safety

arXiv:2604.23646v1 Announce Type: new Abstract: Recent evidence suggests that frontier AI systems can exhibit agentic misalignment, generating and executing harmful actions derived from internally con

arXiv:2511.01490v2 Announce Type: replace Abstract: As synthetic data becomes widely used in language model development, understanding its impact on model behavior is crucial. This paper investigates

Gary Marcus announced a discussion about AI scheduled for 9am PT, with details to be found either in Mario Nawfal's pinned tweet or on YouTube. The conversation appears to be a live social media event

arXiv:2604.24005v1 Announce Type: cross Abstract: On-policy distillation (OPD) has shown strong potential for transferring reasoning ability from frontier or domain-specific models to smaller students

arXiv:2604.22899v1 Announce Type: new Abstract: Industrial anomaly detection based on RGB-3D multimodal data has emerged as a mainstream paradigm for intelligent quality inspection. However, existing

arXiv:2604.23575v1 Announce Type: cross Abstract: Silicon samples are increasingly used as a low-cost substitute for human panels and have been shown to reproduce aggregate human opinion with high fid

arXiv:2602.11318v3 Announce Type: replace Abstract: In machine learning, 'ground truth' refers to the assumed correct labels used to train and evaluate models. However, the foundational 'ground truth'

arXiv:2604.22767v1 Announce Type: cross Abstract: Ethical discourse on AI in healthcare has focused predominantly on back-end concerns such as bias, fairness and explainability, while the front-end in

arXiv:2602.21954v2 Announce Type: replace-cross Abstract: In Part I of this companion paper series, we introduced SWIFTraj, a new open-source vehicle trajectory dataset collected using a unmanned aeri

Thoughtful book on LLMs and linguistics — by someone who actually knows linguistics. Interested in the LLM vs. linguistic theory debate? My just out book will tell you (almost) all about it. https://m

arXiv:2604.23859v1 Announce Type: new Abstract: With spotforecast2-safe we present an integrated Compliance-by-Design approach to Python-based point forecasting of time series in safety-critical envir

arXiv:2601.02018v2 Announce Type: replace Abstract: Segment Anything Models (SAMs), known for their exceptional zero-shot segmentation performance, have garnered significant attention in the research

arXiv:2603.15941v2 Announce Type: replace Abstract: Automated diagnosis from chest computed tomography (CT) scans faces two persistent challenges in clinical deployment: distribution shift across acqu

arXiv:2505.15957v4 Announce Type: replace-cross Abstract: With advancements in large audio-language models (LALMs), which enhance large language models (LLMs) with auditory capabilities, these models

arXiv:2604.23067v1 Announce Type: cross Abstract: Automated methods for red teaming LLMs are an important tool to identify LLM vulnerabilities that may not be covered in static benchmarks, allowing fo

arXiv:2604.23105v1 Announce Type: new Abstract: Deep learning drives major advances in autonomous driving (AD), where object detectors are central to perception. However, adversarial attacks pose sign

arXiv:2604.23938v1 Announce Type: new Abstract: Target Safety Assessment (TSA) requires systematic integration of heterogeneous evidence, including genetic, transcriptomic, target homology, pharmacolo

arXiv:2604.22789v1 Announce Type: cross Abstract: Organizations deploying AI-enabled Intelligent Transportation Systems face fragmented governance: ISO/IEC 42001 demands a certifiable management syste

arXiv:2604.23019v1 Announce Type: new Abstract: Accurate classification of tropical tree species from unoccupied aerial vehicle (UAV) imagery remains challenging due to high species diversity and stro

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:2604.23141v1 Announce Type: cross Abstract: Emerging AR-LLM-based Social Engineering attack (e.g., SEAR) is at the edge of posing great threats to real-world social life. In such AR-LLM-SE attac

arXiv:2604.22893v1 Announce Type: cross Abstract: Traditional data valuation methods based on ``row-count imes quality coefficient'' paradigms fail to capture the nuanced, nonlinear contributions that

arXiv:2604.23380v1 Announce Type: cross Abstract: Aligning denoising generative models with human preferences or verifiable rewards remains a key challenge. While policy-gradient online reinforcement

arXiv:2602.12134v2 Announce Type: replace Abstract: Existing work on value alignment typically characterizes value relations statically, ignoring how alignment interventions, such as prompting, fine-t

arXiv:2510.08045v2 Announce Type: replace-cross Abstract: We introduce a logical language for reasoning about quantized aggregate-combine graph neural networks with global readout (ACR-GNNs). We provi

arXiv:2604.23001v1 Announce Type: cross Abstract: Despite remarkable progress in Vision--Language--Action (VLA) models, a central bottleneck remains underexamined: the data infrastructure that underli

arXiv:2604.23775v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models are emerging as a unified substrate for embodied intelligence. This shift raises a new class of safety challenges, s

arXiv:2512.07834v2 Announce Type: replace Abstract: Voxel art is a distinctive stylization widely used in games and digital media, yet automated generation from 3D meshes remains challenging due to co

