Knowledge catalogue
arXiv:2609.03454v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) can improve the specificity and grounding of large language model responses, but its effect is not uniformly benefi
arXiv:2609.02414v1 Announce Type: cross Abstract: Multi-turn jailbreak attacks demonstrate that harmful intent can be distributed across dialogue, yet existing methods obscure what conversational mech
arXiv:2609.00076v1 Announce Type: new Abstract: Clinical artificial intelligence is increasingly embedded in real-world care, yet existing safety mechanisms are poorly suited to reconstructing and lea
arXiv:2609.00904v1 Announce Type: new Abstract: Whether large language models (LLMs) can control their own internal representations matters for both machine metacognition and AI safety. A recent study
arXiv:2608.29109v1 Announce Type: new Abstract: Large language models often answer structurally unanswerable questions, such as computing cot(-540{eg}) or evaluating (1).startswith('1'), instead of ab
arXiv:2608.29458v1 Announce Type: cross Abstract: Sandbagging, in which a model deliberately underperforms on an evaluation despite retaining the underlying capability, threatens the safety evaluation
arXiv:2602.08136v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) are now a core part of modern AI. Recent work proposed several visual jailbreak attacks using single/ holistic i
arXiv:2608.30512v1 Announce Type: cross Abstract: Large-scale industrial robot fleets share constrained physical infrastructure, making vehicle travel times dependent on safety separation, intersectio
arXiv:2608.26506v1 Announce Type: cross Abstract: Model merging enables combining multiple fine-tuned models without additional training, but its safety implications remain poorly understood. Prior wo
arXiv:2511.02605v3 Announce Type: replace Abstract: Shielding is widely used to enforce safety in reinforcement learning (RL), ensuring that an agent's actions remain compliant with formal specificati
arXiv:2608.23870v1 Announce Type: new Abstract: When it comes to safety policies for generative AI, one size does not fit all. Each organization and use case needs to mitigate different risks dependin
arXiv:2608.22312v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable progress in vision-language interaction, yet their safety alignment remains vulnerable
arXiv:2608.19580v1 Announce Type: new Abstract: Vessel trajectory prediction is critical for maritime safety and accident prevention. While most existing trajectory prediction models rely on Automatic
arXiv:2608.18900v1 Announce Type: new Abstract: As AI systems are increasingly deployed in safety-critical application domains (e.g., autonomous driving), associated risks increase too. Deep learning
arXiv:2608.18715v1 Announce Type: cross Abstract: Ensuring not only high accuracy but also reliable and robust predictions is critical for the deployment of semantic segmentation models in safety-crit
nobody takes Altman at his word anymore – nor should they. Altman's claim that OpenAI is slowing their frontier model training in order to focus on safety doesn't pass the sniff test.👃 For several yea
arXiv:2608.13617v1 Announce Type: new Abstract: Verifying whether clinical care follows evidence-based protocols is a natural neuro-symbolic problem, yet the safety-critical setting defeats either par
arXiv:2604.05498v2 Announce Type: replace Abstract: World Action Models (WAMs) have emerged as a promising paradigm for robotic manipulation, enabling physical interaction across diverse tasks and env
arXiv:2608.10703v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly act in interactive settings where their behavioral styles affect user experience, safety, and downstream dec
arXiv:2608.09484v1 Announce Type: new Abstract: Many diffusion-based planners enforce safety through inference-time guidance, but such interleaved trajectory deformations often degrade kinematic feasi
arXiv:2509.03985v2 Announce Type: replace-cross Abstract: In deployment and application, large language models (LLMs) typically undergo safety alignment to prevent illegal and unethical outputs. Howev
arXiv:2608.03010v1 Announce Type: new Abstract: In robot-assisted surgery, Forbidden Region Active Constraints (FRAC) represent a control strategy that helps maintain task safety by generating anisotr
arXiv:2607.27511v1 Announce Type: new Abstract: Imitation learning has shown increasing promise for autonomous robotic surgery, yet safe deployment remains challenging due to the safety-critical natur
arXiv:2607.28248v1 Announce Type: cross Abstract: The deployment of deep neural networks in safety-critical domains demands reliable estimates of predictive confidence, yet conventional architectures
arXiv:2607.26574v1 Announce Type: cross Abstract: Safety classifiers ('guards') are the dominant black-box defense for vision-language models, yet they judge an input's surface form, not its meaning:
arXiv:2607.26228v1 Announce Type: new Abstract: Instruction hierarchies are a core safety assumption of language model deployment: higher priority inputs, such as system prompts, should override confl
The narrative: Blame the Agent, instead of the Agency that told him to “apply all your powers and told to achieve this win.” Ironically, many forefront members of the AI-Safety community, in their fer
arXiv:2607.25664v1 Announce Type: new Abstract: Machine learning demand forecasts optimize statistical accuracy yet leave excess operational volatility that inflates safety stock and amplifies the Bul
arXiv:2607.24769v1 Announce Type: new Abstract: With the growing capabilities of frontier models, AI alignment becomes increasingly critical in high-risk deployment settings. While recent work has emp
arXiv:2607.24057v1 Announce Type: new Abstract: Real-world Reinforcement Learning depends on the ability to formulate safety constraints into a policy. A common way to model such constraints is to int
