BadEvolve is proposed, a failure-aware task-poisoning framework against self-evolving LLM agents that diagnoses attack failures across four stages, i.e., Induction, Activation, Following, and Effect, and directs updates toward the failing stage.
Min-hua Lin, Zongyu Wu, Han-Qing Lu et al.· 0 citations
This work presents a unified abstraction of Matryoshka embeddings, early exit, 2D~Matryoshka, and layerwise token compression that enables Matryoshka~LTC (MLTC), which jointly trains several token-compression ratios in one retriever checkpoint.
Yu Wang, Shengyao Zhuang, Xue-Guang Ma et al.· 1 citation
A novel framework for constructing a Context-Enhanced MMKG (CEMMKG) is proposed, effective in leveraging contextual information to improve MMKG-based RAG performance and its effectiveness across different MMKG-based RAG methods demonstrates its broad applicability.
Zongyu Wu, Yilong Wang, Xiaochen Wang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.