← Search

Wei Cai

2 accepted papers

2026

When Safe Unimodal Inputs Collide: Optimizing Reasoning Chains for Cross-Modal Safety in Multimodal Large Language Models

AAAI 2026technical

Multimodal Large Language Models (MLLMs) are susceptible to the implicit reasoning risk, wherein innocuous unimodal inputs synergistically assemble into risky multimodal data that produce harmful outputs. We attribute this vulnerability to the difficulty of MLLMs maintaining safety alignment through

Cited by 0SourcePDFScholar
2025

Adaptive Time-Optimal Trajectory Planning Subject to Kinematic and Dynamic Constraints for Articulated Robots

RA-L 2025

This letter proposes an adaptive time-optimal path parameterization algorithm (A-TOPP) subject to kinematic and dynamic constraints for articulated robots. The algorithm efficiently incorporates the effects of Coulomb and viscous friction, while flexibly and comprehensively addressing various kinema

Cited by 1SourceScholar