arXiv:2607.22877v1 Announce Type: new Abstract: With the emergence of Physical AI, artificial intelligence is extending beyond screen-based applications to embodied systems that perceive, interact wit
arXiv:2607.24199v1 Announce Type: new Abstract: Understanding and complying with traffic regulations is a safety-critical requirement for autonomous driving, yet remains challenging due to the diversi
For my first post, I’m sharing a letter @NVIDIA signed on why open models matter. AI will transform every industry, power every company, and be built by every country. Open models strengthen safety an
arXiv:2607.13348v1 Announce Type: new Abstract: Autonomous racing overtaking requires balancing competitive performance with safety under nonlinear vehicle dynamics and real-time constraints. Model Pr
arXiv:2607.13175v1 Announce Type: cross Abstract: Safe reinforcement learning typically enforces safety by bounding expected cumulative costs, a criterion that often fails to detect rare but catastrop
arXiv:2607.07916v1 Announce Type: new Abstract: Large language models exhibit recurring behavioural patterns -- personas -- that shape generalisation and safety, but we lack reliable tools for decompo
arXiv:2606.20023v2 Announce Type: replace-cross Abstract: As LLM agents increasingly select tools autonomously, their choices among tools with different privileges become safety-relevant. However, pri
arXiv:2607.00576v1 Announce Type: new Abstract: Multi-image content has become an increasingly prevalent form of visual communication in social media, giving rise to a new safety issue, multi-image im
arXiv:2504.12557v3 Announce Type: replace-cross Abstract: Ensuring safe behavior in reinforcement learning (RL) is challenging when safety constraints are implicit and cannot be densely measured. In m
arXiv:2603.05786v2 Announce Type: replace-cross Abstract: As AI agents become widely deployed as online services, users often rely on an agent developer's claim about how safety is enforced, which int
arXiv:2606.29115v1 Announce Type: cross Abstract: Autonomous vehicles (AVs) are increasingly deployed in urban environments, yet their safety frameworks remain primarily designed around collision avoi
arXiv:2606.26151v1 Announce Type: cross Abstract: While autonomous rovers have become indispensable to precision farming, achieving consistent operational safety remains a critical challenge. Conventi
arXiv:2606.25134v1 Announce Type: new Abstract: Safe control has been widely studied in various safety-critical applications, for instance, autonomous driving. In order to ensure the autonomous vehicl
arXiv:2502.02205v4 Announce Type: replace Abstract: The application of deep learning for partial differential equation (PDE)-constrained control is gaining increasing attention. However, existing meth
arXiv:2512.15503v3 Announce Type: replace-cross Abstract: Vehicular platooning promises transformative improvements in transportation efficiency and safety through the coordination of multi-vehicle fo
arXiv:2606.22278v1 Announce Type: cross Abstract: Ensuring safety of learning-enabled robotic manipulation across diverse embodiments and tasks still requires significant manual engineering. Existing
arXiv:2606.22319v1 Announce Type: cross Abstract: Robotic ultrasound scanning in real clinical environments requires both high-level clinical workflow reasoning and low-level closed-loop execution. Ph
arXiv:2606.20748v1 Announce Type: new Abstract: Humanoid robots are emerging as co-workers in smart manufacturing, yet their dynamic, human-like movements introduce safety risks that differ fundamenta
arXiv:2606.10487v1 Announce Type: cross Abstract: Deploying large language models in user-facing systems requires efficient output safety filtering. Existing approaches typically rely on a separate mo
arXiv:2606.09475v1 Announce Type: new Abstract: Work on `emergent misalignment' shows that finetuning LLMs on narrow tasks can induce broadly misaligned behavior. This supports the `persona selection'
arXiv:2606.08919v1 Announce Type: new Abstract: As LLM agents begin to take real, irreversible actions (shell commands, file edits, deploys), the standard safety pattern is a human-in-the-loop approva
arXiv:2606.08741v1 Announce Type: new Abstract: Robots operating in human environments must not only ensure physical safety but also exhibit behaviors that are understandable, fluent, and acceptable t
arXiv:2606.05551v1 Announce Type: cross Abstract: Reliable decision making pipelines powered by machine learning models require uncertainty quantification (UQ) methods that come with explicit safety g
arXiv:2606.04812v1 Announce Type: cross Abstract: Guaranteeing safety is critical to the deployment of reinforcement learning (RL) agents in the real-world, especially as policies learned using deep R
arXiv:2606.01051v1 Announce Type: new Abstract: Dynamic medical treatment requires deciding treatment intensity and intervention timing, while patient states evolve continuously and adverse events may
arXiv:2606.00261v1 Announce Type: new Abstract: Police-reported crash statistics remain the standard input for urban road-safety assessment, but their incompleteness and reporting lag limit their usef
arXiv:2604.17176v2 Announce Type: replace-cross Abstract: Future spacecraft operations require autonomy that can interpret high-level mission intent while preserving safety. However, existing trajecto
arXiv:2605.29068v1 Announce Type: new Abstract: Maintaining the safety of large language models (LLMs) is crucial as they are increasingly deployed in real-world applications. Existing safety guardrai
arXiv:2605.27766v1 Announce Type: new Abstract: LLM safety evaluations predominantly test models in isolation, yet deployed AI agents increasingly operate within persistent social environments alongsi
arXiv:2605.28137v1 Announce Type: new Abstract: Text-to-image models trained on large-scale data often inevitably ingest unsafe content. While some people observe input-output amplifications, it remai