Showing cs.AIShow all
3 papers · 1 filter
cs.AI2026
Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion
ShiYing Huang, Liang Lin, Yuer Li +6
In the realm of multi-objective alignment for large language models, balancing disparate human preferences often manifests as a zero-sum conflict. Specifically, the intrinsic tensi…
cs.AI2026
Ace-Skill: Bootstrapping Multimodal Agents with Prioritized and Clustered Evolution
Feng Xiong, Zengbin Wang, Yong Wang +5
Self-evolving agents present a promising path toward continual adaptation by distilling task interactions into reusable knowledge artifacts. In practice, this paradigm remains hind…
cs.AI2026
Large Vision-Language Models Get Lost in Attention
Gongli Xi, Ye Tian, Mengyu Yang +5
Despite the rapid evolution of training paradigms, the decoder backbone of large vision--language models (LVLMs) remains fundamentally rooted in the residual-connection Transformer…