Full list also available on Google Scholar
Proposed a method that casts selective KV recomputation as an information flow problem, using attention-norm signals to identify tokens that are both semantically relevant and structurally capable of propagating information. Introduced information-flow-guided chunk reordering and...
Read more →Proposed HilbertA, a sparse attention mechanism based on the Hilbert curve that jointly preserves 2D spatial locality and enables contiguous memory access, improving sparsity efficiency and memory throughput. Designed Hilbert-curve sparse attention with reordering, tiling,...
Read more →Proposed Sub-CP, a submodular, block-aware context selection framework that controls a diversity–coherence spectrum for scalable in‑context learning. Designed four partition strategies—Global Diverse, Global–Local Diverse, Local Diverse, and Local Coherent—to balance global coverage and local structure....
Read more →