Search: “safety”

arXiv:2603.22341v2 Announce Type: replace-cross Abstract: While prior red-teaming efforts have focused on eliciting harmful text outputs from large language models (LLMs), such approaches fail to capt

arXiv:2608.29596v1 Announce Type: new Abstract: Autonomous large language model (LLM) agents increasingly face reliability, context consumption, and execution stability bottlenecks when deployed on co

arXiv:2608.28405v1 Announce Type: new Abstract: Current cultural evaluations for large language models (LLMs) often reduce culture to single-turn factual recall via MCQs, failing to capture a common u

arXiv:2608.27844v1 Announce Type: new Abstract: Existing evaluations of harmful content detection rely predominantly on static benchmarks, which struggle to reflect the interactive adversarial ecosyst

arXiv:2608.27465v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly used for everyday decision-making advice, whether a model shifts the direction of its advice according

We’re excited to launch the official LlamaParse connector on Claude! Yes Claude can already read PDFs, and it probably works fine for relatively simple queries over relatively simple docs. But if you

happened simultaneously across the board. OpenCode, OpenRouter, and Ollama all ruined DeepSeek at the exact same moment. They literally turned a brilliant model into a complete idiot overnight. I abso

arXiv:2608.26701v1 Announce Type: new Abstract: We present an extension and comprehensive real-world validation of Co-Scientist, a Gemini-based multi-agent system designed to accelerate end-to-end sci

arXiv:2608.26143v1 Announce Type: cross Abstract: Memes have turned out to be a powerful tool through which individuals share their ideas concerning contemporary social and political problems. Their a

arXiv:2608.27158v1 Announce Type: new Abstract: Robot crowd navigation requires safe and efficient decision-making under dense, dynamic, and multimodal human--robot interactions. Existing reinforcemen

arXiv:2608.27110v1 Announce Type: new Abstract: Reliable medical conversational AI requires authentic expert--patient interaction data, yet such datasets remain scarce, especially for low-resource lan

arXiv:2608.27021v1 Announce Type: cross Abstract: LLM-based agents are increasingly proposed for network fault diagnosis, but existing benchmarks evaluate them only on accurate tickets and always assu

arXiv:2608.26157v1 Announce Type: new Abstract: Natural-language analytics over enterprise data warehouses is increasingly important, but production use is limited by hallucinated metrics, invalid joi

arXiv:2608.26820v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) exhibit strong generalization, visual instruction tuning for downstream tasks inevitably causes catastrop

arXiv:2608.26800v1 Announce Type: new Abstract: We present an online learning framework that enables a bimanual robot to acquire diverse juggling patterns directly on physical hardware within minutes,

arXiv:2608.26109v1 Announce Type: new Abstract: Machine-learning models can predict ICU mortality accurately, but feature-attribution methods alone rarely provide the clinical narrative needed for bed

arXiv:2608.26382v1 Announce Type: new Abstract: Pathology vision-language models are advancing rapidly, yet existing benchmarks remain focused on human tissue, particularly oncology, leaving non-human

arXiv:2608.26008v1 Announce Type: cross Abstract: Large language models (LLMs) remain vulnerable to jailbreak attacks that exploit techniques such as role-playing, obfuscation, code transformation, an

Jack Queen / Reuters: A US judge blocks the Pentagon from blacklisting Anthropic, ruling that its designation as a supply-chain risk was “illegal and baseless” — A U.S. judge on Thursday blocked the P

Breaking Claude Code Opus 5 Auto Mode Anthropic are putting a great deal of faith in Claude Code's auto mode for protecting their coding agent users against prompt injection attacks. They recently mad

arXiv:2509.09297v2 Announce Type: replace Abstract: Open-set detection is crucial for robust UAV autonomy in air-to-air object detection under real-world conditions. Traditional closed-set detectors d

arXiv:2608.24907v1 Announce Type: cross Abstract: In health and nutrition consulting, widely used prompting methods pass the user profile as an unstructured block without a dedicated analysis step, le

arXiv:2506.23492v2 Announce Type: replace-cross Abstract: Recent advances in deep learning have significantly improved predictive accuracy. However, modern neural networks remain systematically overco

