AI safety and alignment

Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.

10,646 stories · RSS feed

Hugging Face Trending Papers
Jun 18

HumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretraining

Embodied foundation models are expected to benefit from data scaling like large language models, but face a much tighter data bottleneck. Teleoperated real-robot trajectories remain the dominant pretraining source due to their precise action supervision and embodiment alignment, yet their scalability is limited by high collection cost, acquisition difficulty, and low behavioral and environmental diversity.

Hugging Face Trending Papers
Jun 18

See-and-Reach: Precise Vision-Language Navigation for UAVs within the Field of View

UAV Vision-Language Navigation (UAV-VLN) is typically formulated as a holistic search-and-reach problem, where long-range target discovery and final target approach are optimized and evaluated jointly. This formulation makes it difficult to assess a critical capability of aerial embodied agents, namely whether a UAV can accurately ground a visible target and translate vision-language evidence into precise 3D motion once the target enters its field of view.

arXiv AI
Jun 18

Improving Scientific Document Retrieval with Academic Concept Index

arXiv:2601. 00567v2 Announce Type: replace-cross Abstract: Adapting general-domain retrievers to scientific domains is challenging due to the scarcity of large-scale domain-specific relevance annotations and the substantial mismatch in vocabulary and information needs.

By Jeyun Lee, Junhyoung Lee, Wonbin Kweon, Bowen Jin, Yu Zhang, Susik Yoon, Dongha Lee, Hwanjo Yu, Jiawei Han, Seongku Kang
arXiv AI
Jun 18

TRIDENT: Breaking the Hybrid-Safety-Physics Coupling for Provably Safe Multi-Agent Reinforcement Learning

arXiv:2606. 18308v1 Announce Type: cross Abstract: Safe coordination in networked cyber-physical systems forces learning algorithms to simultaneously handle hybrid discrete-continuous actions, hard training-time safety constraints, and physics-governed dynamics.

By Zijie Meng, Ziwei Li, Yufei Liu, Zhiyu Li, Jiyuan Liu, Wenhua Nie, Bingcai Wei, Miao Zhang
arXiv Machine Learning
Jun 18

Benchmarking Physics-Informed Time-Series Models for Operational Global Station Weather Forecasting

arXiv:2406. 14399v4 Announce Type: replace Abstract: The development of Time-Series Forecasting (TSF) models is often constrained by the lack of comprehensive datasets, especially in Global Station Weather Forecasting (GSWF), where existing datasets are small, temporally short, and spatially sparse.

By Tao Han, Zhibin Wen, Zhenghao Chen, Dazhao Du, Song Guo, Lei Bai
arXiv Machine Learning
Jun 18

Generalised Eigenvalue Geometry of Semantic Adversarial Attacks

arXiv:2606. 19212v1 Announce Type: cross Abstract: Recent empirical work shows that semantically equivalent paraphrases can fool financial sentiment classifiers: although a paraphrase remains close to the original under a strong reference embedding, it may shift the target model's representation enough to change the predicted class.

By Martin Anthony, Kaveh Salehzadeh Nobari
arXiv Machine Learning
Jun 18

Fair Online Resource Allocation

arXiv:2606. 18679v1 Announce Type: cross Abstract: We study the problem of fair online resource allocation, motivated by applications such as refugee resettlement and airline scheduling, where agents arrive sequentially and must be assigned to facilities with limited capacities.

By Christopher En, Yuri Faenza, Andrea Lodi, Gonzalo Mu\~noz