safety

The OpenAI Academy page on 'Responsible and Safe Use of AI' is a guidance resource focused on best practices for using ChatGPT responsibly in professional and personal settings. It emphasizes that ...

arXiv:2604.06628v1 Announce Type: new Abstract: A prevailing narrative in LLM post-training holds that supervised finetuning (SFT) memorizes while reinforcement learning (RL) generalizes. We revisit t

arXiv:2604.06378v1 Announce Type: cross Abstract: In many real-world settings, institutions can and do adjust the consequences attached to algorithmic classification decisions, such as the size of fin

arXiv:2604.08536v1 Announce Type: new Abstract: We introduce RewardFlow, an inversion-free framework that steers pretrained diffusion and flow-matching models at inference time through multi-reward La

arXiv:2604.07774v1 Announce Type: cross Abstract: This paper focuses on embodied task planning, where an agent acquires visual observations from the environment and executes atomic actions to accompli

arXiv:2604.07331v1 Announce Type: cross Abstract: Scaling up robot learning will likely require human data containing rich and long-horizon interactions in the wild. Existing approaches for collecting

arXiv:2604.08034v1 Announce Type: new Abstract: Image registration is a fundamental task that aligns anatomical structures between images. While CNNs perform well, they lack rotation equivariance - a

arXiv:2604.07644v1 Announce Type: new Abstract: We present GPU-SLS, a GPU-parallelized framework for safe, robust nonlinear model predictive control (MPC) that scales to high-dimensional uncertain rob

arXiv:2604.08541v1 Announce Type: cross Abstract: Multimodal Mixture-of-Experts (MoE) models have achieved remarkable performance on vision-language tasks. However, we identify a puzzling phenomenon t

arXiv:2407.04183v4 Announce Type: replace Abstract: Large language models (LLMs) are trained on broad corpora and then used in communities with specialized norms. Is providing LLMs with community rule

arXiv:2604.08243v1 Announce Type: new Abstract: Although Large Language Models (LLMs) demonstrate remarkable reasoning capabilities, inherent social biases often cascade throughout the Chain-of-Though

arXiv:2604.03128v2 Announce Type: replace Abstract: On-policy distillation (OPD) has become a popular training paradigm in the LLM community. This paradigm selects a larger model as the teacher to pro

arXiv:2604.08153v1 Announce Type: new Abstract: Unmanned Aerial Vehicles (UAVs) have emerged as a key enabler technology for data collection from Internet of Things (IoT) devices. However, effective d

arXiv:2604.08147v1 Announce Type: cross Abstract: Recent advances in audio-visual representation learning have shown the value of combining contrastive alignment with masked reconstruction. However, j

arXiv:2509.26036v3 Announce Type: replace Abstract: While Contrastive Language-Image Pretraining (CLIP) excels at zero-shot tasks by aligning image and text embeddings, its performance in few-shot cla

arXiv:2604.07936v1 Announce Type: new Abstract: Stain variability is a pervasive source of distribution shift and potential shortcut learning in renal pathology AI. We ask whether lupus nephritis glom

arXiv:2604.08544v1 Announce Type: cross Abstract: Robotic manipulation with deformable objects represents a data-intensive regime in embodied learning, where shape, contact, and topology co-evolve in

arXiv:2504.13378v2 Announce Type: replace-cross Abstract: Generating high-quality, photorealistic textures for 3D human avatars remains a fundamental yet challenging task in computer vision and multim

arXiv:2604.06523v1 Announce Type: cross Abstract: Quantum operations on pure states can be fully represented by unitary matrices. Variational quantum circuits, also known as quantum neural networks, e

arXiv:2503.02642v3 Announce Type: replace-cross Abstract: In both machine learning and in computational neuroscience, plasticity in functional neural networks is frequently expressed as gradient desce

arXiv:2604.08508v1 Announce Type: new Abstract: This paper presents a sim-to-real approach that enables legged robots to dynamically manipulate large and heavy objects with whole-body dexterity. Our k

arXiv:2604.06375v1 Announce Type: new Abstract: AI-driven symptom analysis systems face persistent challenges in reliability, interpretability, and hallucination. End-to-end generative approaches ofte

