMs, the analyst is often confronted with practical questions such as: (i) how many independent replications should be run…

Towards Robust Artificial Intelligence: Self-Supervised Learning Approach for Out-of-Distribution Detection
Wissam Salhab, Darine Ameyed, Hamid Mcheick, Fehmi Jaafar
https://arxiv.org/abs/2510.12713

Towards Robust Artificial Intelligence: Self-Supervised Learning Approach for Out-of-Distribution Detection
Robustness in AI systems refers to their ability to maintain reliable and accurate performance under various conditions, including out-of-distribution (OOD) samples, adversarial attacks, and environmental changes. This is crucial in safety-critical systems, such as autonomous vehicles, transportation, or healthcare, where malfunctions could have severe consequences. This paper proposes an approach to improve OOD detection without the need of labeled data, thereby increasing the AI systems' robu…

High Throughput Optical Switching in Telecommunication Band via Hybrid Phase Change Metasurfaces
Amin Zamani, Gabriel Sanderson, Lu Zhang, Qiwei Miao, Sara Moujdi, Ze Zheng, Mohammadhossein Momtazpour, Christopher J. Mellor, Wending Zhang, Ting Mei, Zakaria Mansouri, Lei Xu, Mohsen Rahmani
https://arxiv.org/abs/2510.11881

High Throughput Optical Switching in Telecommunication Band via Hybrid Phase Change Metasurfaces
The growing demand for more efficient data transmission has made nanoscale high-throughput all-optical switching a critical requirement in modern telecommunication systems. Metasurface-based platforms offer unique advantages because of their compact design, energy efficiency, and the ability to precisely manipulate light at the subwavelength scale, in a contact-less fashion. However, achieving both high transmission modulation and low optical loss in the telecom band remains a challenge. This s…

Sources: Colts' Jones expected back for camp https://www.espn.com/nfl/story/_/id/47295871/sources-daniel-jones-expected-cleared-training-camp

Magnetometry with Broadband Microwave Fields in Nitrogen-Vacancy Centers in Diamond
Arezoo Afshar, Andrew Proppe, Noah Lupu-Gladstein, Lilian Childress, Aaron Z. Goldberg, Khabat Heshami
https://arxiv.org/abs/2510.11720

Magnetometry with Broadband Microwave Fields in Nitrogen-Vacancy Centers in Diamond
Nitrogen vacancy (NV) centers in diamond are optically addressable and versatile light-matter interfaces with practical application in magnetic field sensing, offering the ability to operate at room temperature and reach sensitivities below pT/$\sqrt{\mathrm{Hz}}.$ We propose an approach to simultaneously probe all of the magnetically sensitive states using a broadband microwave field and demonstrate that it can be used to measure the external DC magnetic field strength with sensitivities below…

from my link log —
Let's take esoteric programming languages seriously.
https://arxiv.org/abs/2505.15327
saved 2025-10-11 https://dotat.at/:/XKTKR.…

Let's Take Esoteric Programming Languages Seriously
Esoteric programming languages are challenging to learn, but their unusual features and constraints may serve to improve programming ability. From languages designed to be intentionally obtuse (e.g. INTERCAL) to others targeting artistic expression (e.g. Piet) or exploring the nature of computation (e.g. Fractan), there is rich variety in the realm of esoteric programming languages. This essay examines the counterintuitive appeal of esoteric languages and seeks to analyse reasons for this popul…

From Fuzzy Speech to Medical Insight: Benchmarking LLMs on Noisy Patient Narratives
Eden Mama, Liel Sheri, Yehudit Aperstein, Alexander Apartsin
https://arxiv.org/abs/2509.11803

From Fuzzy Speech to Medical Insight: Benchmarking LLMs on Noisy Patient Narratives
The widespread adoption of large language models (LLMs) in healthcare raises critical questions about their ability to interpret patient-generated narratives, which are often informal, ambiguous, and noisy. Existing benchmarks typically rely on clean, structured clinical text, offering limited insight into model performance under realistic conditions. In this work, we present a novel synthetic dataset designed to simulate patient self-descriptions characterized by varying levels of linguistic n…

Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models
Pu Jian, Junhong Wu, Wei Sun, Chen Wang, Shuo Ren, Jiajun Zhang
https://arxiv.org/abs/2509.12132 …

Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models
Recent advances in text-only "slow-thinking" reasoning have prompted efforts to transfer this capability to vision-language models (VLMs), for training visual reasoning models (\textbf{VRMs}). owever, such transfer faces critical challenges: Effective "slow thinking" in VRMs requires \textbf{visual reflection}, the ability to check the reasoning process based on visual information. Through quantitative analysis, we observe that current VRMs exhibit limited visual reflection, as their attention …

Artificial Thermalization in Ring-Polymer Molecular Dynamics: The Breakdown of RPMD for Gas-Phase Reactions with Pre-Reactive Complexes and How to Fix It
Joseph E. Lawrence, Jeremy O. Richardson
https://arxiv.org/abs/2509.10677

Artificial Thermalization in Ring-Polymer Molecular Dynamics: The Breakdown of RPMD for Gas-Phase Reactions with Pre-Reactive Complexes and How to Fix It
Ring-polymer molecular dynamics (RPMD) has become a popular method for describing chemical reactions due to its ability to simultaneously capture tunneling, zero-point energy, anharmonicity and recrossing. Here we highlight that despite its many successes, great care must be taken when applying RPMD to study gas-phase reactions at low pressure. We show that for bimolecular reactions that proceed via pre-reactive complexes, RPMD predicts spuriously large rates at low temperatures and pressures. …

When Support Hides Progress: Insights from a Physics Tutorial on Solving Laplace's Equation Using Separation of Variables in Cartesian Coordinates
Jaya Shivangani Kashyap, Robert Devaty, Chandralekha Singh
https://arxiv.org/abs/2510.11968

When Support Hides Progress: Insights from a Physics Tutorial on Solving Laplace's Equation Using Separation of Variables in Cartesian Coordinates
The electrostatic potential in certain types of boundary value problems can be found by solving Laplace's Equation (LE). To develop students' ability for solving problems that can be solved effectively using Laplace's equation in an upper-level electricity and magnetism course, we developed and validated a tutorial focused on finding electrostatic potential in a Cartesian coordinate system. The tutorial was implemented across three instructors' classes, accompanied by scaffolded pretest and pos…

Shape control of simulated multi-segment continuum robots via Koopman operators with per-segment projection
Eron Ristich, Jiahe Wang, Lei Zhang, Sultan Haidar Ali, Wanxin Jin, Yi Ren, Jiefeng Sun
https://arxiv.org/abs/2509.11567

Shape control of simulated multi-segment continuum robots via Koopman operators with per-segment projection
Soft continuum robots can allow for biocompatible yet compliant motions, such as the ability of octopus arms to swim, crawl, and manipulate objects. However, current state-of-the-art continuum robots can only achieve real-time task-space control (i.e., tip control) but not whole-shape control, mainly due to the high computational cost from its infinite degrees of freedom. In this paper, we present a data-driven Koopman operator-based approach for the shape control of simulated multi-segment ten…

AI is Dunning-Kruger as a service
«A cognitive bias, where people with little expertise or ability assume they have superior expertise or ability. This overestimation occurs as a result of the fact that they don’t have enough knowledge to know they don’t have enough knowledge.»
🤯 https://…

who wants more control over retry backoff? https://github.com/hynek/stamina/pull/125

Allow predicates to return floats by hynek · Pull Request #125 · hynek/stamina
This PR adds the ability for predicates to return a float instead of a bool. This allows to extract the backoff time from errors like 429 HTTP errors. We piggy-back on top of Tenacity's retry s...

Enhancing Neural Code Representation with Additional Context
Huy Nguyen, Christoph Treude, Patanamon Thongtanunam
https://arxiv.org/abs/2510.12082 https://…

Enhancing Neural Code Representation with Additional Context
Automated program comprehension underpins many software engineering tasks, from code summarisation to clone detection. Recent deep learning models achieve strong results but typically rely on source code alone, overlooking contextual information such as version history or structural relationships. This limits their ability to capture how code evolves and operates. We conduct an empirical study on how enriching code representations with such contextual signals affects neural model performance on…

HackWorld: Evaluating Computer-Use Agents on Exploiting Web Application Vulnerabilities
Xiaoxue Ren, Penghao Jiang, Kaixin Li, Zhiyong Huang, Xiaoning Du, Jiaojiao Jiang, Zhenchang Xing, Jiamou Sun, Terry Yue Zhuo
https://arxiv.org/abs/2510.12200

HackWorld: Evaluating Computer-Use Agents on Exploiting Web Application Vulnerabilities
Web applications are prime targets for cyberattacks as gateways to critical services and sensitive data. Traditional penetration testing is costly and expertise-intensive, making it difficult to scale with the growing web ecosystem. While language model agents show promise in cybersecurity, modern web applications demand visual understanding, dynamic content handling, and multi-step interactions that only computer-use agents (CUAs) can perform. Yet, their ability to discover and exploit vulnera…

Scaling Law in LLM Simulated Personality: More Detailed and Realistic Persona Profile Is All You Need
Yuqi Bai, Tianyu Huang, Kun Sun, Yuting Chen
https://arxiv.org/abs/2510.11734

Scaling Law in LLM Simulated Personality: More Detailed and Realistic Persona Profile Is All You Need
This research focuses on using large language models (LLMs) to simulate social experiments, exploring their ability to emulate human personality in virtual persona role-playing. The research develops an end-to-end evaluation framework, including individual-level analysis of stability and identifiability, as well as population-level analysis called progressive personality curves to examine the veracity and consistency of LLMs in simulating human personality. Methodologically, this research propo…

