Buchumschlag

ForesightSafety Bench: A Frontier Risk Evaluation and Governance Framework towards Safe AI

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Tong, Haibo, Zhao, Feifei, Feng, Linghao, Wu, Ruoyu, Chen, Ruolin, Jia, Lu, Zhao, Zhou, Li, Jindong, Li, Tenglong, Lin, Erliang, Yang, Shuai, Lu, Enmeng, Sun, Yinqian, Zhang, Qian, Ruan, Zizhe, Fan, Jinyu, Yue, Zeyang, Wu, Ping, Li, Huangrui, Sun, Chengyi, Zeng, Yi
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Artificial Intelligence Cryptography and Security Computers and Society
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Reinforcement Fine-Tuning of Flow-Matching Policies for Vision-Language-Action Models
von: Lyu, Mingyang, et al.
Veröffentlicht: (2025)

Building Altruistic and Moral AI Agent with Brain-inspired Emotional Empathy Mechanisms
von: Zhao, Feifei, et al.
Veröffentlicht: (2024)

CogToM: A Comprehensive Theory of Mind Benchmark inspired by Human Cognition for Large Language Models
von: Tong, Haibo, et al.
Veröffentlicht: (2026)

Autonomous Alignment with Human Value on Altruism through Considerate Self-imagination and Theory of Mind
von: Tong, Haibo, et al.
Veröffentlicht: (2024)

STEP: A Unified Spiking Transformer Evaluation Platform for Fair and Reproducible Benchmarking
von: Shen, Sicheng, et al.
Veröffentlicht: (2025)

MTDP: A Modulated Transformer based Diffusion Policy Model
von: Wang, Qianhao, et al.
Veröffentlicht: (2025)

Brain-inspired Action Generation with Spiking Transformer Diffusion Policy Model
von: Wang, Qianhao, et al.
Veröffentlicht: (2024)

Multi-compartment Neuron and Population Encoding Powered Spiking Neural Network for Deep Distributional Reinforcement Learning
von: Sun, Yinqian, et al.
Veröffentlicht: (2023)

Spiking World Model with Multi-Compartment Neurons for Model-based Reinforcement Learning
von: Sun, Yinqian, et al.
Veröffentlicht: (2025)

$SpikePack$: Enhanced Information Flow in Spiking Neural Networks with High Hardware Compatibility
von: Shen, Guobin, et al.
Veröffentlicht: (2025)

Safety Instincts: LLMs Learn to Trust Their Internal Compass for Self-Defense
von: Shen, Guobin, et al.
Veröffentlicht: (2025)

Continual Learning of Multiple Cognitive Functions with Brain-inspired Temporal Development Mechanism
von: Han, Bing, et al.
Veröffentlicht: (2025)

FireFly-S: Exploiting Dual-Side Sparsity for Spiking Neural Networks Acceleration with Reconfigurable Spatial Architecture
von: Li, Tenglong, et al.
Veröffentlicht: (2024)

FireFly-T: High-Throughput Sparsity Exploitation for Spiking Transformer Acceleration with Dual-Engine Overlay Architecture
von: Li, Tenglong, et al.
Veröffentlicht: (2025)

FireFly-P: FPGA-Accelerated Spiking Neural Network Plasticity for Robust Adaptive Control
von: Li, Tenglong, et al.
Veröffentlicht: (2026)

Revealing Untapped DSP Optimization Potentials for FPGA-Based Systolic Matrix Engines
von: Li, Jindong, et al.
Veröffentlicht: (2024)

Pushing up to the Limit of Memory Bandwidth and Capacity Utilization for Efficient LLM Decoding on Embedded FPGA
von: Li, Jindong, et al.
Veröffentlicht: (2025)

C-VARC: A Large-Scale Chinese Value Rule Corpus for Value Alignment of Large Language Models
von: Wu, Ping, et al.
Veröffentlicht: (2025)

Super Co-alignment of Human and AI for Sustainable Symbiotic Society
von: Zeng, Yi, et al.
Veröffentlicht: (2025)

SafeMind: Benchmarking and Mitigating Safety Risks in Embodied LLM Agents
von: Chen, Ruolin, et al.
Veröffentlicht: (2025)

Hummingbird: A Smaller and Faster Large Language Model Accelerator on Embedded FPGA
von: Li, Jindong, et al.
Veröffentlicht: (2025)

Brain-inspired and Self-based Artificial Intelligence
von: Zeng, Yi, et al.
Veröffentlicht: (2024)

Reduction of Buchnera with rifampicin impairs the density‐dependent induction of winged morph in pea aphid
von: Erliang Yuan, et al.
Veröffentlicht: (2025)

Parallel Spiking Unit for Efficient Training of Spiking Neural Networks
von: Li, Yang, et al.
Veröffentlicht: (2024)

Supplementary materials for "Melting of the thickened lower crust in the Northern Himalayan Gneiss Domes, Southern Tibet: Further evidence from the ca. 43–40 Ma granite–intermediate rock suite from the Yardoi area"
von: Wu, Hailin, et al.
Veröffentlicht: (2025)

BenchEvolver: Frontier Task Synthesis via Solution-Centric Evolution
von: Wu, Yangzhen, et al.
Veröffentlicht: (2026)

AI Governance InternationaL Evaluation Index (AGILE Index) 2025
von: Zeng, Yi, et al.
Veröffentlicht: (2025)

Learning High-Order Relationships of Brain Regions
von: Qiu, Weikang, et al.
Veröffentlicht: (2023)

Shower formation in the presence of a string-inspired foam in space-time
von: Li, Chengyi
Veröffentlicht: (2025)

Automatic reproducing kernel and regularization for learning convolution kernels
von: Li, Haibo, et al.
Veröffentlicht: (2025)

Weberite Na$_2$MM'F$_7$ (M,M'=Redox-Active Metal) as Promising Fluoride-Based Sodium-Ion Battery Cathodes
von: Lu, Tenglong, et al.
Veröffentlicht: (2023)

Expert Incentives under Partially Contractible States
von: Xia, Zizhe
Veröffentlicht: (2025)

The Global Food Trade Network as a Complex Adaptive System: A Review of Structure, Evolution, and Resilience
von: Li, Zebiao, et al.
Veröffentlicht: (2026)

BrainKnow -- Extracting, Linking, and Synthesizing Neuroscience Knowledge
von: Huangfu, Cunqing, et al.
Veröffentlicht: (2024)

Evidence-Grounded Multi-Agent Planning Support for Urban Carbon Governance via RAG
von: Huang, Yuyan, et al.
Veröffentlicht: (2026)

AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts
von: Li, Keyu, et al.
Veröffentlicht: (2026)

PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks
von: Shen, Guobin, et al.
Veröffentlicht: (2025)

Boosting Na‐O Affinity in Na3Zr2Si2PO12 Electrolyte Promises Highly Rechargeable Solid‐State Sodium Batteries
von: Yang Li, et al.
Veröffentlicht: (2024)

Piezoelectric Effect Promoted Photoelectrochemical Water Splitting Ability of ZnIn2S4 Photoanode with Highly Exposed Active (110) Facets
von: Jiazeyu Li, et al.
Veröffentlicht: (2024)

VEU-Bench: Towards Comprehensive Understanding of Video Editing
von: Li, Bozheng, et al.
Veröffentlicht: (2025)