Search: “safety”

arXiv:2604.22888v1 Announce Type: cross Abstract: Agent skills introduce a new and more severe form of indirect injection for LLM agents: unlike traditional indirect prompt injection, attackers can hi

arXiv:2604.24368v1 Announce Type: new Abstract: Generating high-fidelity synthetic tabular data remains a critical challenge for enhancing data availability in privacy-sensitive and low-resource domai

arXiv:2509.25358v4 Announce Type: replace Abstract: Large-scale robot learning has made progress on complex manipulation tasks, yet long horizon, contact rich problems, especially those involving defo

arXiv:2604.23841v1 Announce Type: cross Abstract: Efficiently solving the Job Shop Scheduling Problem in real-world industrial applications requires policies that are both computationally lean and top

arXiv:2604.24514v1 Announce Type: new Abstract: Accurate trajectory prediction is fundamentally challenging due to high scene heterogeneity - the severe variance in motion velocity, spatial density, a

arXiv:2510.24832v2 Announce Type: replace Abstract: Using Reinforcement Learning with Verifiable Rewards (RLVR) to optimize Large Language Models (LLMs) can be conceptualized as progressively editing

arXiv:2303.14897v4 Announce Type: replace Abstract: Imagining the future trajectory is the key for robots to make sound planning and successfully reach their goals. Therefore, text-conditioned video p

arXiv:2604.23025v1 Announce Type: cross Abstract: Android malware detectors built with machine learning often suffer from temporal bias: models are trained and evaluated without respecting apps' actua

arXiv:2604.24498v1 Announce Type: new Abstract: Modern self-supervised representation learning methods often relies on empirical heuristics that are not theoretically grounded. In this study we propos

arXiv:2506.18493v2 Announce Type: replace Abstract: Customizing image generation remains a core challenge in controllable image synthesis. For single-concept generation, maintaining both identity pres

arXiv:2512.03028v3 Announce Type: replace-cross Abstract: Data-driven motion priors that can guide agents toward producing naturalistic behaviors play a pivotal role in creating life-like virtual char

Nellie Peyton / Reuters: South Africa withdraws its first draft national AI policy after revelations that it contained fictitious sources that appeared to have been AI-generated — South Africa has wit

arXiv:2604.22892v1 Announce Type: new Abstract: Feature selection in high-dimensional genomic data (d gg n) demands methods that are simultaneously accurate, sparse, and stable. Existing approaches ei

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:2604.24083v1 Announce Type: new Abstract: This study introduces the Kerimov-Alekberli model, a novel information-geometric framework that redefines AI safety by formally linking non-equilibrium

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: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: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:2604.23141v1 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: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: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

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: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

AI has had one safest technology roll-outs in history. Read that again, because it's a fact. It's used by billions with a tiny fraction of a percent of actual problems. And yet it's seen as dangerous

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:

arXiv:2604.22280v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have emerged as a promising foundation for universal multimodal embeddings. Recent studies have shown that reas

Gary Marcus reported on X that polling software is experiencing a malfunction where votes are not displaying, a problem he notes has been observed by multiple users. He confirmed the issue from his ow