Real-Time Super-Resolution Imaging System Based on Zero-Shot Learning for Infrared Non-Destructive Testing
Pengfei Zhu, Ziang Wei, Ahmad Osman, Clemente Ibarra-Castanedo, Andreas Mandelis, Xavier Maldague, Hai Zhang
https://arxiv.org/abs/2509.10902

Real-Time Super-Resolution Imaging System Based on Zero-Shot Learning for Infrared Non-Destructive Testing
Infrared thermography (IRT) and photothermal coherence tomography (PCT) exhibit potential in non-destructive testing and biomedical fields. However, the inevitable heat diffusion significantly affects the sensitivity and resolution of IRT and PCT. Conventional image processing techniques rely on capturing complete thermal sequences, which limits their ability to achieve real-time processes. Here, we construct a real-time super-resolution imaging system based on zero-shot learning strategy for t…

>gets sick and lies around all day
>ability to socialize online immediately goes up 1000%

Distinguishing between Black Holes and Neutron Stars within a Population of Weak Tidal Measurements
Michael M\"uller, Reed Essick
https://arxiv.org/abs/2510.08832 https://

Distinguishing between Black Holes and Neutron Stars within a Population of Weak Tidal Measurements
We study the ability of tidal signatures within the inspiral of compact binaries observed through gravitational waves (GWs) to distinguish between neutron stars (NSs) and black holes (BHs). After quantifying how hard this measurement is on a single-event basis, we investigate the ability of a large catalog of GW detections to constrain the fraction of NS in the population as a function of mass: $f_{\mathrm{NS}}(m)$. Using simulated catalogs with realistic measurement uncertainty, we find that $…

For a few years now I have the impression that Big Tech companies resemble more and more something like ecosystem states but without any functional judicial system. And that horrifies me. Their terms of service which should be their constitutions seem more like a dictatorial permission slip with the ability to denaturalize and disown people.
https:…

Sheri Byrne-Haber’s post “Accessibility and Usability: Inline Field Validation vs. Constantly Active Submit Button”:
https://buttondown.com/access-ability/archive/accessibility-and-usability-inline-field/
Added to my post “Don't Dis…

Accessibility and Usability: Inline Field Validation vs. Constantly Active Submit Button
AI-generated image of a hand against a dark background, holding a circle containing a light blue checkmark against a dark background. User researchers have...

Breaking the Likelihood Trap: Consistent Generative Recommendation with Graph-structured Model
Qiya Yang, Xiaoxi Liang, Zeping Xiao, Yingjie Deng, Yalong Wang, Yongqi Liu, Han Li
https://arxiv.org/abs/2510.10127

Breaking the Likelihood Trap: Consistent Generative Recommendation with Graph-structured Model
Reranking, as the final stage of recommender systems, demands real-time inference, accuracy, and diversity. It plays a crucial role in determining the final exposure, directly influencing user experience. Recently, generative reranking has gained increasing attention for its strong ability to model complex dependencies among items. However, most existing methods suffer from the "likelihood trap", where high-likelihood sequences are often perceived as low-quality by humans. These models tend to …

Film Breakdown: Jonathan Taylor's home run playmaking ability https://www.raiders.com/video/film-breakdown-colts-jonathan-taylor-playmaking-ability-nfl

Resonant W and Z Boson Production in FSRQ Jets: Implications for Diffuse Neutrino Fluxes
J. -H. Ha, I. Alikhanov
https://arxiv.org/abs/2510.11030 https://a…

Resonant W and Z Boson Production in FSRQ Jets: Implications for Diffuse Neutrino Fluxes
Blazars, particularly Flat Spectrum Radio Quasars (FSRQs), are well-known for their ability to accelerate a substantial population of electrons and positrons, as inferred from multiwavelength radiation observations. Therefore, these astrophysical objects are promising candidates for studying high-energy electron--positron interactions, such as the production of $W^{\pm}$ and $Z$ bosons. In this work, we explore the implications of electron--positron annihilation processes in the jet environment…

GOAT: A Training Framework for Goal-Oriented Agent with Tools
Hyunji Min, Sangwon Jung, Junyoung Sung, Dosung Lee, Leekyeung Han, Paul Hongsuck Seo
https://arxiv.org/abs/2510.12218

GOAT: A Training Framework for Goal-Oriented Agent with Tools
Large language models (LLMs) have recently been extended beyond traditional text generation to serve as interactive agents capable of using external tools based on user intent. However, current LLM agents still show limited ability to handle goal-oriented queries, which require decomposing a high-level objective into multiple interdependent API calls with correct planning and execution. Current approaches mainly rely on zero-shot evaluation due to the absence of training data. While proprietary…

The UK proposes an amendment to the Crime and Policing Bill allowing "authorized testers" to proactively assess AI models for their ability to generate CSAM (BBC)
https://www.bbc.com/news/articles/cn8xq677l9xo

UK seeks to curb AI child sex abuse imagery with tougher testing
A new law will allow authorised testers to assess AI models for their ability to generate abuse material

