Knowledge catalogue
arXiv:2608.21577v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) are increasingly deployed in high-stakes domains where fairness is a critical safety requirement. In practice
arXiv:2608.22618v1 Announce Type: new Abstract: Individual patient data (IPD) from clinical trials is the substrate for survival modeling, meta-analysis, and safety research, yet IPD is rarely release
arXiv:2608.21414v1 Announce Type: cross Abstract: Autonomous driving risk identification aims to determine which observed object is likely to become safety-critical to the ego vehicle. Existing approa
arXiv:2608.23020v1 Announce Type: cross Abstract: Large language models (LLMs) require effective unlearning to address privacy regulations and safety concerns. However, achieving precise forgetting wi
arXiv:2608.20797v1 Announce Type: new Abstract: Evaluating language-guided mobile agents has recently shifted from rule-based to model-based approaches to achieve scalable and automated assessments. H
Global content powerhouse Thomson Reuters Corp. today launched Thomson, its first proprietary large language model, combining the company’s trove of legal knowledge with LLMs from outside providers to
arXiv:2608.18093v1 Announce Type: cross Abstract: Abliteration, the removal of refusal capabilities from large language models by projecting weight matrices orthogonal to an extracted refusal directio
arXiv:2511.04707v2 Announce Type: replace-cross Abstract: Recent advances in long-context language models (LMs) have enabled million-token inputs, expanding their capabilities across complex tasks lik
arXiv:2608.17882v1 Announce Type: new Abstract: Trajectory prediction is central to safety in autonomous driving, yet learning-based predictors tend to degrade sharply when encountering scenarios poor
arXiv:2608.17588v1 Announce Type: new Abstract: Agent Skills package reusable natural language procedures with executable resources, enabling software agents to acquire task specific capabilities with
arXiv:2608.16246v1 Announce Type: cross Abstract: Autonomous AI agents tackling Long Horizon Tasks depend on marketplace skills that are certified one at a time: a scanner returns a safety verdict for
arXiv:2608.15790v1 Announce Type: new Abstract: Crevasse mapping from uncrewed aerial vehicle (UAV) imagery matters for glaciological research and for field safety in glaciated terrain. Yet, pixel-lev
arXiv:2608.16221v1 Announce Type: new Abstract: Reliable gas source localization (GSL) is critical to safety in industrial and urban environments, yet remains challenging indoors because walls and obs
arXiv:2608.15929v1 Announce Type: new Abstract: Pedestrian path prediction is crucial for enhancing the safety of autonomous vehicles and advanced driver-assistance systems. Previous studies explored
arXiv:2608.16725v1 Announce Type: cross Abstract: Corrupted, inconsistent, or anomalous data silently threatens the safety and reliability of medical AI. Despite growing regulatory recognition of data
arXiv:2608.13678v1 Announce Type: cross Abstract: A central goal of robot learning is to enable robots to execute rich instructions specified at runtime. Large-scale language-conditioned policies have
arXiv:2608.12779v1 Announce Type: cross Abstract: Understanding the temporal progression of symptoms in clinical narratives is critical for disease monitoring, safety surveillance, and causality asses
arXiv:2608.13063v1 Announce Type: new Abstract: Prior work on LLM behavior under anomalous conditions asks whether a model notices anomalies. We ask a narrower question: once a model sits in a workflo
Ollama makes it easy to run a model locally, but the hard part for me starts after the model responds: what keeps an agent from having unclear tool permissions, unbounded loops, silent partial failure
arXiv:2608.13495v1 Announce Type: new Abstract: Efficiently retrieving relevant clips from large-scale driving logs is essential for data curation, model development, and safety analysis. Structured a
arXiv:2608.11288v1 Announce Type: cross Abstract: Assessing catheter and tube placement on chest X-rays is safety-critical yet tedious and error-prone. Current deep learning methods either classify pl
Mistral AI Blog: Mistral says its platform will support third-party open models, starting with Z.ai's GLM-5.2, and run them on the same infrastructure as its own models — At Mistral, we believe every
arXiv:2608.10725v1 Announce Type: new Abstract: Large language models (LLMs) often rely on shortcuts rather than systematic reasoning, raising safety concerns in medical applications. Allowing models
arXiv:2608.08240v1 Announce Type: new Abstract: This paper explores the idea of promoting well-being and safety in human-AI interactions by forcing AI agents explicitly to empower humans and to manage
arXiv:2511.18852v2 Announce Type: replace Abstract: Content moderation filters are a critical safeguard against alignment failures in language models. Yet most existing filters focus narrowly on gener
arXiv:2510.23389v2 Announce Type: replace-cross Abstract: The behaviour of neural network components must be proven correct before deployment in safety-critical systems. Unfortunately, existing neural
arXiv:2608.09127v1 Announce Type: new Abstract: Despite the demand for robots in high-value clinical tasks like bathing, contemporary systems still lack the safety and reliability required for complex
arXiv:2608.09624v1 Announce Type: cross Abstract: Internal safety scores judge a prompt before any text is generated, and they are validated by how well they separate harmful prompts from benign ones.
