Signals 4 · free daily AI digest

Copy the Same, Distill the Difference: Initializing Linear Vision Transformers

Paper recorded by Signals 4 on 2026-09-28 in cs.AI. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-28 on arXiv · recorded by Signals 4 on 2026-09-29

Category: cs.AI · 人工智能 · first seen 2026-09-29

Abstract

Linear Vision Transformers (ViTs) are designed to replace the attention in Softmax ViTs with the linear-complexity attention operator for more efficient token routing, but they require from-scratch pre-training and typically underperform the original Softmax version. How to initialize linear ViTs both efficiently and effectively still remains unclear. In this work, we explicitly ask: given that mo

Read on arXiv →

#7 most recent of 440 cs.AI papers we have recorded · ↑ newer: KV-streams for Efficient Compaction in Agentic Reinforcement Learning · ↓ older: FinAutoRubric: Expert-Guided Automatic Rubric Generation for Evaluatin
Cite this page: Copy the Same, Distill the Difference: Initializing Linear Vision Transformers: the #7 most recent of 440 cs.AI papers we have recorded (as of 2026-09-28). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/copy-the-same-distill-the-difference-initializing-linear-vision-transformers.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.AI papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions