Regional-to-global distillation uses crop-conditioned guidance to improve full-image understanding. The challenge is to effectively transfer the teacher's crop-based advantage to the student's full-image inference. We propose progressive-view on-policy distillation (PVD), which shifts the student's view distribution fr...
Shan-Feng Huang, Zhou Fang, Song Xiao et al.· 0 citations
For large language models (LLMs), parametric adaptation is costly when retrieval already suffices. We introduce ALLOT, a hybrid-memory routing framework that separates learned write priority from a hard parametric budget. A memory-aware router combines frozen text representations, retrieval confidence, and relation met...
Shan-Feng Huang, Zhou Fang, Song Xiao et al.· 0 citations
WorldMark is introduced, a plug-and-play interface that uses World Knowledge Memory to organize semantic and episodic knowledge in a memory graph, converts the retrieved knowledge into a token-level knowledge saliency score, and adjusts the strength of a host watermark through Asymmetric Knowledge Modulation (AKM).
Song Xiao, Yuqi Yuan, Yanshuo Zhang 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.