safety

arXiv:2506.05412v3 Announce Type: replace-cross Abstract: Where someone looks is a nonverbal communication cue that children and adults readily use. How well can Vision-Language Models (VLMs) infer ga

arXiv:2604.27656v1 Announce Type: cross Abstract: To preserve previously learned representations, continual learning systems must strike a balance between plasticity, the ability to acquire new knowle

who's ready to dance? 😆🕺🎶 uploaded 11 new favorite @suno songs to @spotify [search: 'captain yohei'] 💿 Captain Yohei Vol 1. 💿 ♫ Don't Go in the Office [hard rock] ♫ Nine-Nine-Six [hip-hop/rap] ♫ Fog F

arXiv:2604.26379v1 Announce Type: new Abstract: Reliable seizure detection in mouse models is essential for preclinical epilepsy research, yet manual review of synchronized video-EEG recordings is lab

arXiv:2604.25963v1 Announce Type: new Abstract: Vehicle platooning has attracted increasing attention as a promising approach to improve traffic efficiency, energy consumption, and roadway safety thro

arXiv:2604.25933v1 Announce Type: cross Abstract: As large language models (LLMs) increasingly generate and process clinical text, scalable evaluation has become critical. LLM-as-a-Judge (LaaJ), which

arXiv:2510.08049v3 Announce Type: replace-cross Abstract: Although Large Language Models (LLMs) exhibit advanced reasoning ability, conventional alignment remains largely dominated by outcome reward m

arXiv:2505.17342v2 Announce Type: replace Abstract: Safe Reinforcement Learning (SafeRL) is the subfield of reinforcement learning that explicitly deals with safety constraints during the learning and

arXiv:2505.10924v4 Announce Type: replace-cross Abstract: Recently, AI-driven interactions with computing devices have advanced from basic prototype tools to sophisticated, LLM-based systems that emul

arXiv:2604.26779v1 Announce Type: cross Abstract: RL post-training of frontier language models is increasingly bottlenecked by autoregressive rollout generation, making rollout acceleration a central

arXiv:2604.25965v1 Announce Type: cross Abstract: Deep learning models are widely deployed in safety-critical domains, but remain vulnerable to adversarial attacks. In this paper, we study the adversa

alignment in 2016: obviously any real AI will be made inside a faraday cage magnetically suspended in a 10×10×10 cube of telekill alloy alignment in 2026: yeah we can not make it stop talking about go

arXiv:2604.26637v1 Announce Type: cross Abstract: Annotating long-horizon robotic demonstrations with precise temporal action boundaries is crucial for training and evaluating action segmentation and

arXiv:2604.26689v1 Announce Type: cross Abstract: Skill libraries in deployed robotic systems are continually updated through fine-tuning, fresh demonstrations, or domain adaptation, yet existing type

arXiv:2604.26453v1 Announce Type: new Abstract: Audio-visual deepfakes have reached a level of realism that makes perceptual detection unreliable, threatening media integrity and biometric security. W

arXiv:2604.26577v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly considered for deployment as the control component of robotic health attendants, yet their safety in this

arXiv:2604.26250v1 Announce Type: new Abstract: While Vision-Language Models (VLMs) have achieved state-of-the-art performance in general visual tasks, their perceptual robustness remains remarkably b

Big Tech companies are projected to spend approximately $700 billion on AI infrastructure and development in the current year, a figure that AI researcher and entrepreneur Gary Marcus has criticized a

arXiv:2604.26312v1 Announce Type: new Abstract: Public opinion towards the Free Nutritious Meal Program (MBG) on YouTube social media reflects diverse community responses. This study applies the Long

arXiv:2604.26172v1 Announce Type: cross Abstract: We develop a physics-informed learning framework for energy-shaping control of port-Hamiltonian (pH) systems from trajectory data. The proposed approa

arXiv:2512.08982v2 Announce Type: replace-cross Abstract: Retinex-based low-light image enhancement benefits from separating reflectance and illumination, yet recent generative approaches often rely o

arXiv:2604.26024v1 Announce Type: cross Abstract: Class-level evaluation can conceal substantial performance disparities across subconcepts within the same class, causing models that perform well on a

arXiv:2506.13116v2 Announce Type: replace-cross Abstract: Crime hotspot prediction is critical for ensuring urban safety and effective law enforcement, it remains challenging due to complex spatial de

