AI Paper Atlas

Research map / Label-efficient and robust learning / Test-time adaptation

Rethinking Entropy in Test-Time Adaptation: The Missing Piece from Energy Duality

Mincheol Park, Heeji Won, Won Woo Ro, Suhyun Kim

NeurIPS 2025 · Label-efficient and robust learning › Test-time adaptation · approach: Realistic and stable test-time adaptation

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.

Re-examines entropy minimization in test-time adaptation through its dual relationship with energy-based likelihood, motivating an energy-aware TTA formulation.

Problem

Test-time adaptation under distribution shift commonly relies on entropy minimization, whose sufficiency for preserving performance is questioned.

Approach

Analyzes the dual relationship between entropy and energy, treating energy as a proxy for likelihood (lower energy means higher observability under the learned distribution) to show entropy minimization alone is insufficient and to motivate an energy-aware adaptation objective.

Experimental setup

Builds on: entropy minimization TTA

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