Knowledge catalogue
arXiv:2605.03855v1 Announce Type: new Abstract: Human-AI collaboration requires AI agents to understand human behavior for effective coordination. While advances in foundation models show promising ca
At Google, we see firsthand how cyber threats can outpace traditional defense mechanisms — and how agentic threat intelligence can help bridge the gap. We have a vision for agentic defense where auton
arXiv:2505.08203v2 Announce Type: replace-cross Abstract: While recent advancements in AI music generation have predominantly focused on direct audio synthesis, these systems suffer from inherent rigi
I recently talked with Joseph Ruscio about AI coding tools for Heavybit's High Leverage podcast: Ep. #9, The AI Coding Paradigm Shift with Simon Willison. Here are some of my highlights, including my
arXiv:2605.01544v1 Announce Type: new Abstract: Imitation learning (IL) has seen remarkable progress, yet field deployment of IL-powered robots remains hindered by the challenge of out-of-distribution
arXiv:2605.02402v1 Announce Type: new Abstract: Reflective thinking is a key competency in education, but assessing reflective writing remains a time-consuming and subjective task for education expert
arXiv:2508.12535v3 Announce Type: replace Abstract: Sparse Autoencoders (SAEs) can extract interpretable features from large language models (LLMs) without supervision. However, their effectiveness in
arXiv:2605.02737v1 Announce Type: new Abstract: Synthetic training has recently advanced brain MRI segmentation by enabling contrast-agnostic models trained entirely on generated data. However, most e
arXiv:2508.15658v5 Announce Type: replace Abstract: The rapid growth of academic literature makes the manual creation of scientific surveys increasingly infeasible. While large language models show pr
arXiv:2605.02041v1 Announce Type: new Abstract: The extraction of entities and relationships from threat intelligence reports into structured formats, such as cybersecurity knowledge graphs, is essent
This post documents a 10-day project to build a local AI system using open-source tools and models, specifically combining Ollama (a local LLM framework), Gemma 4 (a language model), Claude Cowork 3P,
arXiv:2602.11897v3 Announce Type: replace-cross Abstract: Cybersecurity decision-making increasingly occurs in environments characterized by uncertainty, partial observability, and adversarial manipul
arXiv:2604.27089v1 Announce Type: new Abstract: Large-language-models (LLMs) demonstrate enormous utility in long-context tasks which require processing prompts that consist of tens to hundreds of tho
arXiv:2604.27547v1 Announce Type: new Abstract: Fine-tuning large language models (LLMs) for domain-specific tasks requires training datasets that comprehensively cover the target capabilities a pract
arXiv:2503.04956v2 Announce Type: replace-cross Abstract: Time series forecasts are widely used to inform decisions. Human decision-makers interpret these forecasts, incorporate prior experience and u
arXiv:2604.27660v1 Announce Type: new Abstract: Many real-world tasks require language models (LMs) to reason over complex contexts that exceed their parametric knowledge. This calls for context learn
arXiv:2604.27955v1 Announce Type: new Abstract: Graphical User Interface (GUI) agents have emerged as a promising paradigm for intelligent systems that perceive and interact with graphical interfaces
arXiv:2604.28158v1 Announce Type: new Abstract: Existing research infrastructure is fundamentally document-centric, providing citation links between papers but lacking explicit representations of meth
arXiv:2604.27321v1 Announce Type: cross Abstract: Security Operations Centers (SOCs) face mounting operational challenges. These challenges come from increasing threat volumes, heterogeneous SIEM plat
Claude's Computer Use capability has been integrated into the Codex app, delivering a 42% performance improvement for this use case in the latest update. This enhancement likely demonstrates improved
arXiv:2604.25850v1 Announce Type: new Abstract: Harnesses have become a central determinant of coding-agent performance, shaping how models interact with repositories, tools, and execution environment
arXiv:2604.25241v1 Announce Type: new Abstract: Categorical structural optimization under aleatoric uncertainty is challenging because each design variable must be selected from a finite catalog of ad
arXiv:2604.25891v1 Announce Type: new Abstract: Finetuning a language model can lead to emergent misalignment (EM) [Betley et al., 2025b]. Models trained on a narrow distribution of misaligned behavio
arXiv:2603.12118v2 Announce Type: replace Abstract: Any-to-Any models are an emerging class of multimodal models that accept combinations of multimodal data (e.g., text, image, video, audio) as input
arXiv:2601.02078v2 Announce Type: replace Abstract: The development of robust and generalizable robot learning models is critically contingent upon the availability of large-scale, diverse training da
arXiv:2503.06778v3 Announce Type: replace Abstract: Event annotation is important for identifying market changes, monitoring breaking news, and understanding sociological trends. Although expert annot
arXiv:2601.21293v2 Announce Type: replace Abstract: Reliability-centered prognostics for rotating machinery requires early-warning signals that remain accurate under nonstationary operating conditions
At UKG, we’ve spent years building and expanding our human capital management (HCM) and workforce management (WFM) solutions with new products, capabilities, and a series of acquisitions. Our cloud pl
arXiv:2512.21372v2 Announce Type: replace-cross Abstract: The accurate classification of gastrointestinal diseases from endoscopic and histopathological imagery remains a significant challenge in medi
arXiv:2604.23415v1 Announce Type: new Abstract: Most two-stream action recognition networks apply the same convolutional backbone to both RGB and optical flow streams, ignoring the fact that the two m
