Tao Yu
6 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper proposes FRA-Attack, a frequency-domain regularization method, to significantly improve the transferability of adversarial attacks against closed-source Multimodal Large Language Models (MLLMs).
Qwen-VLA introduces a unified embodied foundation model that extends vision-language understanding to continuous action generation, enabling robust, multi-task generalization across diverse robotic tasks and embodiments.
The paper introduces AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex, open-world agentic scenarios.
The paper introduces AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex open-world agent deployments.
COLLEAGUE.SKILL introduces an automated system that distills heterogeneous traces of human expertise and role-specific knowledge into portable, inspectable, and usable AI skill packages.
AnyEdit++ introduces a structure-aware framework that uses Bayesian Surprise to adaptively segment long-form knowledge, significantly improving the coherence and accuracy of knowledge editing in LLMs.
Papers
AnyEdit++: Adaptive Long-Form Knowledge Editing via Bayesian Surprise
Bowen Tian, Caixue He, Jiemin Wu, Jingying Wang +3 more
AnyEdit++ introduces a structure-aware framework that uses Bayesian Surprise to adaptively segment long-form knowledge, significantly improving the coherence and accuracy of knowledge editing in LLMs.