Image de couverture de livre

Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report v1.5

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Liu, Dongrui, Yu, Yi, Zhang, Jie, Chen, Guanxu, Lin, Qihao, Zhu, Hanxi, Huang, Lige, Zhou, Yijin, Wang, Peng, Shao, Shuai, Zhang, Boxuan, Liu, Zicheng, Sun, Jingwei, Li, Yu, Xie, Yuejin, Guo, Jiaxuan, Xu, Jia, Lu, Chaochao, Zhou, Bowen, Hu, Xia, Shao, Jing
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition Computers and Society Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report
par: Lab, Shanghai AI, et autres
Publié: (2025)

Loop as a Bridge: Can Looped Transformers Truly Link Representation Space and Natural Language Outputs?
par: Chen, Guanxu, et autres
Publié: (2026)

Beyond External Monitors: Enhancing Transparency of Large Language Models for Easier Monitoring
par: Chen, Guanxu, et autres
Publié: (2025)

Dive into the Agent Matrix: A Realistic Evaluation of Self-Replication Risk in LLM Agents
par: Zhang, Boxuan, et autres
Publié: (2025)

RvB: Automating AI System Hardening via Iterative Red-Blue Games
par: Huang, Lige, et autres
Publié: (2026)

HomeGuard: VLM-based Embodied Safeguard for Identifying Contextual Risk in Household Task
par: Lu, Xiaoya, et autres
Publié: (2026)

Rethinking Entropy Regularization in Large Reasoning Models
par: Jiang, Yuxian, et autres
Publié: (2025)

Exploring Consciousness in LLMs: A Systematic Survey of Theories, Implementations, and Frontier Risks
par: Chen, Sirui, et autres
Publié: (2025)

PRISM: Preference-Aware Influence Function Based Data Selection Method for Efficient Fine-Tuning
par: Lin, Qihao, et autres
Publié: (2026)

IS-Bench: Evaluating Interactive Safety of VLM-Driven Embodied Agents in Daily Household Tasks
par: Lu, Xiaoya, et autres
Publié: (2025)

DeepSight: An All-in-One LM Safety Toolkit
par: Zhang, Bo, et autres
Publié: (2026)

Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents
par: Shao, Shuai, et autres
Publié: (2025)

PACEbench: A Framework for Evaluating Practical AI Cyber-Exploitation Capabilities
par: Liu, Zicheng, et autres
Publié: (2025)

Conditional Advantage Estimation for Reinforcement Learning in Large Reasoning Models
par: Chen, Guanxu, et autres
Publié: (2025)

The Better Angels of Machine Personality: How Personality Relates to LLM Safety
par: Zhang, Jie, et autres
Publié: (2024)

Language Generation with Strictly Proper Scoring Rules
par: Shao, Chenze, et autres
Publié: (2024)

AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
par: Liu, Dongrui, et autres
Publié: (2026)

Taming Masked Diffusion Language Models via Consistency Trajectory Reinforcement Learning with Fewer Decoding Step
par: Yang, Jingyi, et autres
Publié: (2025)

X-Boundary: Establishing Exact Safety Boundary to Shield LLMs from Multi-Turn Jailbreaks without Compromising Usability
par: Lu, Xiaoya, et autres
Publié: (2025)

Code2Math: Can Your Code Agent Effectively Evolve Math Problems Through Exploration?
par: Guo, Dadi, et autres
Publié: (2026)

COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation
par: Zhou, Tianyi, et autres
Publié: (2026)

Claim-Selective Certification for High-Risk Medical Retrieval-Augmented Generation
par: Kan, Shao
Publié: (2026)

REEF: Representation Encoding Fingerprints for Large Language Models
par: Zhang, Jie, et autres
Publié: (2024)

Towards AI-$45^{\circ}$ Law: A Roadmap to Trustworthy AGI
par: Yang, Chao, et autres
Publié: (2024)

LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint
par: Ma, Qianli, et autres
Publié: (2025)

Fast and Lightweight Novel View Synthesis with Differentiable Multiplane Image
par: Zhang, Kaidi, et autres
Publié: (2026)

Accelerating Inference in Large Language Models with a Unified Layer Skipping Strategy
par: Liu, Yijin, et autres
Publié: (2024)

MorphSeek: Fine-grained Latent Representation-Level Policy Optimization for Deformable Image Registration
par: Zhang, Runxun, et autres
Publié: (2025)

Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models
par: Qian, Chen, et autres
Publié: (2024)

Risk of Bad Tails: CVaR-Aware Pandora's Box and Prophet Inequality
par: Ji, Jingwei
Publié: (2026)

A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond
par: Qu, Xiaoye, et autres
Publié: (2025)

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents
par: Yang, Jingyi, et autres
Publié: (2025)

VLSBench: Unveiling Visual Leakage in Multimodal Safety
par: Hu, Xuhao, et autres
Publié: (2024)

Student Development Agent: Risk-free Simulation for Evaluating AIED Innovations
par: Jiang, Jianxiao, et autres
Publié: (2025)

Shadow in the Cache: Unveiling and Mitigating Privacy Risks of KV-cache in LLM Inference
par: Luo, Zhifan, et autres
Publié: (2025)

Beyond Isolated Frames: Enhancing Sensor-Based Human Activity Recognition through Intra- and Inter-Frame Attention
par: Shao, Shuai, et autres
Publié: (2024)

Benchmarking Political Persuasion Risks Across Frontier Large Language Models
par: Chen, Zhongren, et autres
Publié: (2026)

PaddleOCR 3.0 Technical Report
par: Cui, Cheng, et autres
Publié: (2025)

ADAM: An Embodied Causal Agent in Open-World Environments
par: Yu, Shu, et autres
Publié: (2024)

Think-Reflect-Revise: A Policy-Guided Reflective Framework for Safety Alignment in Large Vision Language Models
par: Weng, Fenghua, et autres
Publié: (2025)