safety

weirdly the New York Post (which did that stupid and egregious hatchet job on METR) may well be right about this one OpenAI and Anthropic oversold AI security breaches to pressure feds into protecting

with @Thom_Wolf in sunny italy ☀️chatting about the @huggingface @OpenAI attack, the “tell” that it was an agentic swarm, how misalignment arises in RL, whether agent awareness of evaluation is eviden

arXiv:2609.19398v1 Announce Type: cross Abstract: Spontaneous speech offers a scalable, noninvasive signal for respiratory health assessment, yet interpretable models that generalize across languages

A few thoughts on this: 1) If you’ve only seen clips of this interview, I’d encourage you to watch the full podcast. I push back on plenty of AI hype in it. 2) As I said in the podcast, this example i

arXiv:2609.20162v1 Announce Type: new Abstract: Injecting stochastic noise into a consolidation rule can improve a network's retention of earlier tasks up to an optimal level, then degrade it -- an in

arXiv:2609.19640v1 Announce Type: new Abstract: Croissant is the de facto machine-readable descriptor for ML datasets: JSON-LD over schema.org. Since version 1.1 it also carries data use conditions, r

arXiv:2609.19812v1 Announce Type: new Abstract: Traditional scene understanding focuses on affirmative information objectively present in images. However, in safety-critical domains, comprehending key

Absolutely right Gary. LLMs simply don't understand causality at the level needed to make truly data driven decisions. My work combines Causal AI (using Pearl's Causal Calculus), knowledge graphs, LLM

arXiv:2609.20249v1 Announce Type: new Abstract: Deep knowledge tracing (DKT) models implicitly decide which students an adaptive system believes have mastered a skill, yet almost all evidence on their

arXiv:2609.20301v1 Announce Type: new Abstract: AI agents increasingly orchestrate long-running activities with users, tools, and system resources for days and weeks. To improve agent quality, safety,

arXiv:2609.20761v1 Announce Type: cross Abstract: World Action Models (WAMs) advance beyond conventional visuomotor policies by jointly predicting future world states and robot actions, enabling the p

arXiv:2609.20059v1 Announce Type: cross Abstract: AI systems can strengthen democracy by supporting deliberation at scale by addressing cognitive, social, platform-design, and market-driven frictions,

arXiv:2506.12374v3 Announce Type: replace-cross Abstract: Natural-language manipulation instructions specify the task goal but leave the underlying robot trajectory unspecified. We present AntiGroundi

arXiv:2609.20107v1 Announce Type: new Abstract: Visuomotor policies for multi-fingered dexterous manipulation are highly sensitive to camera viewpoint shifts. To achieve view invariance, recent method

arXiv:2512.13142v5 Announce Type: replace Abstract: People use LLMs for reproductive-health questions, including abortion-related support. A response can sound supportive while answers reinforce harmf

arXiv:2609.20765v1 Announce Type: new Abstract: Radio Frequency(RF)-Fingerprinting is a spectrum monitoring technique that identifies specific transmitters based on hardware impairments imprinted with

arXiv:2609.20098v1 Announce Type: new Abstract: Reliable temporal-difference targets are central to off-policy actor-critic learning. Direct value improvement refines the next-state target with altern

arXiv:2609.19970v1 Announce Type: new Abstract: Predicting cellular responses to perturbations supports the study of gene function, disease mechanisms, and therapeutic strategies. Despite advances in

arXiv:2609.20822v1 Announce Type: cross Abstract: Coding agents have emerged as a promising paradigm for robot manipulation: a language model writes the robot controller as a program, and agents built

arXiv:2609.19976v1 Announce Type: new Abstract: Vision-language-action models tell a robot where to move, but not how hard to push. Contact-rich tasks depend on that second quantity, compliance, yet n

arXiv:2607.09557v2 Announce Type: replace Abstract: Fine grain control and positioning of autonomous underwater vehicles (AUVs) is critical for sampling, maintenance, and survey applications. Traditio

arXiv:2609.19670v1 Announce Type: new Abstract: Direct forecasting has become a standard paradigm for multivariate time-series forecasting because it predicts the full future horizon in a single pass.