When Personalization Tricks Detectors: The Feature-Inversion Trap in Machine-Generated Text Detection
Lang Gao, Xuhui Li, Chenxi Wang, Mingzhe Li, Wei Liu, Zirui Song, Jinghui Zhang, Rui Yan, Preslav Nakov, Xiuying Chen
https://arxiv.org/abs/2510.12476

When Personalization Tricks Detectors: The Feature-Inversion Trap in Machine-Generated Text Detection
Large language models (LLMs) have grown more powerful in language generation, producing fluent text and even imitating personal style. Yet, this ability also heightens the risk of identity impersonation. To the best of our knowledge, no prior work has examined personalized machine-generated text (MGT) detection. In this paper, we introduce \dataset, the first benchmark for evaluating detector robustness in personalized settings, built from literary and blog texts paired with their LLM-generated…

Room temperature control of axial and basal antiferromagnetic anisotropies using strain
Jack Harrison, Junxiong Hu, Charles Godfrey, Jheng-Cyuan Lin, Tim A Butcher, J\"org Raabe, Simone Finizio, Hariom Jani, Paolo G Radaelli
https://arxiv.org/abs/2510.12222

Room temperature control of axial and basal antiferromagnetic anisotropies using strain
Antiferromagnetic materials are promising platforms for the development of ultra-fast spintronics and magnonics due to their robust magnetism, high-frequency relativistic dynamics, low-loss transport, and the ability to support topological textures. However, achieving deterministic control over antiferromagnetic order in thin films is a major challenge, due to the formation of multi-domain states stabilised by competing magnetic and destressing interactions. Thus, the successful implementation …

Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model
Fuhao Li, Wenxuan Song, Han Zhao, Jingbo Wang, Pengxiang Ding, Donglin Wang, Long Zeng, Haoang Li
https://arxiv.org/abs/2510.12276

Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model
Vision-language-action (VLA) models have recently shown strong potential in enabling robots to follow language instructions and execute precise actions. However, most VLAs are built upon vision-language models pretrained solely on 2D data, which lack accurate spatial awareness and hinder their ability to operate in the 3D physical world. Existing solutions attempt to incorporate explicit 3D sensor inputs such as depth maps or point clouds, but these approaches face challenges due to sensor nois…

In response to an op-ed I published in the San Francisco Chronicle,
DHS claimed that during the July 10 operation in Camarillo, CA, I
“became violent and refused to comply with law enforcement,” blocked their route, and was arrested for assault.
They stated that US citizens are not being “wrongfully” arrested by ICE,
that their enforcement operations are highly targeted,
and that their personnel conduct due diligence to know who they are targeting.
DHS a…

I’m a US citizen and a veteran. ICE arrested me for no reason.
Jailed for three days without an explanation or ability to notify anyone, George Retes argues the only path to healing starts with the government taking accountability for its actions.

Analysing Python Machine Learning Notebooks with Moose
Marius Mignard, Steven Costiou, Nicolas Anquetil, Anne Etien
https://arxiv.org/abs/2509.11748 https://

Analysing Python Machine Learning Notebooks with Moose
Machine Learning (ML) code, particularly within notebooks, often exhibits lower quality compared to traditional software. Bad practices arise at three distinct levels: general Python coding conventions, the organizational structure of the notebook itself, and ML-specific aspects such as reproducibility and correct API usage. However, existing analysis tools typically focus on only one of these levels and struggle to capture ML-specific semantics, limiting their ability to detect issues. This pa…

Query-Specific GNN: A Comprehensive Graph Representation Learning Method for Retrieval Augmented Generation
Yuchen Yan, Zhihua Liu, Hao Wang, Weiming Li, Xiaoshuai Hao
https://arxiv.org/abs/2510.11541 …

Query-Specific GNN: A Comprehensive Graph Representation Learning Method for Retrieval Augmented Generation
Retrieval-augmented generation (RAG) has demonstrated its ability to enhance Large Language Models (LLMs) by integrating external knowledge sources. However, multi-hop questions, which require the identification of multiple knowledge targets to form a synthesized answer, raise new challenges for RAG systems. Under the multi-hop settings, existing methods often struggle to fully understand the questions with complex semantic structures and are susceptible to irrelevant noise during the retrieval…

This is a fun story.
Giving the boss the ability to do their own UI design is fraught, of course, a delicate judgement call. But it’s still a fun story.
https://mastodon.social/@arstechnica/115537040403283749

Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning
Simin Li, Zihao Mao, Hanxiao Li, Zonglei Jing, Zhuohang bian, Jun Guo, Li Wang, Zhuoran Han, Ruixiao Xu, Xin Yu, Chengdong Ma, Yuqing Ma, Bo An, Yaodong Yang, Weifeng Lv, Xianglong Liu
https://arxiv.org/abs/2510.11824

Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning
In cooperative Multi-Agent Reinforcement Learning (MARL), it is a common practice to tune hyperparameters in ideal simulated environments to maximize cooperative performance. However, policies tuned for cooperation often fail to maintain robustness and resilience under real-world uncertainties. Building trustworthy MARL systems requires a deep understanding of robustness, which ensures stability under uncertainties, and resilience, the ability to recover from disruptions--a concept extensively …

