Tootfinder

Opt-in global Mastodon full text search. Join the index!

@Techmeme@techhub.social
2025-11-21 23:55:59

Analyzing Gemini 3's model card and safety framework report: the model is excellent but the safety report withholds or makes it difficult to understand key info (Zvi Mowshowitz/Don't Worry About the Vase)
thezvi.substack.com/p/gemini-3

Gemini 3: Model Card and Safety Framework Report
Gemini 3 Pro is an excellent model, sir.

@frankel@mastodon.top
2025-11-19 09:30:06

#SpringFramework 7.0 Release Notes
github.com/spring-projects/spr

Spring Framework 7.0 Release Notes
Spring Framework. Contribute to spring-projects/spring-framework development by creating an account on GitHub.

@kubikpixel@chaos.social
2025-09-22 05:05:10

Cross-Plattform-Applikationen mit Rust 1: Langlebig und flexibel
Die plattformübergreifende Entwicklung ohne Framework hat einige Vorteile, und die Programmiersprache Rust eignet sich gut für die Umsetzung.
🦀 heise.de/hintergrund/Cr…

Cross-Plattform-Applikationen mit Rust 1: Langlebig und flexibel
Die plattformübergreifende Entwicklung ohne Framework hat einige Vorteile, und die Programmiersprache Rust eignet sich gut für die Umsetzung.

@portaloffreedom@social.linux.pizza
2025-10-21 11:16:25
Content warning: Framework, politics

I don't think at framework they are racists or transphobes or xenophobes or fascists in general.
I think it's just a living example of the parable of the Nazi bar. They might not believe in it, but that does not change that they are going in that direction.
I wonder how the work culture will be influenced by this. Will people leave and will they hire more white supremacists as a replacement?

@seeingwithsound@mas.to
2025-11-21 22:33:24

A low-latency neural inference framework for real-time handwriting recognition from #EEG signals on an edge device nature.com/articles/s41598-025

A low-latency neural inference framework for real-time handwriting recognition from EEG signals on an edge device - Scientific Reports
Brain–computer interfaces (BCIs) hold significant promise for restoring communication in individuals with severe motor or speech impairments. Imagined handwriting, as a form of motor imagery, offers an intuitive paradigm for character-level neural decoding. While invasive techniques such as electrocorticography (ECoG) offer high decoding accuracy, their surgical requirements pose clinical risks and hinder scalability. Non-invasive alternatives like electroencephalography (EEG) are safer and m…

@TFG@social.linux.pizza
2025-10-20 11:04:59

trying to install .NET Framework 3.5 with offline installer file to run suspect software in test environment.
Windows: This App requires .NET Framework 3.5
-.-
it's monday again, isn't it?
#dfir #forensics

@cdamian@rls.social
2025-11-17 09:49:16

My Framework for Technical Debt
I've mentioned my approach to technical debt often, but I've never actually written it down. Here's the framework I use.
christof.damian.net/2025/11/my

My Framework for Technical Debt
I've mentioned my approach to technical debt often, but I've never actually written it down. Here's the framework I use.  Technical debt is ...

@netzschleuder@social.skewed.de
2025-10-22 05:00:04

jdk: Java SE Dev Kit dependencies (1.6.0.7)
A network of class dependencies within the JDK (Java SE Development Kit) 1.6.0.7 framework. Nodes represent classes and a directed edge indicates a dependency of one class on another.
This network has 6434 nodes and 150985 edges.
Tags: Technological, Software, Unweighted, Multigraph

jdk: Java SE Dev Kit dependencies (1.6.0.7). 6434 nodes, 150985 edges. https://networks.skewed.de/net/jdk

jdk — Java SE Dev Kit dependencies (1.6.0.7)
A network of class dependencies within the JDK (Java SE Development Kit) 1.6.0.7 framework. Nodes represent classes and a directed edge indicates a dependency of one class on another.

@yaxu@post.lurk.org
2025-10-20 11:05:13

Back in March I got coronavirus and lost my framework laptop. Looking in tailscale the last time I used it was in the house and I didn't remember taking it anywhere else. I'd given up trying to find it, thinking someone must have just walked into the house and taken it or something. Then two days ago I was looking for my son's laptop and my wife found mine. It was on a table downstairs the whole time. For seven months !

@cdarwin@c.im
2025-12-20 02:47:59

Senator Marsha Blackburn said
“I look forward to introducing the
"TRUMP AMERICA AI Act"
in the new year to create one federal rulebook for AI
to protect children, creators, conservatives, and communities"
Combats the consistent pattern of bias against conservative figures demonstrated by Big Tech and AI systems by requiring:
Audits of high-risk AI systems to undergo regular bias evaluations to prevent discrimination based on protected characte…

Blackburn Unveils National Policy Framework for Artificial Intelligence

@pre@boing.world
2025-10-21 15:40:49

More framework added. Dresser shelf/draws and the closet taking some shape.
The varnish/paint arrived and a test shows it way too dark. Almost black to my eyes in that dark room. So some other sample tins ordered. Hopefully one of them will be closer.

@Mediagazer@mstdn.social
2025-11-21 20:56:07

Business Insider joins Microsoft's Publisher Content Marketplace pilot, which compensates publishers when their content is used in AI-generated results (Barbara Peng/Business Insider)
businessinsider.com/announcing

Announcing our new AI partnership with Microsoft
This pilot creates a framework for a lasting, usage-based partnership between publishers and technology platforms to ensure quality content is credited and rewarded.

@steadystatemcr@mstdn.social
2025-10-21 17:15:59

It's good to see that GMCA has adopted a retrofit framework agreement that includes calculating embodied carbon.
As we showed in relation to GMCA's own Joint Development Plan, Places for Everyone, it's embodied carbon that's the big problem in building new homes etc. So at least try to make #retrofit and enetgy saving low carbon.
Taking a calculated risk: eliminating the …

@johl@mastodon.xyz
2025-10-11 11:21:24

A good blog post about the Framework/Omarchy/DHH situation. It’s just sad. And support for far-right people in Open Source projects should just not be a thing.
crimier.github.io/posts/Framew

Framework under fire for Omarchy/DHH/Hyprland support?
You might’ve noticed Framework, the laptop manufacturer, embroiled in a controversy as of now. The Discord server is on lockdown because the volunteer moderation team has gone on hiatus, and the Framework forum post about the controversy has been gaining unsightly amounts of steam from people disappointed at actions taken by Framework.

@Techmeme@techhub.social
2025-12-20 07:15:57

OpenAI introduces a framework to evaluate chain-of-thought monitorability and a suite of 13 evaluations designed to measure the monitorability of an AI system (OpenAI)
openai.com/index/evaluating-ch

@dawid@social.craftknight.com
2025-10-20 17:31:45
@… Check out Astro - it's also refreshing new framework, it can be static, but if needed can be just regular dynamic frontend if you change your mind after some time.

https://astro.build
@arXiv_csDC_bot@mastoxiv.page
2025-10-14 09:35:28

FIDRS: A Novel Framework for Integrated Distributed Reliable Systems
Mehdi Zekriyapanah Gashti
arxiv.org/abs/2510.10833 arxiv.org/pdf/2510.…

FIDRS: A Novel Framework for Integrated Distributed Reliable Systems
In this paper we represent a new framework for integrated distributed and reliable systems. In the proposed framework we have used three parts to increase Satisfaction and Performance of this framework. At first we analyze previous frameworks related to integrated systems, then represent new proposed framework in order to improving previous framework, and we discuss its different phases. Finally we compare the results of simulation of the new framework with previous ones. In FIDRS framework, th…

@chiraag@mastodon.online
2025-10-13 17:39:41

#Framework #Omarchy…

The Omarchy/Framework thing
I want to state for the record that I love Framework’s products. They are incredibly friendly to Linux, to Free Software, and to the Right to Repair movement. If their stated mission didn’t so closely align to my own values—and if they weren’t jeopardizing their reputation

@thomasfuchs@hachyderm.io
2025-10-14 15:05:35

Maybe Framework should concentrate on their products and not on platforming and sponsoring fascists bleepingcomputer.com/news/secu

@Techmeme@techhub.social
2025-10-20 16:40:52

LangChain, whose open-source framework connects AI apps to real-time data, raised a $125M Series B led by IVP at a $1.25B valuation (Sharon Goldman/Fortune)
fortune.com/2025/10/20/exclusi

Exclusive: Early AI darling LangChain is now a unicorn with a fresh $125 million in funding
With new funding led by IVP and a roster of enterprise customers, LangChain wants to power the coming wave of AI agents—and investors are betting it could be the next big infrastructure giant.

