3 papers
cs.CR2026
Implicit Manipulation for Skill Selection in LLM Agents with Semantic Matching
Qikai Wang, Yongzhao Zhang, Zhiwei Chen +3
Skill selection is a key stage in LLM-agent workflows, determining which installed skill should handle a user request. Existing attacks on this stage primarily rely on explicit pro…
cs.RO2026
VerNav: Verifier-First Low-Latency Vision-and-Language Navigation
Zhixin Wang, Chengzheyi Yao, Leyuan Liu +2
Vision-and-Language Navigation (VLN) requires an agent to navigate through unseen 3D environments according to natural-language instructions. Explicit reasoning can improve instruc…
cs.LG2026
Mode Connectivity Beyond Classifiers: Evidence from Generative and Contrastive Models
Chengzheyi Yao, Yongzhao Zhang, Yongding Tian
The loss landscape of Deep Neural Networks (DNNs) exhibits highly complex and non-convex properties. Recent studies have revealed the phenomenon of mode connectivity, demonstrating…