arXiv:2604.07513v1 Announce Type: cross Abstract: AI-based persona simulation -- often referred to as digital twin simulation -- is increasingly used for market research, recommender systems, and soci

arXiv:2604.08423v1 Announce Type: new Abstract: What are the limits of controlling language models via synthetic training data? We develop a reinforcement learning (RL) primitive, the Dataset Policy G

arXiv:2604.04563v2 Announce Type: replace-cross Abstract: Recent advances in vision--language pretraining have enabled strong medical foundation models, yet most analyze radiographs in isolation, over

arXiv:2604.07754v1 Announce Type: cross Abstract: The deployment of large language models (LLMs) raises significant ethical and safety concerns. While LLM alignment techniques are adopted to improve m

arXiv:2604.06436v2 Announce Type: cross Abstract: We prove that no continuous, utility-preserving wrapper defense-a function D: Xo X that preprocesses inputs before the model sees them-can make al

arXiv:2604.06217v1 Announce Type: cross Abstract: The foundation model era -- roughly 2020 to 2025 -- is over. The forces that defined it have inverted. Open source models have reached frontier perfor

arXiv:2604.06377v1 Announce Type: cross Abstract: We investigate whether post-trained capabilities can be transferred across models without retraining, with a focus on transfer across different model

The reaction people are having to AIs that can find bugs in code is fascinating. Finally, we have the capacity to fix the crisis in computer security we’ve had for decades, and everyone is treating it

arXiv:2604.07921v1 Announce Type: new Abstract: We present a large-scale survey of sustainability communication and motivation in robotics research. Our analysis covers nearly 50,000 open-access paper

arXiv:2604.06621v1 Announce Type: cross Abstract: Dr. David Blackwell was a mathematician and statistician of the first rank, whose contributions to statistical theory, game theory, and decision theor

this from @Kasparov63 applies to the AI autocrats as well. “he would never sell my personal conversations to the government.” oh, yes, he would. I will point out preemptively that one of the autocrat'

This is despicable. Satanic maybe. So AI can talk your kids into suicide and there's nothing you can do about it. Join MAMA and be a part of the future we all want and deserve. Mothers Against Media A

To a degree that may surprise some people, I agree with much of this* from @deanwball and would only add that you don’t have to believe that AGI is remotely close to want to find—ASAP—a regulatory reg

Today we visited Japan's hottest AI startup @SakanaAILabs🎏🇯🇵! We met their research scientists and discussed the implications and impact of some their works like 'The AI scientist' and 'Continous Thou

arXiv:2604.06205v1 Announce Type: cross Abstract: The growth of online platforms and user content requires strong content moderation systems that can handle complex inputs from various media types. Wh

arXiv:2604.06831v1 Announce Type: cross Abstract: Current LLM-based services typically require users to submit raw text regardless of its sensitivity. While intuitive, such practice introduces substan

arXiv:2506.05171v3 Announce Type: replace-cross Abstract: Embodied AI systems, comprising AI models and physical plants, are increasingly prevalent across various applications. Due to the rarity of sy

arXiv:2604.06274v1 Announce Type: cross Abstract: In recent years, the pace of development of information technology in various areas has increased drastically, forcing cybersecurity specialists to co

arXiv:2604.06610v1 Announce Type: cross Abstract: Decentralised online learning enables runtime adaptation in cyber-physical multi-agent systems, but when operating conditions change, learned policies

arXiv:2604.06728v1 Announce Type: cross Abstract: Multimodal sarcasm detection (MSD) aims to identify sarcastic intent from semantic incongruity between text and image. Although recent methods have im

arXiv:2604.08168v1 Announce Type: new Abstract: Vision-language-action (VLA) models have advanced robot manipulation through large-scale pretraining, but real-world deployment remains challenging due

arXiv:2604.06502v1 Announce Type: new Abstract: Vision-Language Models (VLMs) face significant safety vulnerabilities from malicious prompt attacks due to weakened alignment during visual integration.

We are not getting to the G in Artificial General Intelligence; we are getting to (impressive) advances in particular areas where particular (verifiable) techniques can be used, on problems with advan

arXiv:2604.06177v1 Announce Type: cross Abstract: Specialized web tasks in finance, biomedicine, and pharmaceuticals remain challenging due to missing domain priors: queries drift, evidence is noisy,