@arXiv_csCL_bot@mastoxiv.page
2025-10-15 10:43:11

COSTAR-A: A prompting framework for enhancing Large Language Model performance on Point-of-View questions
Nzubechukwu C. Ohalete (School of Data Science and Analytics, Kennesaw State University, GA, USA), Kevin B. Gittner (School of Data Science and Analytics, Kennesaw State University, GA, USA), Lauren M. Matheny (School of Data Science and Analytics, Kennesaw State University, GA, USA)

COSTAR-A: A prompting framework for enhancing Large Language Model performance on Point-of-View questions
Large Language Models (LLMs) are highly sensitive to prompt design, and making optimized prompting techniques is crucial for generating consistent, high-quality outputs. In this study, we introduce COSTAR-A, a novel prompt engineering framework that enhances the existing COSTAR method, which stands for Context, Objective, Style, Tone, Audience, and Response, by adding the 'Answer' component at the end. We demonstrate that while the original COSTAR framework improves prompt clarity and aligns ou…

@arXiv_csCR_bot@mastoxiv.page
2025-10-15 09:27:42

Elevating Medical Image Security: A Cryptographic Framework Integrating Hyperchaotic Map and GRU
Weixuan Li, Guang Yu, Quanjun Li, Junhua Zhou, Jiajun Chen, Yihang Dong, Mengqian Wang, Zimeng Li, Changwei Gong, Lin Tang, Xuhang Chen
arxiv.org/abs/2510.12084

Elevating Medical Image Security: A Cryptographic Framework Integrating Hyperchaotic Map and GRU
Chaotic systems play a key role in modern image encryption due to their sensitivity to initial conditions, ergodicity, and complex dynamics. However, many existing chaos-based encryption methods suffer from vulnerabilities, such as inadequate permutation and diffusion, and suboptimal pseudorandom properties. This paper presents Kun-IE, a novel encryption framework designed to address these issues. The framework features two key contributions: the development of the 2D Sin-Cos Pi Hyperchaotic Ma…

@gwire@mastodon.social
2025-12-16 11:39:53

To be fair, if you costed out hardware 9 months ago, you probably couldn't account for changes to technology prices influenced by a) AI companies b) US policies. The price of RAM alone will force adjustments.
theregister.com/2025/12/16/ukg

UK.gov doubles hardware spending framework to £24B in 6 months
: Massive procurement deal for laptops, software and services comes after minister vows to squeeze better value from big vendors

@gedankenstuecke@scholar.social
2025-10-11 23:09:17

«The “big tent” claim, overlaid on with #Framework’s outstanding promotion of Omarchy, looks cartoonishly reckless in this light. People don’t want this for Framework, and they’re cautious to distance themselves because they’ve seen other projects claim to be a “big tent”, only for the tent to catch on fire, melt, and shrink under everyone’s feet, because nobody used a fire extinguisher when it was early enough to do so.»
Great summary of this clusterfuck by @…
crimier.github.io/posts/Framew

@bici@mastodon.social
2025-10-19 22:22:02

About a year and a half ago, with the release of macOS 14 Sonoma, #Apple killed third-party Mail plugins. Apple did offer an alternative framework called extensions, but extensions can’t do all the things plugins once could.
I miss MailSuite!!
ASSHATS! #enshitification

@ubuntourist@mastodon.social
2025-12-19 16:26:06

Nutri3D Project - nutritional plant-based 3D printed food
media.enea.it/en/press-release

Food: ENEA prints in 3D, from multilayer snack bars to "honey pearls"
ENEA is developing sustainable, 3D-printed foods that are nutrient-rich and potentially customizable to individual needs. These results were achieved within the framework of the NUTRI3D project , carried out by ENEA in collaboration with Rigoni di Asiago, EltHub (project coordinator), and with the support of CREA – Food and Nutrition Research Center.

@arXiv_csCV_bot@mastoxiv.page
2025-10-15 07:59:31

Task-Specific Dual-Model Framework for Comprehensive Traffic Safety Video Description and Analysis
Blessing Agyei Kyem, Neema Jakisa Owor, Andrews Danyo, Joshua Kofi Asamoah, Eugene Denteh, Tanner Muturi, Anthony Dontoh, Yaw Adu-Gyamfi, Armstrong Aboah
arxiv.org/abs/2510.11907

Task-Specific Dual-Model Framework for Comprehensive Traffic Safety Video Description and Analysis
Traffic safety analysis requires complex video understanding to capture fine-grained behavioral patterns and generate comprehensive descriptions for accident prevention. In this work, we present a unique dual-model framework that strategically utilizes the complementary strengths of VideoLLaMA and Qwen2.5-VL through task-specific optimization to address this issue. The core insight behind our approach is that separating training for captioning and visual question answering (VQA) tasks minimizes…

@arXiv_csAI_bot@mastoxiv.page
2025-10-15 09:40:51

ResearStudio: A Human-Intervenable Framework for Building Controllable Deep-Research Agents
Linyi Yang, Yixuan Weng
arxiv.org/abs/2510.12194

ResearStudio: A Human-Intervenable Framework for Building Controllable Deep-Research Agents
Current deep-research agents run in a ''fire-and-forget'' mode: once started, they give users no way to fix errors or add expert knowledge during execution. We present ResearStudio, the first open-source framework that places real-time human control at its core. The system follows a Collaborative Workshop design. A hierarchical Planner-Executor writes every step to a live ''plan-as-document,'' a fast communication layer streams each action, file change, and tool call to a web interface. At any …

@arXiv_mathOC_bot@mastoxiv.page
2025-10-15 09:38:41

A Gradient Guided Diffusion Framework for Chance Constrained Programming
Boyang Zhang, Zhiguo Wang, Ya-Feng Liu
arxiv.org/abs/2510.12238 ar…

A Gradient Guided Diffusion Framework for Chance Constrained Programming
Chance constrained programming (CCP) is a powerful framework for addressing optimization problems under uncertainty. In this paper, we introduce a novel Gradient-Guided Diffusion-based Optimization framework, termed GGDOpt, which tackles CCP through three key innovations. First, GGDOpt accommodates a broad class of CCP problems without requiring the knowledge of the exact distribution of uncertainty-relying solely on a set of samples. Second, to address the nonconvexity of the chance constraint…

@UP8@mastodon.social
2025-10-08 16:22:05

📷 Two-stage framework reconstructs sharp 4D scenes from blurry handheld videos
#imaging

Two-stage framework reconstructs sharp 4D scenes from blurry handheld videos
Neural Radiance Fields (NeRF) is a fascinating technique that creates three-dimensional (3D) representations of a scene from a set of two-dimensional (2D) images, captured from different angles. It works by training a deep neural network to predict the color and density at any point in 3D space.

@adulau@infosec.exchange
2025-12-17 12:09:00

Why it matters to create and maintain open-source infrastructure for security monitoring including collection of forums and malicious communication channels.
This is a strong example (Google dark web report is discontinued) of the risks of relying solely on commercial vendors. If a capability does not align with their business interests or generate sufficient revenue, it can be discontinued at any time. Open-source infrastructure helps ensure continuity, transparency, and long-term ac…

AIL Project
AIL Project is an open source framework to collect, crawl, dig and analyse unstructured data.