arXiv:2609.19512v1 Announce Type: cross Abstract: Robots can recall prior failures without knowing whether recalled evidence remains valid, conflicts with current observations, or is sufficient to gui

arXiv:2609.20691v1 Announce Type: new Abstract: Mapping and monitoring aquatic environments can benefit from hybrid aerial-amphibious drones able to combine flight and water-surface navigation within

arXiv:2609.19801v1 Announce Type: new Abstract: Executable environments enable LLM agents to learn from the consequences of their actions. For embodied agents, those consequences extend beyond whether

arXiv:2609.19367v1 Announce Type: new Abstract: Ensuring intrinsic safety in physical human robot interaction (pHRI) is a critical requirement for social and service robots. While Series Elastic Actua

arXiv:2609.20649v1 Announce Type: cross Abstract: Learning predictive models of contact-rich dexterous manipulation requires dense tactile interaction, but such data are costly to scale on real robots

arXiv:2609.20304v1 Announce Type: new Abstract: A deployed control policy can conceal consequential dynamics changes: an actuator may lose effectiveness without affecting the current task when the pol

arXiv:2609.20715v1 Announce Type: cross Abstract: Agent trajectories record what an agent does and what happens next. Yet standard supervised fine-tuning (SFT) applies loss only to agent-authored acti

arXiv:2609.19830v1 Announce Type: new Abstract: Reinforcement learning for LLM agents involves two distinct optimization di- mensions: how environment feedback is exploited within a trajectory, and ho

arXiv:2609.20008v1 Announce Type: cross Abstract: Gromov--Wasserstein optimal transport (GW-OT) extends classical optimal transport by introducing structure-aware transport cost. This is particularly

arXiv:2409.18457v2 Announce Type: replace Abstract: This paper addresses a special Perspective-n-Point (PnP) problem: estimating the optimal pose to align 3D and 2D shapes in real-time without corresp

arXiv:2609.19399v1 Announce Type: cross Abstract: Computing Nash equilibria of simulation-based cybersecurity games with policy-space response oracles (PSRO) is bottlenecked by payoff estimation: ever

arXiv:2609.20821v1 Announce Type: new Abstract: Embedding spaces define notions of semantic similarity and distance. We study whether those embeddings reflect physical measurements of mass, distance,

arXiv:2609.19375v1 Announce Type: new Abstract: Safety and comfort in human-robot physical in-teractions are essential aspects in the development of social technologies, where natural gestures, such a

even the anti-woke media sure loves this narrative. doesn’t make it true. 'I worked at OpenAI for two years before resigning in 2024. Fears that AI will cause human extinction are real. You should tak

arXiv:2609.19362v1 Announce Type: cross Abstract: We study high-order safety-critical control of quadrotor teams under bounded inputs and pairwise collision-avoidance constraints. Squared-distance bar

arXiv:2609.19863v1 Announce Type: cross Abstract: Navigation world models plan by foresight, predicting the future that each candidate action sequence produces and selecting the best, rather than mapp

Four-byline alert: 🚨 “.. People who have discussed the subject with Mr. Trump .. say his outbursts are rooted in worries that if the artificial intelligence boom .. slows down, the market could crash

arXiv:2609.19413v1 Announce Type: cross Abstract: Robot manipulation policies are improving quickly, and real-robot evaluation remains the standard evidence for that progress. It still relies on a hum

arXiv:2609.19447v1 Announce Type: new Abstract: Robots that follow natural-language instructions in everyday indoor environments must act on incomplete human utterances. Instructions often omit essent

arXiv:2609.19452v1 Announce Type: cross Abstract: Robots are moving out of the structured factory floor and into unstructured environments such as disaster sites, planetary surfaces, and agricultural

arXiv:2609.20016v1 Announce Type: cross Abstract: The EU AI Act (Regulation 2024/1689) imposes technical obligations on high-risk AI providers, yet Articles 8-15 were drafted for predictive AI and lea

Bloomberg: Governor Gavin Newsom signs an EO directing a working group to provide a guide in two months with measures to boost California's AI safety and security laws — California Governor Gavin News

arXiv:2609.19850v1 Announce Type: new Abstract: Actor-critic architecture has been widely used in continuous robot control. However, they rely on learning a value network, introducing additional compu

arXiv:2609.19956v1 Announce Type: new Abstract: Tree-based Monte-Carlo Tree Search (MCTS) duplicates the same state when it is reached through different trajectories, which can waste simulations in st