Knowledge catalogue
arXiv:2608.18116v1 Announce Type: new Abstract: Vision-language models enable zero-shot classification through natural language prompts, but performance is sensitive to prompt formulation, especially
arXiv:2608.16893v1 Announce Type: cross Abstract: Expert surveys are widely used in security research to study practitioner workows and decision-making, yet recruiting domain experts - especially in S
arXiv:2608.17070v1 Announce Type: new Abstract: With the growing deployment of machine learning models, formal guarantees of the robustness and fairness of these models have become increasingly import
arXiv:2607.16660v2 Announce Type: replace-cross Abstract: The increasing adoption of Large Language Models (LLMs) as AI components in modern software systems introduces distinct security risks to the
arXiv:2603.24126v2 Announce Type: replace Abstract: When language models are trained by reinforcement learning (RL) to write probabilistic programs, they can artificially inflate their marginal-likeli
arXiv:2608.17178v1 Announce Type: new Abstract: Video self-supervised learning through masked spatiotemporal prediction has emerged as a promising paradigm for learning feature representations from un
arXiv:2606.13113v2 Announce Type: replace-cross Abstract: Underactuated spacecraft faces controllability limitations and heightened sensitivity to environmental disturbances, complicating attitude man
arXiv:2608.17779v1 Announce Type: new Abstract: Controlling an autonomous vehicle at the limits of handling is a challenging task. Due to external influences, such as road conditions or weather, a veh
arXiv:2608.17038v1 Announce Type: new Abstract: Autonomous navigation in complex outdoor terrains presents critical challenges for unmanned ground vehicles (UGVs) due to the inherent disconnect betwee
arXiv:2608.17176v1 Announce Type: cross Abstract: An AI audit record is useful only if its durability and trust boundary are explicit. Returning a guarded decision before any durable write minimizes l
arXiv:2608.17084v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) increasingly answer questions whose correctness depends on visual, textual, temporal, acoustic, document, chart
arXiv:2608.17275v1 Announce Type: cross Abstract: AI agents increasingly act rather than merely read: across the Model Context Protocol (MCP) ecosystem, the share of deployed tools that modify externa
arXiv:2608.15380v1 Announce Type: cross Abstract: In ROS 2 systems using DDS, a single slow subscriber on a RELIABLE topic can cause backpressure that degrades throughput and latency for all subscribe
arXiv:2608.15591v1 Announce Type: new Abstract: Large Language Model (LLM) agents deployed in production environments face a fundamental tension: the agent's behavior is frozen at deployment time, whi
As models become more capable, the risks associated with developing and testing them internally also grow. We temporarily paused reinforcement learning (RL) training on our latest models intended for
arXiv:2608.14766v1 Announce Type: new Abstract: Uncertainty estimation is critical for the safe clinical deployment of deep learning in medical image segmentation, with aleatoric uncertainty theoretic
arXiv:2608.16773v1 Announce Type: new Abstract: Prototype-based neural networks are hailed as interpretable-by-design architectures. Recently, Abductive Latent Explanations (ALE) were introduced to pr
arXiv:2608.16785v1 Announce Type: new Abstract: This paper proposes a calibration-free framework for reliably and effectively estimating vehicle speeds from monocular videos, without relying on roadwa
arXiv:2608.16068v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as agents that rely on system prompts to use tools and complete tasks. Such deployments impose
arXiv:2608.14630v1 Announce Type: cross Abstract: Human decision-making is often shaped by a range of well-documented cognitive biases. As large language models (LLMs) become increasingly integrated i
arXiv:2608.14666v1 Announce Type: new Abstract: Unsupervised fault detection in industrial systems is dominated by reconstruction based methods that monitor individual sensor marginal distributions. T
arXiv:2412.07672v2 Announce Type: replace-cross Abstract: Large language models (LLMs) remain vulnerable to jailbreak attacks in which adversarial prompts induce harmful outputs. Existing defenses oft
arXiv:2512.22983v2 Announce Type: replace Abstract: Recent advances in vision, language, and multimodal learning have significantly accelerated progress in robotic foundation models, with robotic mani
arXiv:2608.14825v1 Announce Type: cross Abstract: Frontier LLM agents increasingly transact on behalf of separate principals, often using natural language rather than structured APIs. Much of the safe
arXiv:2608.16476v1 Announce Type: new Abstract: Learning embodied urban navigation policies from real-world data is constrained by the cost of task-specific data collection and the limited coverage of
arXiv:2608.15762v1 Announce Type: cross Abstract: Container-granularity scheduling leaves abundant short-lived idle slices within containers unexploited. Reallocating containers is too heavyweight to
arXiv:2608.16837v1 Announce Type: cross Abstract: Humanoid robots hold great promise as general-purpose agents in human-centered environments, yet generalist vision-language-action (VLA) foundation mo
I would like to publicly commend @sama and @OpenAI for this taking it at face value. It is very clear that strange and perhaps dangerous things are happening and our systems are not ready for this. Mo
If alignment issues are becoming big enough that OpenAI is willing to commit 20% of research inference compute to chain-of-thought monitoring, that suggests that alignment issues are becoming a pretty
arXiv:2608.14629v1 Announce Type: cross Abstract: As Large Language Models (LLMs) become the mainstay for information retrieval and summarization tasks, ensuring that they are always non-partisan and