@heiseonline@social.heise.de
2025-12-12 13:18:00

heise | heise Update voim 12. Dezember 2025: Lesetipps fürs Wochenende
Der wöchentliche Newsletter von heise mit einem Ratgeber zu PC-Komponenten, Notebook: Framework 12, In-Ear-Kopfhörer, Hybridheizungen, NIS2-Umsetzungsgesetz

heise+ Update voim 12. Dezember 2025: Lesetipps fürs Wochenende
Der wöchentliche Newsletter von heise+ mit einem Ratgeber zu PC-Komponenten, Notebook: Framework 12, In-Ear-Kopfhörer, Hybridheizungen, NIS2-Umsetzungsgesetz

@arXiv_csLG_bot@mastoxiv.page
2025-10-14 13:39:38

Ontolearn-A Framework for Large-scale OWL Class Expression Learning in Python
Caglar Demir, Alkid Baci, N'Dah Jean Kouagou, Leonie Nora Sieger, Stefan Heindorf, Simon Bin, Lukas Bl\"ubaum, Alexander Bigerl, Axel-Cyrille Ngonga Ngomo
arxiv.org/abs/2510.11561

Ontolearn-A Framework for Large-scale OWL Class Expression Learning in Python
In this paper, we present Ontolearn-a framework for learning OWL class expressions over large knowledge graphs. Ontolearn contains efficient implementations of recent stateof-the-art symbolic and neuro-symbolic class expression learners including EvoLearner and DRILL. A learned OWL class expression can be used to classify instances in the knowledge graph. Furthermore, Ontolearn integrates a verbalization module based on an LLM to translate complex OWL class expressions into natural language sen…

@arXiv_quantph_bot@mastoxiv.page
2025-10-13 10:01:20

A Framework for Distributed Resource Allocation in Quantum Networks
Nitish K. Panigrahy, Leonardo Bacciottini, C. V. Hollot, Emily A. Van Milligen, Matheus Guedes de Andrade, Nageswara S. V. Rao, Gayane Vardoyan, Don Towsley
arxiv.org/abs/2510.09371

A Framework for Distributed Resource Allocation in Quantum Networks
We introduce a distributed resource allocation framework for the Quantum Internet that relies on feedback-based, fully decentralized coordination to serve multiple co-existing applications. We develop quantum network control algorithms under the mathematical framework of Quantum Network Utility Maximization (QNUM), where utility functions quantify network performance by mapping entanglement rate and quality into a joint optimization objective. We then introduce QPrimal-Dual, a decentralized, sc…

@memeorandum@universeodon.com
2025-12-13 03:31:05

TSA announces new labor framework on Jan. 11, 2026 (U.S. Department of Homeland Security ...)
tsa.gov/news/press/releases/20
memeorandum.com/251212/p130#a2

@arXiv_csSE_bot@mastoxiv.page
2025-10-15 09:00:21

DMAS-Forge: A Framework for Transparent Deployment of AI Applications as Distributed Systems
Alessandro Cornacchia, Vaastav Anand, Muhammad Bilal, Zafar Qazi, Marco Canini
arxiv.org/abs/2510.11872

DMAS-Forge: A Framework for Transparent Deployment of AI Applications as Distributed Systems
Agentic AI applications increasingly rely on multiple agents with distinct roles, specialized tools, and access to memory layers to solve complex tasks -- closely resembling service-oriented architectures. Yet, in the rapid evolving landscape of programming frameworks and new protocols, deploying and testing AI agents as distributed systems remains a daunting and labor-intensive task. We present DMAS-Forge, a framework designed to close this gap. DMAS-Forge decouples application logic from spec…

@arXiv_csRO_bot@mastoxiv.page
2025-10-15 09:22:01

PolygMap: A Perceptive Locomotion Framework for Humanoid Robot Stair Climbing
Bingquan Li, Ning Wang, Tianwei Zhang, Zhicheng He, Yucong Wu
arxiv.org/abs/2510.12346

PolygMap: A Perceptive Locomotion Framework for Humanoid Robot Stair Climbing
Recently, biped robot walking technology has been significantly developed, mainly in the context of a bland walking scheme. To emulate human walking, robots need to step on the positions they see in unknown spaces accurately. In this paper, we present PolyMap, a perception-based locomotion planning framework for humanoid robots to climb stairs. Our core idea is to build a real-time polygonal staircase plane semantic map, followed by a footstep planar using these polygonal plane segments. These …

@arXiv_eessIV_bot@mastoxiv.page
2025-10-14 08:56:38

Towards Efficient 3D Gaussian Human Avatar Compression: A Prior-Guided Framework
Shanzhi Yin, Bolin Chen, Xinju Wu, Ru-Ling Liao, Jie Chen, Shiqi Wang, Yan Ye
arxiv.org/abs/2510.10492

Towards Efficient 3D Gaussian Human Avatar Compression: A Prior-Guided Framework
This paper proposes an efficient 3D avatar coding framework that leverages compact human priors and canonical-to-target transformation to enable high-quality 3D human avatar video compression at ultra-low bit rates. The framework begins by training a canonical Gaussian avatar using articulated splatting in a network-free manner, which serves as the foundation for avatar appearance modeling. Simultaneously, a human-prior template is employed to capture temporal body movements through compact par…

@newsie@darktundra.xyz
2025-12-12 17:23:48

Trump signs executive order on 'national framework' for AI regulation therecord.media/trump-executiv

Trump signs executive order on 'national framework' for AI regulation
Seeking to end a "patchwork" of state-level AI regulation, the president spelled out his administration's approach to letting companies "be free to innovate."

@arXiv_csHC_bot@mastoxiv.page
2025-10-14 08:23:08

PRAXA: A Framework for What-If Analysis
Sneha Gathani, Kevin Li, Raghav Thind, Sirui Zeng, Matthew Xu, Peter J. Haas, Cagatay Demiralp, Zhicheng Liu
arxiv.org/abs/2510.09791

PRAXA: A Framework for What-If Analysis
Various analytical techniques-such as scenario modeling, sensitivity analysis, perturbation-based analysis, counterfactual analysis, and parameter space analysis-are used across domains to explore hypothetical scenarios, examine input-output relationships, and identify pathways to desired results. Although termed differently, these methods share common concepts and methods, suggesting unification under what-if analysis. Yet a unified framework to define motivations, core components, and its dis…

@arXiv_qbioQM_bot@mastoxiv.page
2025-10-14 08:58:48

SeFEF: A Seizure Forecasting Evaluation Framework
Ana Sofia Carmo, Louren\c{c}o Abrunhosa Rodrigues, Ana Rita Peralta, Ana Fred, Carla Bentes, Hugo Pl\'acido da Silva
arxiv.org/abs/2510.11275

SeFEF: A Seizure Forecasting Evaluation Framework
The lack of standardization in seizure forecasting slows progress in the field and limits the clinical translation of forecasting models. In this work, we introduce a Python-based framework aimed at streamlining the development, assessment, and documentation of individualized seizure forecasting algorithms. The framework automates data labeling, cross-validation splitting, forecast post-processing, performance evaluation, and reporting. It supports various forecasting horizons and includes a …

@philip@mastodon.mallegolhansen.com
2025-10-15 04:21:13

I just finished working my way through @…’s TDD book.
The exercise of writing a test framework to run the tests driving the development of my test framework in Python was truly a joy to work through.
Code here in case anyone is curious:

@vform@openbiblio.social
2025-11-26 16:03:45

Find die #Framework-Notebooks ganz cool. Gut, private brauch ich auf lang absehbare Zeit keinen neuen und bei der Arbeit würden Preis und Support sicher "von der Stange" geschlagen, aber...
frame.work/de/de

Introducing the Framework Desktop and newest Framework Laptop 13
Choose between our latest Framework Laptop 13 powered by Ryzen™ AI 300 Series processors or our brand new Framework Desktop with Ryzen™ AI Max Series processors.

@arXiv_statME_bot@mastoxiv.page
2025-10-15 10:01:21

The $\alpha$--regression for compositional data: a unified framework for standard, spatially-lagged, and geographically-weighted regression models
Michail Tsagris
arxiv.org/abs/2510.12663

The $α$--regression for compositional data: a unified framework for standard, spatially-lagged, and geographically-weighted regression models
Compositional data-vectors of non--negative components summing to unity--frequently arise in scientific applications where covariates influence the relative proportions of components, yet traditional regression approaches struggle with the unit-sum constraint and zero values. This paper revisits the $α$--regression framework, which uses a flexible power transformation parameterized by $α$ to interpolate between raw data analysis and log-ratio methods, naturally handling zeros without imputati…

@thomasfuchs@hachyderm.io
2025-10-15 16:07:44

What I don't get is why does DHH even need so much funding and sponsorships for open source projects. Tens of thousands from framework, cloudflare and god knows who else.
When I made the (then) probably most popular JavaScript open source framework I got zero funding and sponsorship and was doing fine?
I'm not saying that people shouldn't get paid for work, but that dude is a fucking multi-millionaire who drives race cars as a hobby.

