AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Energy Landscape-Aware Vision Transformers: Layerwise Dynamics and Adaptive Task-Specific Training via Hopfield States

Runze Xia, Richard Jiang

NeurIPS 2025 · Architectures and efficiency › Attention and transformers · approach: Efficient and robust vision transformers · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Analyzes ViT layer dynamics through the lens of modern Hopfield networks and proposes a layer instability metric to guide adaptive, task-specific training.

Problem

Vision Transformers have deep, uniform layer stacks that incur significant computational overhead, and their layerwise dynamics are poorly understood.

Approach

Connects self-attention to modern Hopfield networks to interpret ViT layers as energy-based memory dynamics, and introduces a layer instability metric to characterize per-layer behavior for adaptive task-specific training.

Experimental setup

Builds on: modern Hopfield networks

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy