conftrace_

attention locality

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

segment parallelism (1) token sparsification (1) video large language model (1) inference acceleration (1)

Papers

SegMo: Co-Designing Content-Aware Sparsity and Locally-Cohesive Segment Parallelism for Efficient VLM Inference CVPR 2026