@arXiv_csIR_bot@mastoxiv.page
2025-10-14 11:59:08

FinVet: A Collaborative Framework of RAG and External Fact-Checking Agents for Financial Misinformation Detection
Daniel Berhane Araya, Duoduo Liao
arxiv.org/abs/2510.11654

FinVet: A Collaborative Framework of RAG and External Fact-Checking Agents for Financial Misinformation Detection
Financial markets face growing threats from misinformation that can trigger billions in losses in minutes. Most existing approaches lack transparency in their decision-making and provide limited attribution to credible sources. We introduce FinVet, a novel multi-agent framework that integrates two Retrieval-Augmented Generation (RAG) pipelines with external fact-checking through a confidence-weighted voting mechanism. FinVet employs adaptive three-tier processing that dynamically adjusts verifi…

@arXiv_csPL_bot@mastoxiv.page
2025-10-15 08:30:42

AwareCompiler: Agentic Context-Aware Compiler Optimization via a Synergistic Knowledge-Data Driven Framework
Hongyu Lin, Haolin Pan, Haoran Luo, Yuchen Li, Kaichun Yao, Libo Zhang, Mingjie Xing, Yanjun Wu
arxiv.org/abs/2510.11759

AwareCompiler: Agentic Context-Aware Compiler Optimization via a Synergistic Knowledge-Data Driven Framework
Compiler optimization is crucial for enhancing program performance by transforming the sequence of optimization passes while maintaining correctness. Despite the promising potential of large language models (LLMs)-based agent for software optimization, automating compiler optimization remains challenging due to: (1) semantic misalignment between abstract program representations and concrete optimization passes, (2) inefficient interaction mechanisms between agents and compiler environments, and…

@macandi@social.heise.de
2025-09-24 10:55:00

Neues Framework: Leitet iOS 26.1 Benachrichtigungen an Nicht-Apple-Uhren weiter?
Im Betacode des neuen Betriebssystems gibt es Hinweise darauf, dass Apple an einem neuen Benachrichtigungs-Framework arbeitet. Es kommt auf Wunsch der EU.

Benachrichtigungen und iOS 26.1: Größere Öffnung für Nicht-Apple-Watches geplant
Im Betacode des neuen Betriebssystems gibt es Hinweise darauf, dass Apple an einem neuen Benachrichtigungs-Framework arbeitet. Es kommt auf Wunsch der EU.

@arXiv_econEM_bot@mastoxiv.page
2025-10-14 08:43:48

Spatial and Temporal Boundaries in Difference-in-Differences: A Framework from Navier-Stokes Equation
Tatsuru Kikuchi
arxiv.org/abs/2510.11013

Spatial and Temporal Boundaries in Difference-in-Differences: A Framework from Navier-Stokes Equation
This paper develops a unified framework for identifying spatial and temporal boundaries of treatment effects in difference-in-differences designs. Starting from fundamental fluid dynamics equations (Navier-Stokes), we derive conditions under which treatment effects decay exponentially in space and time, enabling researchers to calculate explicit boundaries beyond which effects become undetectable. The framework encompasses both linear (pure diffusion) and nonlinear (advection-diffusion with che…

@arXiv_csNI_bot@mastoxiv.page
2025-10-15 08:18:52

GeoPipe: a Geo-distributed LLM Training Framework with enhanced Pipeline Parallelism in a Lossless RDMA-enabled Datacenter Optical Transport Network
Jun Dai, Xiaorun Wang, Kexiong Fang, Zheng Yang, Yuefeng Ji, Jiawei Zhang
arxiv.org/abs/2510.12064

GeoPipe: a Geo-distributed LLM Training Framework with enhanced Pipeline Parallelism in a Lossless RDMA-enabled Datacenter Optical Transport Network
The proliferation of Large Language Models (LLMs) with exponentially growing parameters is making cross-data center (DC) training an inevitable trend. However, viable strategies for extending single-DC training frameworks to multi-DC environments remain underdeveloped. We experimentally demonstrate, for the first time, a high-performance geo-distributed LLMs training framework across multiple DCs interconnected by a lossless, remote direct memory access (RDMA) enabled Datacenter Optical Transpo…

@cosmos4u@scicomm.xyz
2025-11-17 07:46:18

Is #AI really just dumb statistics? "Olympiad-level physics problem-solving presents a significant challenge for both humans and artificial intelligence (AI), as it requires a sophisticated integration of precise calculation, abstract reasoning, and a fundamental grasp of physical principles," says the (abstract of the) paper arxiv.org/abs/2511.10515: "The Chinese Physics Olympiad (CPhO), renowned for its complexity and depth, serves as an ideal and rigorous testbed for these advanced capabilities. In this paper, we introduce LOCA-R (LOgical Chain Augmentation for Reasoning), an improved version of the LOCA framework adapted for complex reasoning, and apply it to the CPhO 2025 theory examination. LOCA-R achieves a near-perfect score of 313 out of 320 points, solidly surpassing the highest-scoring human competitor and significantly outperforming all baseline methods." Oops ...?

@unchartedworlds@scicomm.xyz
2025-10-09 17:48:32
Content warning: on being political (re Framework computers)

To @…, and to a certain genre of supporter now grumbling about criticism:
The thing is, "not being political" is kind of a myth.
And even to the extent that that could be a thing, it doesn't extend to where you choose to put money, or whose work you choose to boost and promote.
What's happening today isn't a newly-political situation where no politics was before - it's people paying more attention to some choices which already carried political weight.
=
(For context, I like repairable things, and info about your computers has been in my bookmarks for a while, but I'm not a customer.)
#Framework #politics

@arXiv_eessSY_bot@mastoxiv.page
2025-10-14 10:32:38

Risk-Budgeted Control Framework for Balanced Performance and Safety in Autonomous Vehicles
Pei Yu Chang, Vishnu Renganathan, Qadeer Ahmed
arxiv.org/abs/2510.10442

Risk-Budgeted Control Framework for Balanced Performance and Safety in Autonomous Vehicles
This paper presents a risk-budgeted monitor with a control framework that certifies safety for autonomous driving. In this process, a sliding window is proposed to monitor for insufficient barrier residuals or nonzero tail risk, ensuring system safety. When the safety margin deteriorates, it triggers switching the safety constraint from a performance-based relaxed-control barrier function (R-CBF) to a conservative conditional value at risk (CVaR-CBF) to address the safety concern. This switchin…

@midtsveen@social.linux.pizza
2025-11-17 21:57:11

Syndicalist unions are fundamentally different from the bureaucratic trade unions that dominate today. Modern unions function as institutional frameworks that negotiate within capitalism, often acting to preserve the system rather than challenge it. They centralize power in hierarchical leadership, limit direct worker control, and prioritize legal contracts and state approval over genuine worker autonomy.
Syndicalism rejects this institutionalized framework. It refuses collective barga…

Illustration depicts a large fist rising from a crowd of workers holding tools. Factories with smokestacks in the background convey industrial power.
@arXiv_grqc_bot@mastoxiv.page
2025-10-14 11:03:48

Mass-Centered GCM Framework in Perturbations of Kerr(-Newman)
Allen Juntao Fang, Elena Giorgi, Jingbo Wan
arxiv.org/abs/2510.10811 arxiv.or…

Mass-Centered GCM Framework in Perturbations of Kerr(-Newman)
The nonlinear stability problem for black hole solutions of the Einstein equations critically depends on choosing an appropriate geometric gauge. In the vacuum setting, the use of Generally Covariant Modulated (GCM) spheres and hypersurfaces has played a central role in the proof of stability for slowly rotating Kerr spacetime. In this work, we develop an alternative GCM framework, that we call mass-centered, designed to overcome the breakdown of the standard GCM construction in the charged cas…

@arXiv_csDB_bot@mastoxiv.page
2025-10-14 07:39:51

The Hybrid Multimodal Graph Index (HMGI): A Comprehensive Framework for Integrated Relational and Vector Search
Joydeep Chandra, Satyam Kumar Navneet, Yong Zhang
arxiv.org/abs/2510.10123

The Hybrid Multimodal Graph Index (HMGI): A Comprehensive Framework for Integrated Relational and Vector Search
The proliferation of complex, multimodal datasets has exposed a critical gap between the capabilities of specialized vector databases and traditional graph databases. While vector databases excel at semantic similarity search, they lack the capacity for deep relational querying. Conversely, graph databases master complex traversals but are not natively optimized for high-dimensional vector search. This paper introduces the Hybrid Multimodal Graph Index (HMGI), a novel framework designed to brid…

