Search: “safety”

arXiv:2508.21448v3 Announce Type: replace Abstract: Large language models (LLMs) sometimes refuse to follow benign instructions, such as declining to argue a political position or adopt a stated perso

arXiv:2606.00730v1 Announce Type: new Abstract: Imitation learning (IL) is an effective approach to train complex robotics policies. Recent works have introduced hard constraints into imitation-learni

arXiv:2606.00033v1 Announce Type: cross Abstract: While mechanistic interpretability (MI) has produced important insights into neural network internals, the field has yet to establish a standardized s

arXiv:2606.00191v1 Announce Type: cross Abstract: Recent end-to-end (E2E) autonomous driving policies achieve high driving scores in closed-loop simulations. Yet it remains unclear whether these polic

arXiv:2606.01112v1 Announce Type: new Abstract: Heterogeneous marine robotic systems composed of an unmanned surface vehicle (USV) and a hybrid remotely operated vehicle (HROV) have shown great potent

arXiv:2605.31593v1 Announce Type: cross Abstract: Language models can find thousands of severe software vulnerabilities, and agents are increasingly being misused for cyberattacks. To avoid detection,

arXiv:2605.31121v1 Announce Type: cross Abstract: Outdoor vision-language navigation (VLN) in long-range, open-world environments is frequently disrupted by semantic-cue interruptions, where informati

arXiv:2605.30208v1 Announce Type: cross Abstract: AI-assisted coding tools have altered software production. At Meta, significant lines of code per human-landed diff grew by 105.9% year over year and

arXiv:2605.30273v1 Announce Type: cross Abstract: Large language models (LLMs) show promise in generating supportive responses for mental health queries, but improving their usefulness, empathy, and s

arXiv:2605.27763v1 Announce Type: new Abstract: Safety evaluations of language models often treat serving configuration as fixed background infrastructure, but batch condition is an untested treatment

arXiv:2605.28330v1 Announce Type: new Abstract: Chance-constrained Model Predictive Path Integral (MPPI) control is increasingly adopted for navigation in dynamic environments to explicitly bound coll

arXiv:2604.01604v2 Announce Type: replace Abstract: While modern LLMs are aligned to refuse harmful requests, it is essential to understand the underlying mechanistic basis of this refusal behavior fo

arXiv:2605.27494v1 Announce Type: cross Abstract: Modern retrieval-augmented generation(RAG) deployments increasingly rely on caching to reduce token cost and time-to-first-token(TTFT). Prefix-level K

arXiv:2605.28617v1 Announce Type: new Abstract: LLM agents increasingly act by writing code, yet a split persists between the runtime that drives the agent and the code the model writes. The runtime o

arXiv:2605.28591v1 Announce Type: cross Abstract: The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings. Prior work has identified tes

Illinois' House of Representatives passed SB 315, a landmark bill requiring frontier AI companies like OpenAI and Anthropic to create, publish and annually update plans addressing severe or catastroph

arXiv:2605.06213v2 Announce Type: replace Abstract: Evaluating large language models (LLMs) today rests on fixed benchmarks that apply the same set of items to any model, producing ceiling and floor e

arXiv:2605.26577v1 Announce Type: cross Abstract: Learning-based methods for synthesizing controllers have gained popularity due to their high expressiveness and strong empirical performance. However,

arXiv:2605.26542v1 Announce Type: cross Abstract: Tool-using agents increasingly operate in open-ended deployment environments, where they compose file systems, web APIs, code interpreters, and enterp

arXiv:2603.25415v2 Announce Type: replace Abstract: Semantic world models enable embodied agents to reason about objects, relations, and spatial context beyond purely geometric representations. In Org

arXiv:2605.26625v1 Announce Type: new Abstract: We present a provably safe sampling-based motion planning algorithm for robotic systems affected by random disturbances of unknown distribution. We cons

arXiv:2602.04599v2 Announce Type: replace Abstract: We propose stochastic decision horizons (SDH), a theoretically grounded framework for solving constrained RL problems with every-step constraint sat

arXiv:2510.10185v2 Announce Type: replace-cross Abstract: Large language models are increasingly being assembled into medical multi-agent systems that emulate multidisciplinary consultation through sp