When an LLM acts happy (“EUREKA!”) or sad (“I have failed…”), is that meaningless mimicry, or does it reflect something “real”? We don’t know if LLMs are conscious. But they increasingly seem to exhib

arXiv:2603.24231v2 Announce Type: replace Abstract: Stance detection is nearly always formulated as classifying text into Favor, Against, or Neutral. This convention was inherited from debate analysis

arXiv:2604.22873v1 Announce Type: cross Abstract: Offline reinforcement learning (RL) can learn effective policies from fixed datasets, but deployment objectives may change after training, and in many

When you project exponential growth – and miss. I stand by my call that OpenAI is likely to someday be seen as the WeWork of AI. Exclusive: OpenAI recently missed its own targets for new users and rev

arXiv:2604.24764v1 Announce Type: new Abstract: Recent video foundation models demonstrate impressive visual synthesis but frequently suffer from geometric inconsistencies. While existing methods atte

Wow. Musk’s lawyers will capitalize on this. 🚨 Microsoft's lawyer just told the jury Microsoft 'knew nothing'. OpenAI's non-profit board approved all funding, every step of the way and Microsoft did i

arXiv:2604.24623v1 Announce Type: new Abstract: Graph-based Retrieval-Augmented Generation (GraphRAG) extends traditional RAG by using knowledge graphs (KGs) to give large language models (LLMs) a str

arXiv:2604.23486v1 Announce Type: new Abstract: Educational NLP systems are typically evaluated using engagement metrics and satisfaction surveys, which are at best a proxy for meeting pedagogical goa

arXiv:2604.23536v1 Announce Type: new Abstract: Diffusion models have achieved unprecedented success in text-aligned generation, largely driven by Classifier-Free Guidance (CFG). However, standard CFG

arXiv:2604.23878v1 Announce Type: new Abstract: Despite a century of empirical memory research, existing AI agent memory systems rely on system-engineering metaphors (virtual-memory paging, flat LLM s

arXiv:2604.23724v1 Announce Type: cross Abstract: Expressway video anomaly detection is essential for safety management. However, identifying anomalies across diverse scenes remains challenging, parti

arXiv:2604.22227v1 Announce Type: cross Abstract: Classical robot ethics is often framed around obedience, most famously through Asimov's laws. This framing is too narrow for contemporary AI systems,

arXiv:2511.14135v2 Announce Type: replace-cross Abstract: Fair workload enforcement in heterogeneous multi-agent systems that pursue shared objectives remains challenging. Fixed fairness penalties oft

arXiv:2604.22378v1 Announce Type: new Abstract: Robot-to-human handovers often rely on static, open-loop strategies (or, at best, approaches that adapt only the position), which generally do not consi

arXiv:2510.21236v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have evolved into AI agents that interact with external tools and environments to perform complex tasks. The Mode

arXiv:2604.22236v1 Announce Type: cross Abstract: Human decision-makers often face choices about complex cases with many potentially relevant features, but limited bandwidth to inspect and integrate a

“Always keep a separate backup.” For sure, every experienced programmer should know this. 𝘉𝘶𝘵 𝘸𝘦 𝘫𝘶𝘴𝘵 𝘤𝘳𝘦𝘢𝘵𝘦𝘥 𝘢 𝘸𝘩𝘰𝘭𝘦 𝘨𝘦𝘯𝘦𝘳𝘢𝘵𝘪𝘰𝘯 𝘰𝘧 𝘷𝘪𝘣𝘦 𝘤𝘰𝘥𝘦𝘳𝘴 𝘸𝘩𝘰 𝘥𝘰𝘯’𝘵. And we now have a legion of synthetic coding

arXiv:2604.22535v1 Announce Type: new Abstract: Objective: To propose and retrospectively validate an integrated framework addressing three barriers to clinical translation of readmission prediction: