paper-with-me

홈 › Papers

\texttt{R$^\textbf{2}$AI}: Towards Resistant and Resilient AI in an Evolving World

2025-09-08 · Youbang Sun, Xiang Wang, Jie Fu, Chaochao Lu, Bowen Zhou arxiv

In this position paper, we address the persistent gap between rapidly growing AI capabilities and lagging safety progress. Existing paradigms divide into `Make AI Safe'', which applies post-hoc alignment and guardrails but remains brittle and reactive, and Make Safe AI'', which emphasizes intrinsic safety but struggles to address unforeseen risks in open-ended environments. We therefore propose \textit{safe-by-coevolution} as a new formulation of the `Make Safe AI'' paradigm, inspired by biological immunity, in which safety becomes a dynamic, adversarial, and ongoing learning process. To operationalize this vision, we introduce \texttt{R$^2$AI} -- \textit{Resistant and Resilient AI} -- as a practical framework that unites resistance against known threats with resilience to unforeseen risks. \texttt{R$^2$AI} integrates \textit{fast and slow safe models}, adversarial simulation and verification through a \textit{safety wind tunnel}, and continual feedback loops that guide safety and capability to coevolve. We argue that this framework offers a scalable and proactive path to maintain continual safety in dynamic environments, addressing both near-term vulnerabilities and long-term existential risks as AI advances toward AGI and ASI.

📄 PDF Abstract BibTeX arXiv:2509.06786

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs

2022-02-17 · Ming Jin, Yu Zheng, Yuan-Fang Li, Siheng Chen 외

Multivariate time series forecasting has long received significant attention in real-world applications, such as energy consumption and traffic prediction. While recent methods demonstrate good forecasting abilities, the…

Multivariate Time Series ForecastingTime SeriesTime Series AnalysisTime Series Forecasting+1

$ρ$-$\texttt{EOS}$: Training-free Bidirectional Variable-Length Control for Masked Diffusion LLMs

2026-01-30 · Jingyi Yang, Yuxian Jiang, Jing Shao arxiv

Beyond parallel generation and global context modeling, current masked diffusion large language models (masked dLLMs, i.e., LLaDA) suffer from a fundamental limitation: they require a predefined, fixed generation length,…

Computational Efficiency

Dispersion Loss Counteracts Embedding Condensation and Improves Generalization in Small Language Models

2026-01-30 · Chen Liu, Xingzhi Sun, Xi Xiao, Alexandre Van Tassel 외 arxiv

Large language models (LLMs) achieve remarkable performance through ever-increasing parameter counts, but scaling incurs steep computational costs. To better understand LLM scaling, we study representational differences …

Knowledge Distillation

Reasoning to Attend: Try to Understand How <SEG> Token Works

2024-12-23 · CVPR 2025 1 · Rui Qian, Xin Yin, Dejing Dou

Current Large Multimodal Models (LMMs) empowered visual grounding typically rely on $\texttt{<SEG>}$ token as a text prompt to jointly optimize the vision-language model (e.g., LLaVA) and the downstream task-specified mo…

Semantic SimilaritySemantic Textual SimilarityVisual Grounding

ORAL: Prompting Your Large-Scale LoRAs via Conditional Recurrent Diffusion

2025-03-31 · Rana Muhammad Shahroz Khan, Dongwen Tang, Pingzhi Li, Kai Wang 외

Parameter generation has emerged as a novel paradigm for neural network development, offering an alternative to traditional neural network training by synthesizing high-quality model weights directly. In the context of L…