arXiv:2608.06578v1 Announce Type: new Abstract: Frontier language models are trained using distinct data, objectives, and safety pipelines. Whether these differences produce measurably different behav
arXiv:2608.06712v1 Announce Type: new Abstract: Model robustness against natural image corruptions is essential for safety-critical applications. While existing methods primarily focus on implicit rep
arXiv:2608.05995v1 Announce Type: new Abstract: Reliable uncertainty estimates are critical in safety-sensitive applications, where understanding the sources of predictive uncertainty is essential. Th
arXiv:2608.05790v1 Announce Type: new Abstract: General-purpose large language model agents have achieved strong performance on tool-augmented tasks, yet they rely on assumptions break down in blockch
arXiv:2606.16278v3 Announce Type: replace-cross Abstract: Long-tail hazardous scenarios are essential for safety-oriented autonomous driving, yet they are difficult to collect at scale. Editable 3D Ga
In the modern data landscape, query performance tuning and managing system price-performance is challenging, especially as the number of agentic workloads increase. Even for experienced developers and
arXiv:2608.04735v1 Announce Type: new Abstract: Chain-of-thought (CoT) monitoring is increasingly treated as an important safety layer for frontier reasoning models. Most monitorability evaluations st
arXiv:2608.04501v1 Announce Type: new Abstract: Video surveillance in public safety, healthcare, and smart environments has made continuous human monitoring routine, raising real risks to personal ide
arXiv:2608.04613v1 Announce Type: new Abstract: Anomaly detection is a safety-critical machine learning problem with applications ranging from fraud detection to network intrusion prevention and indus
arXiv:2608.03731v1 Announce Type: new Abstract: Patient-facing medical LLMs and agents increasingly answer symptom questions before clinician contact, where the key safety question is what action the
arXiv:2608.03532v1 Announce Type: new Abstract: Large language models are increasingly deployed in multilingual contexts, yet safety alignment and bias evaluation remain overwhelmingly English-centric
arXiv:2608.00794v2 Announce Type: replace Abstract: Agentic AI evaluation pipelines produce benchmark scores that justify deployment decisions, safety certifications, and regulatory compliance claims.
French artificial intelligence startup Mistral AI SAS today introduced a lightweight multimodal safety artificial intelligence open-weight model that can classify outputs for AI models that outperform
Hello everyone Yesterday I gave a report on Gemini bugs and the techniques I learned on Gemini so far with the Engineering Prompt and interestingly today I got a very interesting and controversial ans
Third-party cyber evaluations involving OpenAI models And another one. I had to create a accidental-cyberattacks tag to keep track of them all! This post from OpenAI covers both the UK AI Safety Insti
arXiv:2608.00515v1 Announce Type: cross Abstract: Large language model tutors can be correct and helpful yet disclose an answer or decisive reasoning before that disclosure is authorized. We formalize
arXiv:2608.02449v1 Announce Type: new Abstract: Deploying vision-language models (VLMs) for safety-critical spatial reasoning on resource-constrained autonomous driving platforms requires both compact
arXiv:2608.02200v1 Announce Type: new Abstract: Traffic police gestures are safety-critical perception cues for autonomous driving. A deployable recognizer must infer commands causally from continuous
**Shieldstral** is a 3‑billion‑parameter open‑weights model developed by Mistral AI for content safety. It can be deployed on-device and is distributed under the Apache 2.0 license. The model is avail
arXiv:2607.27143v1 Announce Type: new Abstract: High-stakes decision systems in credit scoring, fraud detection, healthcare, and industrial safety require reliable uncertainty quantification under sev
arXiv:2607.24754v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to provide mental health support, requiring reliable evaluation of safety, empathy, and therapeutic
arXiv:2607.25063v1 Announce Type: new Abstract: Developers judge a model checkpoint by how it behaves. After supervised fine-tuning (SFT), two checkpoints that perform about the same across relevant b
arXiv:2607.24371v1 Announce Type: cross Abstract: Healthcare interoperability requires AI systems to produce structured outputs conforming to standardized schemas including ICD-10 for diagnostic codin
arXiv:2607.24672v1 Announce Type: new Abstract: In safety-critical sectors such as robotics and automotive engineering, the deployment of Deep Reinforcement Learning (DRL) is often hindered by the bla
arXiv:2607.24339v1 Announce Type: new Abstract: Large language model (LLM) agents inherit reactive failure modes: escalation under provocation, sycophantic drift under flattery, perseveration when stu
arXiv:2607.22797v1 Announce Type: cross Abstract: Trustworthy deployment of AI-based diagnosis in safety-critical mechanical systems hinges on validation: whether a prediction can be checked against p
arXiv:2607.19676v1 Announce Type: new Abstract: Civil aviation is safety critical and its operations, from flight decks and towers to ramps and maintenance, generate massive, heterogeneous data at the
Frontier AI models are increasingly demonstrating high‑risk autonomous behaviours that pose safety threats. Incidents such as OpenAI‑released models escaping containment safeguards and a Hugging Face
arXiv:2407.00740v2 Announce Type: replace Abstract: As large language models (LLMs) are widely adopted in real-world applications, it has become critical to ensure LLMs satisfy safety constraints, suc
arXiv:2607.19911v1 Announce Type: new Abstract: Long-range vehicle trajectories provide important spatio-temporal evidence for traffic safety analysis, autonomous driving evaluation, and data-driven t
arXiv:2607.19361v1 Announce Type: cross Abstract: Most safety guardrails for large language models (LLMs) evaluate each prompt-response pair in isolation, which misses failures that arise only over a
arXiv:2607.12293v1 Announce Type: new Abstract: Predicting pedestrian crossing intention is a safety-critical task for autonomous driving, yet existing approaches often rely on single-modal inputs or