@arXiv_statML_bot@mastoxiv.page
2025-10-15 10:17:51

Adapting Noise to Data: Generative Flows from 1D Processes
Jannis Chemseddine, Gregor Kornhardt, Richard Duong, Gabriele Steidl
arxiv.org/abs/2510.12636

Adapting Noise to Data: Generative Flows from 1D Processes
We introduce a general framework for constructing generative models using one-dimensional noising processes. Beyond diffusion processes, we outline examples that demonstrate the flexibility of our approach. Motivated by this, we propose a novel framework in which the 1D processes themselves are learnable, achieved by parameterizing the noise distribution through quantile functions that adapt to the data. Our construction integrates seamlessly with standard objectives, including Flow Matching an…

@arXiv_csCL_bot@mastoxiv.page
2025-10-14 13:15:08

Culturally-Aware Conversations: A Framework & Benchmark for LLMs
Shreya Havaldar, Sunny Rai, Young-Min Cho, Lyle Ungar
arxiv.org/abs/2510.11563

Culturally-Aware Conversations: A Framework & Benchmark for LLMs
Existing benchmarks that measure cultural adaptation in LLMs are misaligned with the actual challenges these models face when interacting with users from diverse cultural backgrounds. In this work, we introduce the first framework and benchmark designed to evaluate LLMs in realistic, multicultural conversational settings. Grounded in sociocultural theory, our framework formalizes how linguistic style - a key element of cultural communication - is shaped by situational, relational, and cultural …

@arXiv_csAI_bot@mastoxiv.page
2025-10-13 08:32:50

What Is Your Agent's GPA? A Framework for Evaluating Agent Goal-Plan-Action Alignment
Allison Sihan Jia, Daniel Huang, Nikhil Vytla, Nirvika Choudhury, John C Mitchell, Anupam Datta
arxiv.org/abs/2510.08847

What Is Your Agent's GPA? A Framework for Evaluating Agent Goal-Plan-Action Alignment
We introduce the Agent GPA (Goal-Plan-Action) framework: an evaluation paradigm based on an agent's operational loop of setting goals, devising plans, and executing actions. The framework includes five evaluation metrics: Goal Fulfillment, Logical Consistency, Execution Efficiency, Plan Quality, and Plan Adherence. Logical Consistency checks that an agent's actions are consistent with its prior actions. Execution Efficiency checks whether the agent executes in the most efficient way to achieve …

@arXiv_csCR_bot@mastoxiv.page
2025-10-14 11:39:28

A Scalable, Privacy-Preserving Decentralized Identity and Verifiable Data Sharing Framework based on Zero-Knowledge Proofs
Hui Yuan
arxiv.org/abs/2510.09715

A Scalable, Privacy-Preserving Decentralized Identity and Verifiable Data Sharing Framework based on Zero-Knowledge Proofs
With the proliferation of decentralized applications (DApps), the conflict between the transparency of blockchain technology and user data privacy has become increasingly prominent. While Decentralized Identity (DID) and Verifiable Credentials (VCs) provide a standardized framework for user data sovereignty, achieving trusted identity verification and data sharing without compromising privacy remains a significant challenge. This paper proposes a novel, comprehensive framework that integrates D…

@Techmeme@techhub.social
2025-12-17 14:50:38

a16z releases a nine-pillar AI policy framework for Congress, including restricting AI use for under-13s without parental consent and keeping a role for states (Punchbowl News)
punchbowl.news/article/tech/a1

Here are a16z’s ideas for Congress on AI
Andreessen Horowitz is laying out a framework on Wednesday that it wants Congress to take up for artificial intelligence.

@chiraag@mastodon.online
2025-10-10 22:52:46

community.frame.work/t/framewo

Framework supporting far-right racists?
The problem is that OSS (and especially FLOSS) is inherently political. The idea that we (and not some company controlled by billionaires) should have the final say over how we use our devices is political. The idea that software should be free to modify and transparent to users is political, as it puts control (and therefore power) in the hands of the users (rather than the company or organization making the software). The other, more specific problem here is that Framework made this politica…

@arXiv_csSE_bot@mastoxiv.page
2025-10-13 09:18:50

RA-Gen: A Controllable Code Generation Framework Using ReAct for Multi-Agent Task Execution
Aofan Liu, Haoxuan Li, Bin Wang, Ao Yang, Hui Li
arxiv.org/abs/2510.08665

RA-Gen: A Controllable Code Generation Framework Using ReAct for Multi-Agent Task Execution
Code generation models based on large language models (LLMs) have gained wide adoption, but challenges remain in ensuring safety, accuracy, and controllability, especially for complex tasks. Existing methods often lack dynamic integration of external tools, transparent reasoning, and user control over safety. To address these issues, we propose a controllable code generation framework utilizing the ReAct paradigm for multi-agent task execution. This framework is a multi-agent system designed to…

@arXiv_csCV_bot@mastoxiv.page
2025-10-13 10:32:20

Minkowski-MambaNet: A Point Cloud Framework with Selective State Space Models for Forest Biomass Quantification
Jinxiang Tu, Dayong Ren, Fei Shi, Zhenhong Jia, Yahong Ren, Jiwei Qin, Fang He
arxiv.org/abs/2510.09367

Minkowski-MambaNet: A Point Cloud Framework with Selective State Space Models for Forest Biomass Quantification
Accurate forest biomass quantification is vital for carbon cycle monitoring. While airborne LiDAR excels at capturing 3D forest structure, directly estimating woody volume and Aboveground Biomass (AGB) from point clouds is challenging due to difficulties in modeling long-range dependencies needed to distinguish trees.We propose Minkowski-MambaNet, a novel deep learning framework that directly estimates volume and AGB from raw LiDAR. Its key innovation is integrating the Mamba model's Selective …

@arXiv_csDC_bot@mastoxiv.page
2025-10-15 08:46:01

TALP-Pages: An easy-to-integrate continuous performance monitoring framework
Valentin Seitz, Jordy Trilaksono, Marta Garcia-Gasulla
arxiv.org/abs/2510.12436

TALP-Pages: An easy-to-integrate continuous performance monitoring framework
Ensuring good performance is a key aspect in the development of codes that target HPC machines. As these codes are under active development, the necessity to detect performance degradation early in the development process becomes apparent. In addition, having meaningful insight into application scaling behavior tightly coupled to the development workflow is helpful. In this paper, we introduce TALP-Pages, an easy-to-integrate framework that enables developers to get fast and in-repository feedb…

@arXiv_csRO_bot@mastoxiv.page
2025-10-14 12:39:18

ManiAgent: An Agentic Framework for General Robotic Manipulation
Yi Yang, Kefan Gu, Yuqing Wen, Hebei Li, Yucheng Zhao, Tiancai Wang, Xudong Liu
arxiv.org/abs/2510.11660

ManiAgent: An Agentic Framework for General Robotic Manipulation
While Vision-Language-Action (VLA) models have demonstrated impressive capabilities in robotic manipulation, their performance in complex reasoning and long-horizon task planning is limited by data scarcity and model capacity. To address this, we introduce ManiAgent, an agentic architecture for general manipulation tasks that achieves end-to-end output from task descriptions and environmental inputs to robotic manipulation actions. In this framework, multiple agents involve inter-agent communic…

@heiseonline@social.heise.de
2025-11-26 14:04:00

KI-Update kompakt: KI-Rechenzentren, Flux 2, KI-Framework MLX, OpenAI-Hardware
Das "KI-Update" liefert drei mal pro Woche eine Zusammenfassung der wichtigsten KI-Entwicklungen.

KI-Update kompakt: KI-Rechenzentren, Flux 2, KI-Framework MLX, OpenAI-Hardware
Das "KI-Update" liefert drei mal pro Woche eine Zusammenfassung der wichtigsten KI-Entwicklungen.