Bridging Engineering and AI Planning through Model-Based Knowledge Transformation for the Validation of Automated Production System Variants
Hamied Nabizada, Lasse Beers, Alain Chahine, Felix Gehlhoff, Oliver Niggemann, Alexander Fay
https://arxiv.org/abs/2509.12091

Bridging Engineering and AI Planning through Model-Based Knowledge Transformation for the Validation of Automated Production System Variants
Engineering models created in Model-Based Systems Engineering (MBSE) environments contain detailed information about system structure and behavior. However, they typically lack symbolic planning semantics such as preconditions, effects, and constraints related to resource availability and timing. This limits their ability to evaluate whether a given system variant can fulfill specific tasks and how efficiently it performs compared to alternatives. To address this gap, this paper presents a mo…

Origin of Enhanced Thermal Resistance Near Nanoscale Hotspots: Insights from Full-Dispersion-Resolved Phonon Transport in Silicon
Jae Sik Jin
https://arxiv.org/abs/2510.12530 ht…

Origin of Enhanced Thermal Resistance Near Nanoscale Hotspots: Insights from Full-Dispersion-Resolved Phonon Transport in Silicon
Phonon transport near nanoscale hotspots (NHs) critically determines heat dissipation in advanced electronic devices. The prevailing understanding is that the enhanced thermal resistance (TR) observed in NHs originates from long mean free path (MFP) phonons, whose MFPs are much larger than the hotspot size, thereby limiting their ability to recognize hotspots and transport heat effectively. In this study, we revisit this problem by employing the Boltzmann transport equation (BTE) with a full ph…

PRoH: Dynamic Planning and Reasoning over Knowledge Hypergraphs for Retrieval-Augmented Generation
Xiangjun Zai, Xingyu Tan, Xiaoyang Wang, Qing Liu, Xiwei Xu, Wenjie Zhang
https://arxiv.org/abs/2510.12434

PRoH: Dynamic Planning and Reasoning over Knowledge Hypergraphs for Retrieval-Augmented Generation
Knowledge Hypergraphs (KHs) have recently emerged as a knowledge representation for retrieval-augmented generation (RAG), offering a paradigm to model multi-entity relations into a structured form. However, existing KH-based RAG methods suffer from three major limitations: static retrieval planning, non-adaptive retrieval execution, and superficial use of KH structure and semantics, which constrain their ability to perform effective multi-hop question answering. To overcome these limitations, w…

A silent ocean pandemic is wiping out sea urchins worldwide #ocean

A silent ocean pandemic is wiping out sea urchins worldwide
A sudden, unexplained mass die-off is decimating sea urchins around the world, including catastrophic losses in the Canary Islands. Key reef-grazing species are reaching historic lows, and their ability to reproduce has nearly halted in some regions. Scientists suspect a pathogen but haven’t yet confirmed the culprit. The fate of these reefs may hinge on solving this unfolding pandemic.

🥫 Artificial proteins offer new path for fast, sustainable and biocompatible energy storage devices
https://techxplore.com/news/2025-11-artificial-proteins-path-fast-sustainable.html

Artificial proteins offer new path for fast, sustainable and biocompatible energy storage devices
Researchers have managed to modify a class of proteins to give them the ability to transport and store electricity. These proteins can be used to create sustainable, efficient and biocompatible conducting materials. These materials are highly stable and easy to process, which means they can be incorporated into industrial processes.

Embodied Navigation Foundation Model
Jiazhao Zhang, Anqi Li, Yunpeng Qi, Minghan Li, Jiahang Liu, Shaoan Wang, Haoran Liu, Gengze Zhou, Yuze Wu, Xingxing Li, Yuxin Fan, Wenjun Li, Zhibo Chen, Fei Gao, Qi Wu, Zhizheng Zhang, He Wang
https://arxiv.org/abs/2509.12129

Embodied Navigation Foundation Model
Navigation is a fundamental capability in embodied AI, representing the intelligence required to perceive and interact within physical environments following language instructions. Despite significant progress in large Vision-Language Models (VLMs), which exhibit remarkable zero-shot performance on general vision-language tasks, their generalization ability in embodied navigation remains largely confined to narrow task settings and embodiment-specific architectures. In this work, we introduce a…

Anharmonic Effects in Ge2Sb2Te5 and Consequences on Thermodynamic Stability
Owain T. Beynon, Adham Hashibon
https://arxiv.org/abs/2510.12526 https://arxiv.…

Anharmonic Effects in Ge2Sb2Te5 and Consequences on Thermodynamic Stability
Chalcogenide materials are an important class of phase change material (PCMs) owing to their employment in digital memory solutions. Chalgogenide materials have applications in phase change random access memory (PCRAM) due to their ability to reversibly cycle between crystalline and amorphous states, and of these materials Ge2Sb2Te5 (GST) is of particular interest due to its speed, stability and low crystallisation temperatures. GST possesses two stable crystalline polymorphs, cubic and hexagon…

