14 papers
Safin-1: Safety from Within through Memory-Native State Evolution
Ming Zhang, Kaisen Yang, Shu Yu +15
Long-horizon complex tasks require foundation models to accumulate information, maintain internal states, and adapt over extended interactions. Safety should be an intrinsic proper…
MARCH: Scaling Recurrent Memory with Content-Routed State Anchors
Ming Zhang, Kaisen Yang, Shu Yu +6
Transformers owe much of their strong long-context retrieval capability to a token-level memory that grows with context length. This flexibility, however, incurs a quadratic comput…
An Early Warning of Emerging Biosecurity Risks in Frontier LLMs
Zhida He, Xia Hu, Baichen Le +20
Frontier large language models (LLMs) are increasingly integrated into scientific workflows, yet their growing biological capabilities may outpace current safeguards. To assess the…
Deep Interaction: An Efficient Human-AI Interaction Method for Large Reasoning Models
Hefeng Zhou, Jinxuan Zhang, Jiong Lou +4
The emergence of Chain-of-Thought (CoT) reasoning has significantly enhanced the ability of large language models (LLMs) to tackle complex, multi-step tasks. However, when errors o…
EvoDefense: Co-Evolving Black-Box Defense with Large Language Models
Yu Li, Yuenan Hou, Yingmei Wei +2
Large Language Models (LLMs) remain highly vulnerable to diverse attacks, particularly in black-box settings where the internals of target models are inaccessible. Existing black-b…
TRACE: Task-Aware Adaptive Self-Evolving Agentic Jailbreaking
Churui Zeng, Weiwei Qi, Kedong Xiu +6
The rise of LLM agents introduces a new threat by enabling planning, coding, and even end-to-end execution of expert-level attack workflows. However, this threat remains underexplo…
AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
Dongrui Liu, Yu Li, Zhonghao Yang +47
Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhile, advanced frontier AI mod…
Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report v1.5
Dongrui Liu, Yi Yu, Jie Zhang +18
To understand and identify the unprecedented risks posed by rapidly advancing artificial intelligence (AI) models, Frontier AI Risk Management Framework in Practice presents a comp…
Decoupled Reasoning with Implicit Fact Tokens (DRIFT): A Dual-Model Framework for Efficient Long-Context Inference
Wenxuan Xie, Yujia Wang, Xin Tan +3
The integration of extensive, dynamic knowledge into Large Language Models (LLMs) remains a significant challenge due to the inherent entanglement of factual data and reasoning pat…
AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
Dongrui Liu, Qihan Ren, Chen Qian +40
The rise of AI agents introduces complex safety and security challenges arising from autonomous tool use and environmental interactions. Current guardrail models lack agentic risk…
Think-Reflect-Revise: A Policy-Guided Reflective Framework for Safety Alignment in Large Vision Language Models
Fenghua Weng, Chaochao Lu, Xia Hu +2
As multimodal reasoning improves the overall capabilities of Large Vision Language Models (LVLMs), recent studies have begun to explore safety-oriented reasoning, aiming to enhance…
Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report
Shanghai AI Lab, :, Xiaoyang Chen +35
To understand and identify the unprecedented risks posed by rapidly advancing artificial intelligence (AI) models, this report presents a comprehensive assessment of their frontier…
The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs
Zichen Wen, Jiashu Qu, Zhaorun Chen +13
Diffusion-based large language models (dLLMs) have recently emerged as a powerful alternative to autoregressive LLMs, offering faster inference and greater interactivity via parall…
Epitome: Pioneering an Experimental Platform for AI-Social Science Integration
Jingjing Qu, Kejia Hu, Jun Zhu +9
Large Language Models (LLMs) enable unprecedented social science experimentation by creating controlled hybrid human-AI environments. We introduce Epitome (www.epitome-ai.com), an…