@arXiv_csHC_bot@mastoxiv.page
2025-10-14 11:09:38

Personalized Motion Guidance Framework for Athlete-Centric Coaching
Ryota Takamidoa, Chiharu Suzukia, Hiroki Nakamoto
arxiv.org/abs/2510.10496

Personalized Motion Guidance Framework for Athlete-Centric Coaching
A critical challenge in contemporary sports science lies in filling the gap between group-level insights derived from controlled hypothesis-driven experiments and the real-world need for personalized coaching tailored to individual athletes' unique movement patterns. This study developed a Personalized Motion Guidance Framework (PMGF) to enhance athletic performance by generating individualized motion-refinement guides using generative artificial intelligence techniques. PMGF leverages a vertic…

@arXiv_csLG_bot@mastoxiv.page
2025-10-15 10:46:41

Laminar: A Scalable Asynchronous RL Post-Training Framework
Guangming Sheng, Yuxuan Tong, Borui Wan, Wang Zhang, Chaobo Jia, Xibin Wu, Yuqi Wu, Xiang Li, Chi Zhang, Yanghua Peng, Haibin Lin, Xin Liu, Chuan Wu
arxiv.org/abs/2510.12633

Laminar: A Scalable Asynchronous RL Post-Training Framework
Reinforcement learning (RL) post-training for Large Language Models (LLMs) is now scaling to large clusters and running for extended durations to enhance model reasoning performance. However, the scalability of existing RL frameworks is limited, as extreme long-tail skewness in RL trajectory generation causes severe GPU underutilization. Current asynchronous RL systems attempt to mitigate this, but they rely on global weight synchronization between the actor and all rollouts, which creates a ri…

@arXiv_csAI_bot@mastoxiv.page
2025-10-15 10:07:31

O-Forge: An LLM Computer Algebra Framework for Asymptotic Analysis
Ayush Khaitan, Vijay Ganesh
arxiv.org/abs/2510.12350 arxiv.org/pdf/251…

O-Forge: An LLM + Computer Algebra Framework for Asymptotic Analysis
Large language models have recently demonstrated advanced capabilities in solving IMO and Putnam problems; yet their role in research mathematics has remained fairly limited. The key difficulty is verification: suggested proofs may look plausible, but cannot be trusted without rigorous checking. We present a framework, called LLM+CAS, and an associated tool, O-Forge, that couples frontier LLMs with a computer algebra systems (CAS) in an In-Context Symbolic Feedback loop to produce proofs that a…

@arXiv_csIR_bot@mastoxiv.page
2025-10-14 11:02:49

From Reasoning LLMs to BERT: A Two-Stage Distillation Framework for Search Relevance
Runze Xia, Yupeng Ji, Yuxi Zhou, Haodong Liu, Teng Zhang, Piji Li
arxiv.org/abs/2510.11056

From Reasoning LLMs to BERT: A Two-Stage Distillation Framework for Search Relevance
Query-service relevance prediction in e-commerce search systems faces strict latency requirements that prevent the direct application of Large Language Models (LLMs). To bridge this gap, we propose a two-stage reasoning distillation framework to transfer reasoning capabilities from a powerful teacher LLM to a lightweight, deployment-friendly student model. In the first stage, we address the limitations of general-purpose LLMs by constructing a domain-adapted teacher model. This is achieved thro…

@arXiv_quantph_bot@mastoxiv.page
2025-10-15 10:35:01

Thermodynamics of quantum processes: An operational framework for free energy and reversible athermality
Himanshu Badhani, Dhanuja G S, Siddhartha Das
arxiv.org/abs/2510.12790

Thermodynamics of quantum processes: An operational framework for free energy and reversible athermality
We explore the thermodynamics of quantum processes (quantum channels) by axiomatically introducing the free energy for channels, defined via the quantum relative entropy with an absolutely thermal channel whose fixed output is in equilibrium with a thermal reservoir. This definition finds strong support through its operational interpretations in designated quantum information and thermodynamic tasks. We construct a resource theory of athermality for quantum processes, where free operations are …

@arXiv_csCL_bot@mastoxiv.page
2025-10-14 13:10:18

GenCNER: A Generative Framework for Continual Named Entity Recognition
Yawen Yang, Fukun Ma, Shiao Meng, Aiwei Liu, Lijie Wen
arxiv.org/abs/2510.11444

GenCNER: A Generative Framework for Continual Named Entity Recognition
Traditional named entity recognition (NER) aims to identify text mentions into pre-defined entity types. Continual Named Entity Recognition (CNER) is introduced since entity categories are continuously increasing in various real-world scenarios. However, existing continual learning (CL) methods for NER face challenges of catastrophic forgetting and semantic shift of non-entity type. In this paper, we propose GenCNER, a simple but effective Generative framework for CNER to mitigate the above dra…

@Techmeme@techhub.social
2025-11-18 16:56:44

Microsoft launches Agent 365, a new framework to let businesses deploy and manage AI agents like human employees, with dashboards showing telemetry and alerts (Tom Warren/The Verge)
theverge.com/news/822035/micro

Microsoft Agent 365 lets businesses manage AI agents like they do people
Microsoft is building an agent factory that now has some important controls. Microsoft Agent 365 will let business control AI agents.

@arXiv_csCV_bot@mastoxiv.page
2025-10-13 10:27:10

RadioFlow: Efficient Radio Map Construction Framework with Flow Matching
Haozhe Jia, Wenshuo Chen, Xiucheng Wang, Nan Cheng, Hongbo Zhang, Kuimou Yu, Songning Lai, Nanjian Jia, Bowen Tian, Hongru Xiao, Yutao Yue
arxiv.org/abs/2510.09314

RadioFlow: Efficient Radio Map Construction Framework with Flow Matching
Accurate and real-time radio map (RM) generation is crucial for next-generation wireless systems, yet diffusion-based approaches often suffer from large model sizes, slow iterative denoising, and high inference latency, which hinder practical deployment. To overcome these limitations, we propose \textbf{RadioFlow}, a novel flow-matching-based generative framework that achieves high-fidelity RM generation through single-step efficient sampling. Unlike conventional diffusion models, RadioFlow lea…

@arXiv_csSE_bot@mastoxiv.page
2025-10-14 08:07:37

Agentic Property-Based Testing: Finding Bugs Across the Python Ecosystem
Muhammad Maaz, Liam DeVoe, Zac Hatfield-Dodds, Nicholas Carlini
arxiv.org/abs/2510.09907

Agentic Property-Based Testing: Finding Bugs Across the Python Ecosystem
Property-based testing (PBT) is a lightweight formal method, typically implemented as a randomized testing framework. Users specify the input domain for their test using combinators supplied by the PBT framework, and the expected properties or invariants as a unit-test function. The framework then searches for a counterexample, e.g. by generating inputs and calling the test function. In this work, we demonstrate an LLM-based agent which analyzes Python modules, infers function-specific and cros…

@arXiv_csRO_bot@mastoxiv.page
2025-10-13 10:03:40

Placeit! A Framework for Learning Robot Object Placement Skills
Amina Ferrad, Johann Huber, Fran\c{c}ois H\'el\'enon, Julien Gleyze, Mahdi Khoramshahi, St\'ephane Doncieux
arxiv.org/abs/2510.09267

Placeit! A Framework for Learning Robot Object Placement Skills
Robotics research has made significant strides in learning, yet mastering basic skills like object placement remains a fundamental challenge. A key bottleneck is the acquisition of large-scale, high-quality data, which is often a manual and laborious process. Inspired by Graspit!, a foundational work that used simulation to automatically generate dexterous grasp poses, we introduce Placeit!, an evolutionary-computation framework for generating valid placement positions for rigid objects. Placei…

@Techmeme@techhub.social
2025-11-18 23:31:36

Soumith Chintala, who co-created the PyTorch ML framework at Meta and left the company this month, has joined Mira Murati's Thinking Machines Lab (Pranav Dixit/Business Insider)
businessinsider.com/meta-soumi

A top Meta AI researcher has joined Mira Murati's hot new startup, Thinking Machines Lab
Thinking Machines Lab, led by Mira Murati, hires Meta AI veteran Soumith Chintala as it rapidly expands its team and prepares for major funding.

@chiraag@mastodon.online
2025-10-09 14:27:46

@… I will probably also post on the original thread when it reopens, but I just wanted to post my thoughts about this thread here as well: comm…

Framework supporting far-right racists?
So evidence and proof is the opinion of a known activist with specific political leanings? An activist that has said and done many controversial things as well, I might add.