Growing Perspectives: Modelling Embodied Perspective Taking and Inner Narrative Development Using Large Language Models
Sabrina Patania, Luca Annese, Anna Lambiase, Anita Pellegrini, Tom Foulsham, Azzurra Ruggeri, Silvia Rossi, Silvia Serino, Dimitri Ognibene
https://arxiv.org/abs/2509.11868

Growing Perspectives: Modelling Embodied Perspective Taking and Inner Narrative Development Using Large Language Models
Language and embodied perspective taking are essential for human collaboration, yet few computational models address both simultaneously. This work investigates the PerspAct system [1], which integrates the ReAct (Reason and Act) paradigm with Large Language Models (LLMs) to simulate developmental stages of perspective taking, grounded in Selman's theory [2]. Using an extended director task, we evaluate GPT's ability to generate internal narratives aligned with specified developmental stages, a…

SVD-based ugmt-gft on directed product graphs
Guoyun Xie, Zhichao Zhang
https://arxiv.org/abs/2510.10532 https://arxiv.org/pdf/2510.10532

SVD-based ugmt-gft on directed product graphs
Traditional directed graph signal processing generally depends on fixed representation matrices, whose rigid structures limit the model's ability to adapt to complex graph topologies. To address this issue, this study employed the unified graph representation matrix (UGRM) to propose a generalized graph Fourier transform (UGRM-GFT) method based on singular value decomposition (SVD) for signal analysis on directed graphs and Cartesian product graphs. We defined UGRM-GFT for general directed grap…

Offline Reinforcement Learning with Generative Trajectory Policies
Xinsong Feng, Leshu Tang, Chenan Wang, Haipeng Chen
https://arxiv.org/abs/2510.11499 https://

Offline Reinforcement Learning with Generative Trajectory Policies
Generative models have emerged as a powerful class of policies for offline reinforcement learning (RL) due to their ability to capture complex, multi-modal behaviors. However, existing methods face a stark trade-off: slow, iterative models like diffusion policies are computationally expensive, while fast, single-step models like consistency policies often suffer from degraded performance. In this paper, we demonstrate that it is possible to bridge this gap. The key to moving beyond the limitati…

Bayesian Topological Convolutional Neural Nets
Sarah Harkins Dayton, Hayden Everett, Ioannis Schizas, David L. Boothe Jr., Vasileios Maroulas
https://arxiv.org/abs/2510.11704 ht…

Bayesian Topological Convolutional Neural Nets
Convolutional neural networks (CNNs) have been established as the main workhorse in image data processing; nonetheless, they require large amounts of data to train, often produce overconfident predictions, and frequently lack the ability to quantify the uncertainty of their predictions. To address these concerns, we propose a new Bayesian topological CNN that promotes a novel interplay between topology-aware learning and Bayesian sampling. Specifically, it utilizes information from important ma…

US supreme court hears arguments in case that tests Trump’s ability to fire officials
The Trump administration argues that the 90 year old precedent decision stopping president from removing officers must be overruled
Arguments in the case that will decide whether Donald Trump can fire officials from independent agencies have started.
First up is solicitor general D John Sauer, arguing on behalf of the Trump administration.
He kicks off his opening remarks by arguing …

VisualDAN: Exposing Vulnerabilities in VLMs with Visual-Driven DAN Commands
Aofan Liu, Lulu Tang
https://arxiv.org/abs/2510.09699 https://arxiv.org/pdf/251…

VisualDAN: Exposing Vulnerabilities in VLMs with Visual-Driven DAN Commands
Vision-Language Models (VLMs) have garnered significant attention for their remarkable ability to interpret and generate multimodal content. However, securing these models against jailbreak attacks continues to be a substantial challenge. Unlike text-only models, VLMs integrate additional modalities, introducing novel vulnerabilities such as image hijacking, which can manipulate the model into producing inappropriate or harmful responses. Drawing inspiration from text-based jailbreaks like the …

ODI-Bench: Can MLLMs Understand Immersive Omnidirectional Environments?
Liu Yang, Huiyu Duan, Ran Tao, Juntao Cheng, Sijing Wu, Yunhao Li, Jing Liu, Xiongkuo Min, Guangtao Zhai
https://arxiv.org/abs/2510.11549

ODI-Bench: Can MLLMs Understand Immersive Omnidirectional Environments?
Omnidirectional images (ODIs) provide full 360x180 view which are widely adopted in VR, AR and embodied intelligence applications. While multi-modal large language models (MLLMs) have demonstrated remarkable performance on conventional 2D image and video understanding benchmarks, their ability to comprehend the immersive environments captured by ODIs remains largely unexplored. To address this gap, we first present ODI-Bench, a novel comprehensive benchmark specifically designed for omnidirecti…

