4 papers
ALLOT: Budgeted Hybrid-Memory Routing for Knowledge Updates in LLMs
Shanfeng Huang, Zhou Fang, Song Xiao +1
For large language models (LLMs), parametric adaptation is costly when retrieval already suffices. We introduce ALLOT, a hybrid-memory routing framework that separates learned writ…
Progressive-View On-Policy Distillation for Regional-to-Global Transfer in Multimodal LLMs
Shanfeng Huang, Zhou Fang, Song Xiao +1
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 t…
PRIME: Frequency-Aware Unified Pruning and Merging for MoE Compression
Shanfeng Huang, Rongqian Zhang, Zhou Fang +2
Mixture-of-Experts (MoE) models have emerged as an effective paradigm for scaling large language models, yet their massive parameter footprint poses severe memory challenges for de…
WorldMark: A Plug-and-Play World Knowledge Interface for Cross-Host Language Model Watermarking
Song Xiao, Yuqi Yuan, Yanshuo Zhang +1
Watermarking traces the provenance of text produced by large language models by embedding statistically detectable signals during decoding. Existing schemes fall into logits-based,…