16 citations · 22 across the 10 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.DS2026
Softmax Attention with Any Temperature in Fixed Dimension: Matching the Best Known Maximum-Inner-Product Bounds
Zixuan Huang, Guozhang Chen
Attention is central to modern AI models for language, vision, and scientific modeling. However, direct evaluation compares every query with every key, requiring quadratic time in…
cs.CV2026
Seeing is Free, Speaking is Not: Uncovering the True Energy Bottleneck in Edge VLM Inference
Junfei Zhan, Haoxun Shen, Mingang Guo +2
Vision-Language Models (VLMs) are the perceptual backbone of embodied AI, but their energy footprint on edge hardware remains poorly understood. Existing efficiency efforts focus p…