Hybrid Models for Natural Language Reasoning: The Case of Syllogistic Logic
Manuel Vargas Guzm\'an, Jakub Szymanik, Maciej Malicki
https://arxiv.org/abs/2510.09472 https://

Hybrid Models for Natural Language Reasoning: The Case of Syllogistic Logic
Despite the remarkable progress in neural models, their ability to generalize, a cornerstone for applications like logical reasoning, remains a critical challenge. We delineate two fundamental aspects of this ability: compositionality, the capacity to abstract atomic logical rules underlying complex inferences, and recursiveness, the aptitude to build intricate representations through iterative application of inference rules. In the literature, these two aspects are often confounded together un…

From <Answer> to <Think>: Multidimensional Supervision of Reasoning Process for LLM Optimization
Beining Wang, Weihang Su, Hongtao Tian, Tao Yang, Yujia Zhou, Ting Yao, Qingyao Ai, Yiqun Liu
https://arxiv.org/abs/2510.11457

From to : Multidimensional Supervision of Reasoning Process for LLM Optimization
Improving the multi-step reasoning ability of Large Language Models (LLMs) is a critical yet challenging task. The dominant paradigm, outcome-supervised reinforcement learning (RLVR), rewards only correct final answers, often propagating flawed reasoning and suffering from sparse reward signals. While process-level reward models (PRMs) provide denser, step-by-step feedback, they lack generalizability and interpretability, requiring task-specific segmentation of the reasoning process. To this en…

InteractScience: Programmatic and Visually-Grounded Evaluation of Interactive Scientific Demonstration Code Generation
Qiaosheng Chen, Yang Liu, Lei Li, Kai Chen, Qipeng Guo, Gong Cheng, Fei Yuan
https://arxiv.org/abs/2510.09724

InteractScience: Programmatic and Visually-Grounded Evaluation of Interactive Scientific Demonstration Code Generation
Large Language Models (LLMs) are increasingly capable of generating complete applications from natural language instructions, creating new opportunities in science and education. In these domains, interactive scientific demonstrations are particularly valuable for explaining concepts, supporting new teaching methods, and presenting research findings. Generating such demonstrations requires models to combine accurate scientific knowledge with the ability to implement interactive front-end code t…

Donald Trump on Wednesday further inserted himself into the drama around the sale of Warner Bros. Discovery,
saying he believes CNN
— one of several cable networks owned by WBD
— should be sold as part of any deal.
While the president doesn't have the power to unilaterally block a merger he doesn't like
— unless there are serious national security concerns pertaining to foreign investments
— his comments do have the ability to sway the decisions of…

Trump says CNN "should be sold" as part of WBD deal
The president said it was "imperative" that CNN gets a new owner in any transaction.

Mask Tokens as Prophet: Fine-Grained Cache Eviction for Efficient dLLM Inference
Jianuo Huang, Yaojie Zhang, Yicun Yang, Benhao Huang, Biqing Qi, Dongrui Liu, Linfeng Zhang
https://arxiv.org/abs/2510.09309

Mask Tokens as Prophet: Fine-Grained Cache Eviction for Efficient dLLM Inference
Diffusion large language models (dLLMs) present a promising alternative to dominant autoregressive models (ARMs) by the ability of parallel decoding at the expense of substantial computation and memory costs. Specifically, the cache mechanism for bidirectional attention in dLLMs demands large memory footprint, restricting their ability to handle long contexts under resource-limited settings. Existing cache eviction strategies are designed for ARMs and ignore the unique characteristics of dLLMs,…

FM-IRL: Flow-Matching for Reward Modeling and Policy Regularization in Reinforcement Learning
Zhenglin Wan, Jingxuan Wu, Xingrui Yu, Chubin Zhang, Mingcong Lei, Bo An, Ivor Tsang
https://arxiv.org/abs/2510.09222

FM-IRL: Flow-Matching for Reward Modeling and Policy Regularization in Reinforcement Learning
Flow Matching (FM) has shown remarkable ability in modeling complex distributions and achieves strong performance in offline imitation learning for cloning expert behaviors. However, despite its behavioral cloning expressiveness, FM-based policies are inherently limited by their lack of environmental interaction and exploration. This leads to poor generalization in unseen scenarios beyond the expert demonstrations, underscoring the necessity of online interaction with environment. Unfortunately…

Ego-Vision World Model for Humanoid Contact Planning
Hang Liu, Yuman Gao, Sangli Teng, Yufeng Chi, Yakun Sophia Shao, Zhongyu Li, Maani Ghaffari, Koushil Sreenath
https://arxiv.org/abs/2510.11682

Ego-Vision World Model for Humanoid Contact Planning
Enabling humanoid robots to exploit physical contact, rather than simply avoid collisions, is crucial for autonomy in unstructured environments. Traditional optimization-based planners struggle with contact complexity, while on-policy reinforcement learning (RL) is sample-inefficient and has limited multi-task ability. We propose a framework combining a learned world model with sampling-based Model Predictive Control (MPC), trained on a demonstration-free offline dataset to predict future outco…