arXiv:2605.24926v1 Announce Type: new Abstract: Runtime fairness is not a one-time constraint but a dynamic property evaluated over a sequence of decisions. To ensure fairness at runtime, it is necess

arXiv:2605.25258v1 Announce Type: cross Abstract: Recommender systems generally optimises user engagement, but this approach is dangerous in mental health contexts. When vulnerable users show signs of

arXiv:2605.24649v1 Announce Type: cross Abstract: Recurrent Neural Networks (RNNs) can learn to predict Signal Temporal Logic (STL) verdicts online from partial trajectories, but deploying them as run

arXiv:2605.24004v1 Announce Type: new Abstract: Large language models (LLMs) are promising for autonomous driving, but semantics-only decision policies can yield physically unsafe behavior in dynamic

arXiv:2605.25095v1 Announce Type: new Abstract: Autonomous driving stacks must pick one trajectory from a multi-modal candidate set; choosing by model confidence ignores safety, traffic-law, and comfo

arXiv:2605.25673v1 Announce Type: cross Abstract: Security evaluations inherently depend on stable identifiers. Any finding, audit, or regulatory decision must remain attached to the specific artifact

arXiv:2605.23915v1 Announce Type: cross Abstract: The Intelligent Driver Model (IDM) is a cornerstone of Adaptive Cruise Control (ACC), valued for its interpretable parameters and effectiveness in car

arXiv:2510.11195v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) increases the reliability and trustworthiness of the LLM response and reduces hallucination by eliminatin

arXiv:2605.22600v1 Announce Type: new Abstract: Motion planning for autonomous driving must account for multi-modal uncertainty in both the intentions and trajectories of surrounding vehicles. Handlin

arXiv:2605.21935v1 Announce Type: new Abstract: Safe manipulation-oriented navigation for humanoid robots requires scene memory that remains reliable under locomotion-induced perceptual distortion, en

arXiv:2507.05660v3 Announce Type: replace-cross Abstract: Customizing Large Language Models (LLMs) on untrusted datasets poses severe risks of injecting toxic behaviors. In this work, we introduce Opt

arXiv:2605.22748v1 Announce Type: new Abstract: Autonomous systems have achieved superhuman performance in isolation or simulation, yet they remain brittle in shared, dynamic real-world spaces. This f

arXiv:2605.21139v1 Announce Type: new Abstract: Current end-to-end autonomous driving models are fundamentally constrained by the behavioral cloning ceiling of imitation learning. While reinforcement

arXiv:2605.20654v1 Announce Type: new Abstract: While Large Language Models (LLMs) demonstrate remarkable capabilities, they remain susceptible to sophisticated, multi-step jailbreak attacks that circ

arXiv:2503.04929v3 Announce Type: replace-cross Abstract: Planning and control for high-dimensional robot manipulators in cluttered dynamic environments require computational efficiency and robust saf

arXiv:2605.18988v1 Announce Type: cross Abstract: The expansion of Multimodal Large Language Models (MLLMs) and their integration into autonomous agentic workflows has introduced a non-stationary atta

arXiv:2605.16993v1 Announce Type: cross Abstract: Current clinical artificial intelligence (AI) systems are evaluated almost exclusively on clean, standardised, English-language inputs, conditions tha

arXiv:2605.17304v1 Announce Type: cross Abstract: LLM context is not just tokens; it is a set of commitments. Long-running conversations accumulate goals, constraints, decisions, preferences, tool res

arXiv:2605.16406v1 Announce Type: new Abstract: Night-time pedestrian detection remains challenging because labelled night-time data are limited and large illumination differences make daytime-only tr

arXiv:2605.16858v1 Announce Type: cross Abstract: Autonomous Vehicles (AVs) must make reliable decisions in dense urban environments where pedestrian behavior is variable, sometimes abnormal, and ofte

arXiv:2605.17618v1 Announce Type: new Abstract: Autism Spectrum Disorder (ASD) is characterized by challenges with social interaction and communication and by restricted or repetitive patterns of thou

arXiv:2605.18719v1 Announce Type: new Abstract: Diffusion models have been widely studied for removing unsafe content learned during pre-training. Existing methods require expensive supervised data, e

arXiv:2605.16746v1 Announce Type: new Abstract: LLM agents increasingly rely on persistent state, including transcripts, summaries, retrieved context, and memory buffers, to support long-horizon inter