arXiv:2608.16177v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as agents that operate equipment, execute instructions, and act inside institutional hierarchie
arXiv:2608.16834v1 Announce Type: cross Abstract: We demonstrate that AI models are broadly susceptible to a phenomenon we call model hypnosis, in which individually weak and seemingly irrelevant cues
arXiv:2608.15234v1 Announce Type: cross Abstract: Automated five-stage diabetic retinopathy (DR) grading requires more than high accuracy alone. Medical-grade deployment calls for lesion-aware preproc
arXiv:2608.16888v1 Announce Type: new Abstract: The development of safe and beneficial AI requires that systems can learn and act in accordance with human preferences. However, explicitly specifying t
arXiv:2608.16155v1 Announce Type: new Abstract: In over-the-counter corporate bond markets, dealers compete for client trades by quoting bid and ask prices. Tighter quotes attract more business, but a
arXiv:2608.16237v1 Announce Type: cross Abstract: Building operations are energy-inefficient. Artificial Intelligence (AI)-driven control systems promise benefits through optimization and predictive c
arXiv:2608.15741v1 Announce Type: new Abstract: The one-stage planner YOPO maps a single depth image and the robot state directly to a set of candidate trajectories, trained by backpropagating through
arXiv:2411.19289v4 Announce Type: replace Abstract: Dynamic visual-inertial odometry (VIO) requires reliable suppression of motion-corrupted measurements, yet prior semantic-assisted approaches depend
arXiv:2608.16710v1 Announce Type: new Abstract: As autonomous vehicles (AVs) approach Level 4 and Level 5 operational capability [SAE International, 2018], their on- board decision systems must handle
arXiv:2608.15594v1 Announce Type: new Abstract: Multi-turn jailbreak attacks have emerged as a critical safety threat to LLMs, as harmful objectives are decomposed across a sequence of apparently beni
arXiv:2608.15391v1 Announce Type: new Abstract: Large language model (LLM)-assisted energy-management tools can translate natural-language context into structured grid commands, but syntactic validity
arXiv:2608.16428v1 Announce Type: cross Abstract: Artificial intelligence systems often disclose uncertainty, yet they rarely make clear what response that uncertainty should trigger. Most uncertainty
arXiv:2608.14886v1 Announce Type: new Abstract: Retrieval quality in RAG systems is commonly reported as a single aggregate score, which can hide large differences across query types and language cond
arXiv:2608.14332v1 Announce Type: cross Abstract: Reinforcement learning is promising for autonomous urban driving, but long-horizon goal-directed navigation asks a policy to acquire several competing
arXiv:2608.14082v1 Announce Type: new Abstract: Autonomous navigation in cluttered environments is hampered by partial observability and dynamic constraints. This paper presents PILOT, a constraint-aw
Some thoughts on Dario’s post: 1. Dario does not actually address Gavin Baker’s account of what he said – something he could easily deny if it were inaccurate. 2. Dario claims his critics live in a “b
arXiv:2608.14024v1 Announce Type: new Abstract: Vision-language-action (VLA) models for autonomous driving jointly produce scene interpretation, language-based reasoning, and driving trajectories. Exi
arXiv:2608.14177v1 Announce Type: cross Abstract: Deep spatiotemporal models integrating graph convolutions and attention mechanisms have demonstrated excellent performance in network-level traffic fl
OpenAI has shut down the internal team that evaluated whether its AI models could pose “catastrophic risks,” a decision reported by the Financial Times on August 16, 2026. The move was announced via a
The FT reports this weekend that OpenAI quietly disbanded its preparedness team at the end of last month, with responsibilities for individual areas of the preparedness framework distributed across ot
arXiv:2602.11143v3 Announce Type: replace Abstract: Humanoid locomotion has advanced rapidly with deep reinforcement learning (DRL), enabling robust feet-based traversal over uneven terrain. Yet platf
arXiv:2608.13069v1 Announce Type: new Abstract: Large language models (LLMs) are predominantly aligned to function as passive, sycophantic assistants. We challenge this default paradigm by empirically
arXiv:2608.13209v1 Announce Type: cross Abstract: Many operational decisions are sequences of interventions under a cumulative resource limit, such as a maintenance schedule within a crew-hour budget.
arXiv:2608.12373v1 Announce Type: new Abstract: Large language models are increasingly used in strategic and advisory contexts, yet their safety alignment is typically evaluated in English only. We te
arXiv:2608.12615v1 Announce Type: cross Abstract: In-vehicle music can serve as an adaptive interface to enhance driver experience, attention, and well-being. We present Drive-to-Music, a context-awar
arXiv:2506.13452v3 Announce Type: replace-cross Abstract: Background and Objective: As Deep Brain Stimulation (DBS) advances toward directional leads and optimization-based current steering, selecting
arXiv:2608.12645v1 Announce Type: new Abstract: LLM judges have become central infrastructure for model evaluations, online grading, and reward modeling. Judges are typically validated by accuracy on
arXiv:2608.13284v1 Announce Type: new Abstract: Recent advances in teleoperation have enabled robotic manipulators to perform dexterous, human-arm-like motions. However, human operators may fail to av
arXiv:2508.14390v2 Announce Type: replace-cross Abstract: Large language models (LLMs) often express verbal confidence that is poorly aligned with actual correctness, limiting their reliability in saf
arXiv:2608.12395v1 Announce Type: new Abstract: We describe Research Assistant, an internal LLM-based system developed at AstraZeneca to help scientists and clinicians explore biomedical questions acr