arXiv:2504.06176v3 Announce Type: replace-cross Abstract: Foundation Models, which leverage large neural networks pre-trained on unlabelled data before fine-tuning for specific tasks, are increasingly
arXiv:2604.24039v1 Announce Type: cross Abstract: Embodied AI agents increasingly rely on large language models (LLMs) for planning, yet per-step LLM calls impose severe latency and cost. In this pape
arXiv:2604.23251v1 Announce Type: cross Abstract: Code review is central to software engineering education but hard to scale in capstone projects due to tight deadlines, uneven peer feedback, and limi
It has been just under a decade since Amazon Web Services Inc. launched Amazon Connect, taking its own internal contact center-as-a-service solution and commercialized it. At the time, there were many
arXiv:2604.24685v1 Announce Type: new Abstract: Chromosome analysis is a fundamental step in the diagnosis of genetic diseases, but the manual karyotyping workflow is time-consuming and heavily depend
Israel-based Blocks Platforms Ltd., a startup providing solutions that help companies build and deploy intelligent autonomous apps and agents for a digital workforce, today announced it has raised 20
arXiv:2604.23183v1 Announce Type: cross Abstract: AI incident reporting requirements are emerging in regulation and policy, yet no operational criteria exist for determining when a detected AI inciden
arXiv:2604.24572v1 Announce Type: new Abstract: The Observational Medical Outcomes Partnership Common Data Model (OMOP CDM), maintained by the Observational Health Data Sciences and Informatics (OHDSI
arXiv:2510.18289v2 Announce Type: replace Abstract: Food insecurity remains a persistent public health emergency in the United States, tightly interwoven with chronic disease, mental illness, and opio
arXiv:2604.23776v1 Announce Type: cross Abstract: Accurate monitoring of oil palm plantations is critical for balancing economic development with environmental conservation in Southeast Asia. However,
arXiv:2508.10945v2 Announce Type: replace Abstract: Potholes on the roads are a serious hazard and maintenance burden. This poses a significant threat to road safety and vehicle longevity, especially
arXiv:2604.23257v1 Announce Type: cross Abstract: Software engineering (SE) organizations operate in a knowledge-intensive domain where critical assets -- architectural expertise, design rationale, an
arXiv:2604.23355v1 Announce Type: new Abstract: Existing LLM-based EDA agents are often isolated task-specific systems. This leads to repeated engineering effort and limited reuse of successful design
arXiv:2504.09844v4 Announce Type: replace-cross Abstract: Modern frameworks for training large foundation models (LFMs) employ dataloaders in a data-parallel manner, with each loader processing a disj
arXiv:2604.23148v1 Announce Type: new Abstract: The emerging threat of AR-LLM-based Social Engineering (AR-LLM-SE) attacks (e.g. SEAR) poses a significant risk to real-world social interactions. In su
arXiv:2604.23816v1 Announce Type: cross Abstract: Software documentation frequently becomes outdated or fails to exist entirely, yet developers need focused views of their codebase to understand compl
Should we care about AI happiness? In our new research, we find evidence of functional AI wellbeing across several independent measures. We find which AI models are happiest, how to make them happier,
Autonomous drone startup SkyfireAI Inc. today announced that it has raised 11 million in new funding to accelerate the development of its dual-use, artificial intelligence-native platform for autonomo
arXiv:2604.24306v1 Announce Type: cross Abstract: Accurate forecasting of solar power output is essential for efficient integration of renewable energy into the grid. In this study, an attention-based
arXiv:2509.26158v2 Announce Type: replace-cross Abstract: The performance of deep neural networks is strongly influenced by the quality of their training data. However, mitigating dataset bias by manu
Samantha Subin / CNBC: True Anomaly, which makes autonomous spacecraft and software for the US Space Force, raised a 650M Series D at a 2.2B valuation, bringing total funding to $1B — True Anomaly, a
arXiv:2604.23362v1 Announce Type: cross Abstract: Adversarial attacks play a pivotal role in testing and improving the reliability of deep learning (DL) systems. Existing literature has demonstrated t
arXiv:2505.13360v3 Announce Type: replace Abstract: Prompt underspecification is a common challenge when interacting with LLMs. In this paper, we present an in-depth analysis of this problem, showing
arXiv:2604.22756v1 Announce Type: cross Abstract: Conjoint analysis is a cornerstone of market research for estimating consumer preferences; however, traditional methods face persistent challenges reg
arXiv:2604.21961v1 Announce Type: cross Abstract: Optimization problems are fundamental in diverse fields, such as engineering, economics, and scientific computing. However, current algorithms are mos
arXiv:2604.22436v1 Announce Type: new Abstract: The rapid growth of AI agent ecosystems is transforming how complex tasks are delegated and executed, creating a new challenge of identifying suitable a
arXiv:2604.22199v1 Announce Type: cross Abstract: Autonomous robots operating in open environments need the ability to continuously handle tasks that are not covered by predefined local methods. Howev
arXiv:2411.07378v3 Announce Type: replace Abstract: Artificial intelligence (AI) in medical device software (MDSW) represents a transformative clinical technology, attracting increasing attention with
arXiv:2604.21950v1 Announce Type: cross Abstract: Small language models (1-3B) are practical to run locally, but individually limited on harder code generation tasks. We ask whether composing them int
arXiv:2604.22750v1 Announce Type: new Abstract: The wide adoption of AI agents in complex human workflows is driving rapid growth in LLM token consumption. When agents are deployed on tasks that requi