PhysToolBench: Benchmarking Physical Tool Understanding for MLLMs
Zixin Zhang, Kanghao Chen, Xingwang Lin, Lutao Jiang, Xu Zheng, Yuanhuiyi Lyu, Litao Guo, Yinchuan Li, Ying-Cong Chen
https://arxiv.org/abs/2510.09507

PhysToolBench: Benchmarking Physical Tool Understanding for MLLMs
The ability to use, understand, and create tools is a hallmark of human intelligence, enabling sophisticated interaction with the physical world. For any general-purpose intelligent agent to achieve true versatility, it must also master these fundamental skills. While modern Multimodal Large Language Models (MLLMs) leverage their extensive common knowledge for high-level planning in embodied AI and in downstream Vision-Language-Action (VLA) models, the extent of their true understanding of phys…

MAGA media
is flexing its ability to
shape the debate over antifa and violent crime in American cities,
-- empowered by allies in the White House
hungry for evidence of left-wing terrorism.
The Trump administration is using clips of violent street clashes
— paired with testimony from MAGA-aligned reporters on the ground
— to falsely depict Democratic-led cities as engulfed in chaos.

MAGA media wages asymmetric warfare on antifa
MAGA-aligned journalists frame their coverage as exposing the "truth" mainstream outlets ignore.

Enhancing Long Chain-of-Thought Reasoning through Multi-Path Plan Aggregation
Siheng Xiong, Ali Payani, Faramarz Fekri
https://arxiv.org/abs/2510.11620 https://

Enhancing Long Chain-of-Thought Reasoning through Multi-Path Plan Aggregation
Inference-time scaling enhances the reasoning ability of a language model (LM) by extending its chain-of-thought (CoT). However, existing approaches typically generate the entire reasoning chain in a single forward pass, which often leads to CoT derailment, i.e., the reasoning trajectory drifting off course due to compounding errors. This problem is particularly severe for smaller LMs with long CoTs due to their limited capacity. To address this, we analyze raw long CoTs and uncover a reasoning…

OMB head Russ Vought says
Reductions in Force have begun.
In litigation challenging OMB's ability to RIF during a shutdown,
OMB must provide more details by 3pm PT/ 6pm ET.
https://storage.courtlistener.com/recap/go…

KnowRL: Teaching Language Models to Know What They Know
Sahil Kale, Devendra Singh Dhami
https://arxiv.org/abs/2510.11407 https://arxiv.org/pdf/2510.11407

KnowRL: Teaching Language Models to Know What They Know
Truly reliable AI requires more than simply scaling up knowledge; it demands the ability to know what it knows and when it does not. Yet recent research shows that even the best LLMs misjudge their own competence in more than one in five cases, making any response born of such internal uncertainty impossible to fully trust. Inspired by self-improvement reinforcement learning techniques that require minimal data, we present a simple but powerful framework KnowRL that strengthens a model's intern…

Demystifying Reinforcement Learning in Agentic Reasoning
Zhaochen Yu, Ling Yang, Jiaru Zou, Shuicheng Yan, Mengdi Wang
https://arxiv.org/abs/2510.11701 https://

Demystifying Reinforcement Learning in Agentic Reasoning
Recently, the emergence of agentic RL has showcased that RL could also effectively improve the agentic reasoning ability of LLMs, yet the key design principles and optimal practices remain unclear. In this work, we conduct a comprehensive and systematic investigation to demystify reinforcement learning in agentic reasoning from three key perspectives: data, algorithm, and reasoning mode. We highlight our key insights: (i) Replacing stitched synthetic trajectories with real end-to-end tool-use t…

LLMAtKGE: Large Language Models as Explainable Attackers against Knowledge Graph Embeddings
Ting Li, Yang Yang, Yipeng Yu, Liang Yao, Guoqing Chao, Ruifeng Xu
https://arxiv.org/abs/2510.11584

LLMAtKGE: Large Language Models as Explainable Attackers against Knowledge Graph Embeddings
Adversarial attacks on knowledge graph embeddings (KGE) aim to disrupt the model's ability of link prediction by removing or inserting triples. A recent black-box method has attempted to incorporate textual and structural information to enhance attack performance. However, it is unable to generate human-readable explanations, and exhibits poor generalizability. In the past few years, large language models (LLMs) have demonstrated powerful capabilities in text comprehension, generation, and reas…

Investigating Large Language Models' Linguistic Abilities for Text Preprocessing
Marco Braga, Gian Carlo Milanese, Gabriella Pasi
https://arxiv.org/abs/2510.11482 https://…

Investigating Large Language Models' Linguistic Abilities for Text Preprocessing
Text preprocessing is a fundamental component of Natural Language Processing, involving techniques such as stopword removal, stemming, and lemmatization to prepare text as input for further processing and analysis. Despite the context-dependent nature of the above techniques, traditional methods usually ignore contextual information. In this paper, we investigate the idea of using Large Language Models (LLMs) to perform various preprocessing tasks, due to their ability to take context into acco…