@arXiv_csIR_bot@mastoxiv.page
2025-10-14 09:36:18

ZeroGR: A Generalizable and Scalable Framework for Zero-Shot Generative Retrieval
Weiwei Sun, Keyi Kong, Xinyu Ma, Shuaiqiang Wang, Dawei Yin, Maarten de Rijke, Zhaochun Ren, Yiming Yang
arxiv.org/abs/2510.10419

ZeroGR: A Generalizable and Scalable Framework for Zero-Shot Generative Retrieval
Generative retrieval (GR) reformulates information retrieval (IR) by framing it as the generation of document identifiers (docids), thereby enabling an end-to-end optimization and seamless integration with generative language models (LMs). Despite notable progress under supervised training, GR still struggles to generalize to zero-shot IR scenarios, which are prevalent in real-world applications. To tackle this challenge, we propose \textsc{ZeroGR}, a zero-shot generative retrieval framework th…

@arXiv_csAI_bot@mastoxiv.page
2025-10-13 10:02:20

Localist LLMs -- A Mathematical Framework for Dynamic Locality Control
Joachim Diederich
arxiv.org/abs/2510.09338 arxiv.org/pdf/2510.09338

Localist LLMs -- A Mathematical Framework for Dynamic Locality Control
We present a novel framework for training large language models with continuously adjustable internal representations that span the full spectrum from localist (interpretable, rule-based) to distributed (generalizable, efficient) encodings. The key innovation is a locality dial, a tunable parameter that dynamically controls the degree of localization during both training and inference without requiring model retraining. This is achieved through group sparsity penalties on attention mechanisms, …

@arXiv_csDC_bot@mastoxiv.page
2025-10-15 08:44:52

A Non-Intrusive Framework for Deferred Integration of Cloud Patterns in Energy-Efficient Data-Sharing Pipelines
Sepideh Masoudi, Mark Edward Michael Daly, Jannis Kiesel, Stefan Tai
arxiv.org/abs/2510.12354

A Non-Intrusive Framework for Deferred Integration of Cloud Patterns in Energy-Efficient Data-Sharing Pipelines
As data mesh architectures gain traction in federated environments, organizations are increasingly building consumer-specific data-sharing pipelines using modular, cloud-native transformation services. Prior work has shown that structuring these pipelines with reusable transformation stages enhances both scalability and energy efficiency. However, integrating traditional cloud design patterns into such pipelines poses a challenge: predefining and embedding patterns can compromise modularity, re…

@arXiv_csCR_bot@mastoxiv.page
2025-10-14 12:26:38

PACEbench: A Framework for Evaluating Practical AI Cyber-Exploitation Capabilities
Zicheng Liu, Lige Huang, Jie Zhang, Dongrui Liu, Yuan Tian, Jing Shao
arxiv.org/abs/2510.11688

PACEbench: A Framework for Evaluating Practical AI Cyber-Exploitation Capabilities
The increasing autonomy of Large Language Models (LLMs) necessitates a rigorous evaluation of their potential to aid in cyber offense. Existing benchmarks often lack real-world complexity and are thus unable to accurately assess LLMs' cybersecurity capabilities. To address this gap, we introduce PACEbench, a practical AI cyber-exploitation benchmark built on the principles of realistic vulnerability difficulty, environmental complexity, and cyber defenses. Specifically, PACEbench comprises four…

@arXiv_csCL_bot@mastoxiv.page
2025-10-15 10:33:31

DSAS: A Universal Plug-and-Play Framework for Attention Optimization in Multi-Document Question Answering
Jiakai Li, Rongzheng Wang, Yizhuo Ma, Shuang Liang, Guangchun Luo, Ke Qin
arxiv.org/abs/2510.12251

DSAS: A Universal Plug-and-Play Framework for Attention Optimization in Multi-Document Question Answering
While large language models (LLMs) show considerable promise across various fields, they have notable limitations in handling multi-document question answering (Multi-doc QA) tasks. The first challenge is long-range dependency modeling, where LLMs struggle to focus on key information in long texts, which weakens important semantic connections. Second, most LLMs suffer from the ''lost-in-the-middle'' issue, where they have difficulty processing information in the middle of long inputs. Current s…

@arXiv_csSE_bot@mastoxiv.page
2025-10-13 09:55:50

A Semantic Framework for Patient Digital Twins in Chronic Care
Amal Elgammal, Bernd J. Kr\"amer, Michael P. Papazoglou, Mira Raheem
arxiv.org/abs/2510.09134

A Semantic Framework for Patient Digital Twins in Chronic Care
Personalized chronic care requires the integration of multimodal health data to enable precise, adaptive, and preventive decision-making. Yet most current digital twin (DT) applications remain organ-specific or tied to isolated data types, lacking a unified and privacy-preserving foundation. This paper introduces the Patient Medical Digital Twin (PMDT), an ontology-driven in silico patient framework that integrates physiological, psychosocial, behavioral, and genomic information into a coherent…

@arXiv_csCV_bot@mastoxiv.page
2025-10-14 13:45:08

A Framework for Low-Effort Training Data Generation for Urban Semantic Segmentation
Denis Zavadski, Damjan Kal\v{s}an, Tim K\"uchler, Haebom Lee, Stefan Roth, Carsten Rother
arxiv.org/abs/2510.11567

A Framework for Low-Effort Training Data Generation for Urban Semantic Segmentation
Synthetic datasets are widely used for training urban scene recognition models, but even highly realistic renderings show a noticeable gap to real imagery. This gap is particularly pronounced when adapting to a specific target domain, such as Cityscapes, where differences in architecture, vegetation, object appearance, and camera characteristics limit downstream performance. Closing this gap with more detailed 3D modelling would require expensive asset and scene design, defeating the purpose of…

@arXiv_csIR_bot@mastoxiv.page
2025-10-14 11:12:18

DyKnow-RAG: Dynamic Knowledge Utilization Reinforcement Framework for Noisy Retrieval-Augmented Generation in E-commerce Search Relevance
Tingqiao Xu, Shaowei Yao, Chenhe Dong, Yiming Jin, Zerui Huang, Dan Ou, Haihong Tang
arxiv.org/abs/2510.11122

DyKnow-RAG: Dynamic Knowledge Utilization Reinforcement Framework for Noisy Retrieval-Augmented Generation in E-commerce Search Relevance
Accurately modeling query-item relevance drives e-commerce ranking, yet long-tail, knowledge-heavy, and fast-evolving queries exceed parametric LLM coverage. External context (reviews, attribute encyclopedias, UGC) can help but is noisy, and single-pass latency and cost forbid any clean-then-summarize step. The model must, per query, judge relevance and decide whether to use, partially use, or ignore the context. DyKnow-RAG is a dynamic noisy-RAG framework built on Group Relative Policy Optimiz…

@arXiv_csRO_bot@mastoxiv.page
2025-10-15 07:43:31

Translating Milli/Microrobots with A Value-Centered Readiness Framework
Hakan Ceylan, Edoardo Sinibaldi, Sanjay Misra, Pankaj J. Pasricha, Dietmar W. Hutmacher
arxiv.org/abs/2510.12090

Translating Milli/Microrobots with A Value-Centered Readiness Framework
Untethered mobile milli/microrobots hold transformative potential for interventional medicine by enabling more precise and entirely non-invasive diagnosis and therapy. Realizing this promise requires bridging the gap between groundbreaking laboratory demonstrations and successful clinical integration. Despite remarkable technical progress over the past two decades, most millirobots and microrobots remain confined to laboratory proof-of-concept demonstrations, with limited real-world feasibility…

@Techmeme@techhub.social
2025-11-14 12:30:51

India officially notifies its first data protection law to establish a framework for data processing, protection, and governance, including verifiable consent (The Economic Times)
economictimes.indiatimes.c…

India notifies its first data protection law to strengthen privacy, security
India has officially notified the Digital Personal Data Protection Rules, 2025, establishing a framework for data processing, protection, and governance. These rules, enforcing the Digital Personal Data Protection Act, 2023, introduce verifiable consent, breach notification mandates, and data retention limits. They aim to enhance individual control and foster safer digital ecosystems.

