Image de couverture de livre

COME: Test-time adaption by Conservatively Minimizing Entropy

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Qingyang, Bian, Yatao, Kong, Xinke, Zhao, Peilin, Zhang, Changqing
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization
par: Zhang, Qingyang, et autres
Publié: (2025)

The Best of Both Worlds: On the Dilemma of Out-of-distribution Detection
par: Zhang, Qingyang, et autres
Publié: (2024)

TEMPO: Scaling Test-time Training for Large Reasoning Models
par: Zhang, Qingyang, et autres
Publié: (2026)

Energy-Guided Generative Modeling for Low-Energy Molecular Structure Discovery
par: Xu, Guikun, et autres
Publié: (2025)

Adapt in the Wild: Test-Time Entropy Minimization with Sharpness and Feature Regularization
par: Niu, Shuaicheng, et autres
Publié: (2025)

ETDock: A Novel Equivariant Transformer for Protein-Ligand Docking
par: Yi, Yiqiang, et autres
Publié: (2023)

Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuning
par: Ma, Huan, et autres
Publié: (2023)

Enhancing Neural Subset Selection: Integrating Background Information into Set Representations
par: Xie, Binghui, et autres
Publié: (2024)

CrystalDiT: A Diffusion Transformer for Crystal Generation
par: Yi, Xiaohan, et autres
Publié: (2025)

Graph Unitary Message Passing
par: Qiu, Haiquan, et autres
Publié: (2024)

Learning to Learn with Contrastive Meta-Objective
par: Wu, Shiguang, et autres
Publié: (2024)

How Interpretable Are Interpretable Graph Neural Networks?
par: Chen, Yongqiang, et autres
Publié: (2024)

A Regret Perspective on Online Multiple Testing
par: Hao, Qingyang, et autres
Publié: (2026)

HIGHT: Hierarchical Graph Tokenization for Molecule-Language Alignment
par: Chen, Yongqiang, et autres
Publié: (2024)

One Fits All: Learning Fair Graph Neural Networks for Various Sensitive Attributes
par: Zhu, Yuchang, et autres
Publié: (2024)

Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation Model
par: Ma, Huan, et autres
Publié: (2024)

Ranked Entropy Minimization for Continual Test-Time Adaptation
par: Han, Jisu, et autres
Publié: (2025)

Uncertainty-Calibrated Test-Time Model Adaptation without Forgetting
par: Tan, Mingkui, et autres
Publié: (2024)

Rethinking Selectivity in State Space Models: A Minimal Predictive Sufficiency Approach
par: Wang, Yiyi, et autres
Publié: (2025)

Test-Time Model Adaptation with Only Forward Passes
par: Niu, Shuaicheng, et autres
Publié: (2024)

The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning
par: Agarwal, Shivam, et autres
Publié: (2025)

Think Consistently, Reason Efficiently: Energy-Based Calibration for Implicit Chain-of-Thought
par: Chen, Zhikang, et autres
Publié: (2025)

Question-Adaptive Graph Learning for Multi-hop Retrieval Augmented Generation
par: Yan, Yuchen, et autres
Publié: (2025)

Rethinking Entropy Minimization in Test-Time Adaptation for Autoregressive Models
par: Huang, Wei-Ping, et autres
Publié: (2026)

Speech Separation with Pretrained Frontend to Minimize Domain Mismatch
par: Wang, Wupeng, et autres
Publié: (2024)

Medical Test-free Disease Detection Based on Big Data
par: Zhao, Haokun, et autres
Publié: (2025)

Semantic Energy: Detecting LLM Hallucination Beyond Entropy
par: Ma, Huan, et autres
Publié: (2025)

Context-aware knowledge graph framework for traffic speed forecasting using graph neural network
par: Zhang, Yatao, et autres
Publié: (2024)

SGFormer: Simplifying and Empowering Transformers for Large-Graph Representations
par: Wu, Qitian, et autres
Publié: (2023)

Titans: Learning to Memorize at Test Time
par: Behrouz, Ali, et autres
Publié: (2024)

InversionGNN: A Dual Path Network for Multi-Property Molecular Optimization
par: Niu, Yifan, et autres
Publié: (2025)

Conservative Prediction via Data-Driven Confidence Minimization
par: Choi, Caroline, et autres
Publié: (2023)

UniMoT: Unified Molecule-Text Language Model with Discrete Token Representation
par: Guo, Shuhan, et autres
Publié: (2024)

Energy-Entropy Regularization: The True Power of Minimal Looped Transformers
par: Lam, Wai-Lun
Publié: (2026)

A Contrastive Learning Based Convolutional Neural Network for ERP Brain-Computer Interfaces
par: Cui, Yuntian, et autres
Publié: (2024)

Ignoring Directionality Leads to Compromised Graph Neural Network Explanations
par: Sun, Changsheng, et autres
Publié: (2025)

STRAP: Spatio-Temporal Pattern Retrieval for Out-of-Distribution Generalization
par: Zhang, Haoyu, et autres
Publié: (2025)

ECHO: Entropy-Confidence Hybrid Optimization for Test-Time Reinforcement Learning
par: Zhao, Chu, et autres
Publié: (2026)

Self-Bootstrapping for Versatile Test-Time Adaptation
par: Niu, Shuaicheng, et autres
Publié: (2025)

3D-GSRD: 3D Molecular Graph Auto-Encoder with Selective Re-mask Decoding
par: Wu, Chang, et autres
Publié: (2025)