This post discusses the liability and accountability questions that arise when problems occur in AI-automated workplaces, exploring who bears responsibility—whether the AI developer, the employer, the

arXiv:2604.26494v1 Announce Type: cross Abstract: Generative AI tools are widely used by youth and have introduced new privacy and safety challenges. While prior research has explored youth's safety i

arXiv:2401.02458v3 Announce Type: replace-cross Abstract: The advent of foundation models (FMs) as an emerging suite of AI techniques has struck a wave of opportunities in computational healthcare. Th

arXiv:2604.03905v2 Announce Type: replace-cross Abstract: Heterogeneity is a defining feature of deployed multi-robot teams: platforms often differ in sensing modalities, ranges, fields of view, and f

Dear @elonmusk, If you still genuinely care about AI safety, you can’t let the Trump administration leave the AI industry almost entirely unregulated. You just can’t. - Gary The judge just instructed

arXiv:2604.26503v1 Announce Type: new Abstract: Diffusion models have achieved remarkable success in synthesizing complex static and temporal visuals, a breakthrough largely driven by Classifier-Free

arXiv:2604.26256v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a critical paradigm for LLM post-training, yet the rollout phase -- accounting for 50--80% of total step time --

arXiv:2604.26188v1 Announce Type: new Abstract: The growing reliance of machine learning models in high-stakes, highly regulated domains such as finance and insurance has created a growing tension bet

arXiv:2604.26106v1 Announce Type: new Abstract: Forecasting benchmarks produce accuracy leaderboards but little insight into why some forecasters are more accurate than others. We introduce Bench to t

arXiv:2604.26051v1 Announce Type: cross Abstract: The increasing number of satellites has improved the temporal resolution of Earth observation, making satellite-based flood mapping a promising approa

arXiv:2604.26170v1 Announce Type: new Abstract: Adapting large language models (LLMs) to a targeted task efficiently and effectively remains a fundamental challenge. Such adaptation often requires ite

arXiv:2510.26841v2 Announce Type: replace-cross Abstract: Federated Learning (FL) enables collaborative model training without data sharing, yet participants face a fundamental challenge, e.g., simult

arXiv:2504.09925v3 Announce Type: replace Abstract: We introduce FLARE, a family of vision language models (VLMs) with a fully vision-language alignment and integration paradigm. Unlike existing appro

For better or worse, regulation for closed-source models served by a few (quite large) companies is easy. It is not as easy to imagine how you regulate open-source models that can be served by a range

arXiv:2604.26052v1 Announce Type: new Abstract: Safety evaluations of large language models (LLMs) typically report binary outcomes such as attack success rate, refusal rate, or harmful/not-harmful re

arXiv:2604.26530v1 Announce Type: cross Abstract: Over the past 25 years, I have been involved in some intriguing developments in the foundations of physics, exploring the quantum reality problem, the

arXiv:2508.06550v3 Announce Type: replace-cross Abstract: Bid shading plays a crucial role in Real-Time Bidding (RTB) by adaptively adjusting the bid to avoid advertisers overspending. Existing mainst

arXiv:2601.13942v2 Announce Type: replace-cross Abstract: Large Multimodal Models (LMMs) have achieved remarkable success in visual understanding, yet they struggle with knowledge-intensive queries in

arXiv:2512.06565v2 Announce Type: replace Abstract: We present GNC-Pose, a fully learning-free monocular 6D object pose estimation pipeline for textured objects that combines rendering-based initializ

arXiv:2509.16591v2 Announce Type: replace Abstract: Using entropy as a measure of heterogeneity to guide optimization has emerged as a crucial research direction in Reinforcement Learning for LLMs. Ho

arXiv:2604.26120v1 Announce Type: new Abstract: Behavioral logs provide rich signals for user modeling, but are noisy and interleaved across diverse intents. Recent work uses LLMs to generate interpre

arXiv:2604.26504v1 Announce Type: new Abstract: Navigating quadruped robots in unstructured 3D environments poses significant challenges, requiring goal-directed motion, effective exploration to escap

arXiv:2504.13529v4 Announce Type: replace Abstract: Existing black-box portfolio management systems are prevalent in the financial industry due to commercial and safety constraints, though their perfo