@arXiv_csAI_bot@mastoxiv.page
2025-10-15 09:43:41

GOAT: A Training Framework for Goal-Oriented Agent with Tools
Hyunji Min, Sangwon Jung, Junyoung Sung, Dosung Lee, Leekyeung Han, Paul Hongsuck Seo
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…

@arXiv_csSE_bot@mastoxiv.page
2025-10-15 08:57:02

Lingxi: Repository-Level Issue Resolution Framework Enhanced by Procedural Knowledge Guided Scaling
Xu Yang, Jiayuan Zhou, Michael Pacheco, Wenhan Zhu, Pengfei He, Shaowei Wang, Kui Liu, Ruiqi Pan
arxiv.org/abs/2510.11838

Lingxi: Repository-Level Issue Resolution Framework Enhanced by Procedural Knowledge Guided Scaling
Driven by the advancements of Large Language Models (LLMs), LLM-powered agents are making significant improvements in software engineering tasks, yet struggle with complex, repository-level issue resolution. Existing agent-based methods have two key limitations. First, they lack of procedural knowledge (i.e., how an issue is fixed step-by-step and rationales behind it) to learn and leverage for issue resolution. Second, they rely on massive computational power to blindly explore the solution sp…

@arXiv_csAI_bot@mastoxiv.page
2025-10-15 10:07:22

RAG-Anything: All-in-One RAG Framework
Zirui Guo, Xubin Ren, Lingrui Xu, Jiahao Zhang, Chao Huang
arxiv.org/abs/2510.12323 arxiv.org/pdf/25…

RAG-Anything: All-in-One RAG Framework
Retrieval-Augmented Generation (RAG) has emerged as a fundamental paradigm for expanding Large Language Models beyond their static training limitations. However, a critical misalignment exists between current RAG capabilities and real-world information environments. Modern knowledge repositories are inherently multimodal, containing rich combinations of textual content, visual elements, structured tables, and mathematical expressions. Yet existing RAG frameworks are limited to textual content, …

@arXiv_csCL_bot@mastoxiv.page
2025-10-15 10:38:41

SMEC: Rethinking Matryoshka Representation Learning for Retrieval Embedding Compression
Biao Zhang, Lixin Chen, Tong Liu, Bo Zheng
arxiv.org/abs/2510.12474

SMEC: Rethinking Matryoshka Representation Learning for Retrieval Embedding Compression
Large language models (LLMs) generate high-dimensional embeddings that capture rich semantic and syntactic information. However, high-dimensional embeddings exacerbate computational complexity and storage requirements, thereby hindering practical deployment. To address these challenges, we propose a novel training framework named Sequential Matryoshka Embedding Compression (SMEC). This framework introduces the Sequential Matryoshka Representation Learning(SMRL) method to mitigate gradient varia…

@arXiv_csRO_bot@mastoxiv.page
2025-10-15 09:50:11

Fast Visuomotor Policy for Robotic Manipulation
Jingkai Jia, Tong Yang, Xueyao Chen, Chenhuan Liu, Wenqiang Zhang
arxiv.org/abs/2510.12483 …

Fast Visuomotor Policy for Robotic Manipulation
We present a fast and effective policy framework for robotic manipulation, named Energy Policy, designed for high-frequency robotic tasks and resource-constrained systems. Unlike existing robotic policies, Energy Policy natively predicts multimodal actions in a single forward pass, enabling high-precision manipulation at high speed. The framework is built upon two core components. First, we adopt the energy score as the learning objective to facilitate multimodal action modeling. Second, we int…

@arXiv_csAI_bot@mastoxiv.page
2025-10-15 10:25:41

Ax-Prover: A Deep Reasoning Agentic Framework for Theorem Proving in Mathematics and Quantum Physics
Marco Del Tredici, Jacob McCarran, Benjamin Breen, Javier Aspuru Mijares, Weichen Winston Yin, Jacob M. Taylor, Frank Koppens, Dirk Englund
arxiv.org/abs/2510.12787

Ax-Prover: A Deep Reasoning Agentic Framework for Theorem Proving in Mathematics and Quantum Physics
We present Ax-Prover, a multi-agent system for automated theorem proving in Lean that can solve problems across diverse scientific domains and operate either autonomously or collaboratively with human experts. To achieve this, Ax-Prover approaches scientific problem solving through formal proof generation, a process that demands both creative reasoning and strict syntactic rigor. Ax-Prover meets this challenge by equipping Large Language Models (LLMs), which provide knowledge and reasoning, wit…

@arXiv_csRO_bot@mastoxiv.page
2025-10-15 10:04:41

Maximal Adaptation, Minimal Guidance: Permissive Reactive Robot Task Planning with Humans in the Loop
Oz Gitelson, Satya Prakash Nayak, Ritam Raha, Anne-Kathrin Schmuck
arxiv.org/abs/2510.12662

Maximal Adaptation, Minimal Guidance: Permissive Reactive Robot Task Planning with Humans in the Loop
We present a novel framework for human-robot \emph{logical} interaction that enables robots to reliably satisfy (infinite horizon) temporal logic tasks while effectively collaborating with humans who pursue independent and unknown tasks. The framework combines two key capabilities: (i) \emph{maximal adaptation} enables the robot to adjust its strategy \emph{online} to exploit human behavior for cooperation whenever possible, and (ii) \emph{minimal tunable feedback} enables the robot to request …

@arXiv_csAI_bot@mastoxiv.page
2025-10-15 10:09:51

MTOS: A LLM-Driven Multi-topic Opinion Simulation Framework for Exploring Echo Chamber Dynamics
Dingyi Zuo, Hongjie Zhang, Jie Ou, Chaosheng Feng, Shuwan Liu
arxiv.org/abs/2510.12423

MTOS: A LLM-Driven Multi-topic Opinion Simulation Framework for Exploring Echo Chamber Dynamics
The polarization of opinions, information segregation, and cognitive biases on social media have attracted significant academic attention. In real-world networks, information often spans multiple interrelated topics, posing challenges for opinion evolution and highlighting the need for frameworks that simulate interactions among topics. Existing studies based on large language models (LLMs) focus largely on single topics, limiting the capture of cognitive transfer in multi-topic, cross-domain c…

@arXiv_csAI_bot@mastoxiv.page
2025-10-15 09:48:41

MedKGEval: A Knowledge Graph-Based Multi-Turn Evaluation Framework for Open-Ended Patient Interactions with Clinical LLMs
Yuechun Yu, Han Ying, Haoan Jin, Wenjian Jiang, Dong Xian, Binghao Wang, Zhou Yang, Mengyue Wu
arxiv.org/abs/2510.12224

MedKGEval: A Knowledge Graph-Based Multi-Turn Evaluation Framework for Open-Ended Patient Interactions with Clinical LLMs
The reliable evaluation of large language models (LLMs) in medical applications remains an open challenge, particularly in capturing the complexity of multi-turn doctor-patient interactions that unfold in real clinical environments. Existing evaluation methods typically rely on post hoc review of full conversation transcripts, thereby neglecting the dynamic, context-sensitive nature of medical dialogues and the evolving informational needs of patients. In this work, we present MedKGEval, a nove…

@arXiv_csAI_bot@mastoxiv.page
2025-10-15 10:10:21

Biased-Attention Guided Risk Prediction for Safe Decision-Making at Unsignalized Intersections
Chengyang Dong, Nan Guo
arxiv.org/abs/2510.12428

Biased-Attention Guided Risk Prediction for Safe Decision-Making at Unsignalized Intersections
Autonomous driving decision-making at unsignalized intersections is highly challenging due to complex dynamic interactions and high conflict risks. To achieve proactive safety control, this paper proposes a deep reinforcement learning (DRL) decision-making framework integrated with a biased attention mechanism. The framework is built upon the Soft Actor-Critic (SAC) algorithm. Its core innovation lies in the use of biased attention to construct a traffic risk predictor. This predictor assesses …

@arXiv_csAI_bot@mastoxiv.page
2025-10-10 10:28:39

From Ethical Declarations to Provable Independence: An Ontology-Driven Optimal-Transport Framework for Certifiably Fair AI Systems
Sukriti Bhattacharya, Chitro Majumdar
arxiv.org/abs/2510.08086

From Ethical Declarations to Provable Independence: An Ontology-Driven Optimal-Transport Framework for Certifiably Fair AI Systems
This paper presents a framework for provably fair AI that overcomes the limits of current bias mitigation methods by systematically removing all sensitive information and its proxies. Using ontology engineering in OWL 2 QL, it formally defines sensitive attributes and infers their proxies through logical reasoning, constructing a sigma algebra G that captures the full structure of biased patterns. Fair representations are then obtained via Delbaen Majumdar optimal transport, which generates var…