arXiv:2608.23726v1 Announce Type: cross Abstract: Rapid and accurate fault detection in high-voltage transmission networks is essential for grid reliability and equipment protection. Transmission faul

arXiv:2608.24314v1 Announce Type: new Abstract: Evaluating conversational voice agents at scale re- quires reliable assessment methods that capture both observ- able interaction quality and the contex

arXiv:2608.23653v1 Announce Type: cross Abstract: AI agents are increasingly used for simulation-driven engineering. Physical system modeling presents different requirements from general-purpose code

arXiv:2603.17170v2 Announce Type: replace-cross Abstract: AI agents increasingly execute users' natural-language (NL) tasks by calling Web services, yet today's Web authorizes these calls through OAut

As AI takes on more complex work, business leaders face a new challenge: enabling rapid innovation using agents while protecting their margins and budgets. To get a real return on AI, financial operat

arXiv:2509.19610v3 Announce Type: replace Abstract: Most common tasks for robots in dynamic spaces require that the environment is regularly and actively perceived. The perception task considered in t

arXiv:2608.22994v1 Announce Type: cross Abstract: Training large language models is costly. How low a loss the same compute can ultimately reach depends on how each step's gradient is converted into a

arXiv:2608.21895v1 Announce Type: cross Abstract: Locally deployed Large Language Models (LLMs) via inference engines such as Ollama run without the moderation and abuse detection present in API-serve

arXiv:2608.21993v1 Announce Type: new Abstract: We introduce Gated Decoupled Compositional Bandits (GDCB), a family of contextual bandit algorithms with three structural innovations that jointly fall

arXiv:2608.21836v1 Announce Type: new Abstract: Large language models have become increasingly capable agents for low-level code and kernel optimization, but isolated kernel benchmarks provide only a

arXiv:2512.07609v3 Announce Type: replace-cross Abstract: The conventional Artificial Potential Field (APF) is fundamentally limited by the local minima issue and its inability to account for the kine

I’ve been experimenting with a custom inference/runtime research project called CRANE V2, mostly because I wanted to answer a stupid question: How far can you push absurdly large MoE models on an ordi

arXiv:2608.22527v1 Announce Type: new Abstract: Recently, machine unlearning, the removal of specific training data influence from a model, has gained increasing attention. In large language models (L

arXiv:2602.18492v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are now good enough at coding that developers can describe intent in plain language and let the tool produce the

// Applying Anthropic Primitives at Large Enterprises // Frontier models collapsed the cost of writing custom code. But they did not reduce the cost of reviewing and maintaining it. Each bespoke solut

arXiv:2608.21262v1 Announce Type: cross Abstract: Many machine-learning systems set a threshold at a quantile of a calibration set: conformal predictors that promise 90% coverage by drawing their cuto

arXiv:2608.21049v1 Announce Type: cross Abstract: With the progression in open and disaggregated 6G radio access networks, it is expected that the system will be able to host multi-vendors. In order t

I was fascinated by Nanbeige's outstanding performance for its size, so I started digging into how much a model can improve its own representation just by looping over itself (for fun). My prototype w

arXiv:2608.19932v1 Announce Type: new Abstract: Public cardiac cohorts annotate different subsets of the heart, so shapes from separate sources cannot be pooled without shared correspondence. Among re

arXiv:2608.19380v1 Announce Type: new Abstract: While modern autonomous driving systems excel at perception tasks such as object detection and trajectory prediction, they lack the high-level causal re

arXiv:2508.19008v3 Announce Type: replace Abstract: Building on a human-led thematic analysis of clinical life-story interviews (> 150,000 words) with inpatients with Borderline Personality Disorder,

arXiv:2608.20338v1 Announce Type: new Abstract: Large Language Models (LLMs) increasingly require selective removal of harmful or sensitive knowledge, called unlearning, yet existing methods and bench

arXiv:2608.20055v1 Announce Type: cross Abstract: Hidden chain-of-thought (CoT) traces, especially those from frontier proprietary large reasoning models (LRMs), are valuable model assets. Yet whether