Image de couverture de livre

Don't Break the Boundary: Continual Unlearning for OOD Detection Based on Free Energy Repulsion

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Peng, Ningkang, Shao, Kun, Mao, Jingyang, Qian, Linjing, Peng, Xiaoqian, Yang, Xichen, Gu, Yanhui
Format:	Preprint
Publié:	2026
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

Breaking Semantic Hegemony: Decoupling Principal and Residual Subspaces for Generalized OOD Detection
par: Peng, Ningkang, et autres
Publié: (2026)

HamBR: Active Decision Boundary Restoration Based on Hamiltonian Dynamics for Learning with Noisy Labels
par: Peng, Ningkang, et autres
Publié: (2026)

GAMR: Geometric-Aware Manifold Regularization with Virtual Outlier Synthesis for Learning with Noisy Labels
par: Peng, Ningkang, et autres
Publié: (2026)

How to Achieve Prototypical Birth and Death for OOD Detection?
par: Peng, Ningkang, et autres
Publié: (2026)

Holistic Reliability Propagation: Decoupling Annotation and Prediction for Robust Noisy-Label
par: Mao, Jingyang, et autres
Publié: (2026)

Radial-Angular Geometry for Reliable Update Diagnosis in Noisy-Label Learning
par: Peng, Ningkang, et autres
Publié: (2026)

Halt the Hallucination: Decoupling Signal and Semantic OOD Detection Based on Cascaded Early Rejection
par: Peng, Ningkang, et autres
Publié: (2026)

Is Complex Training Necessary for Long-Tailed OOD Detection? A Re-think from Feature Geometry
par: Peng, Ningkang, et autres
Publié: (2026)

When Accuracy Is Not Enough: Uncertainty Collapse between Noisy Label Learning and Out-of-Distribution Detection
par: Peng, Ningkang, et autres
Publié: (2026)

VMF-GOS: Geometry-guided virtual Outlier Synthesis for Long-Tailed OOD Detection
par: Peng, Ningkang, et autres
Publié: (2026)

Early High-Frequency Injection for Geometry-Sensitive OOD Detection
par: Cheng, Chuanjie, et autres
Publié: (2026)

Learning with Adaptive Prototype Manifolds for Out-of-Distribution Detection
par: Peng, Ningkang, et autres
Publié: (2026)

PIS: A Physics-Informed System for Accurate State Partitioning of $Aβ_{42}$ Protein Trajectories
par: Yu, Qianfeng, et autres
Publié: (2026)

A Multi-dimensional Semantic Surprise Framework Based on Low-Entropy Semantic Manifolds for Fine-Grained Out-of-Distribution Detection
par: Peng, Ningkang, et autres
Publié: (2025)

Detection of algal tiny objects based on morphological features
par: Shuai Yuan, et autres
Publié: (2024)

Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization
par: Kachaev, Nikita, et autres
Publié: (2025)

Don't Collapse Your Features: Why CenterLoss Hurts OOD Detection and Multi-Scale Mahalanobis Wins
par: Ray, Rahul D
Publié: (2026)

Don't Forget It! Conditional Sparse Autoencoder Clamping Works for Unlearning
par: Khoriaty, Matthew, et autres
Publié: (2025)

$Δ\mathrm{Energy}$: Optimizing Energy Change During Vision-Language Alignment Improves both OOD Detection and OOD Generalization
par: Zhu, Lin, et autres
Publié: (2025)

Don't Forget Too Much: Towards Machine Unlearning on Feature Level
par: Xu, Heng, et autres
Publié: (2024)

Don't Walk the Line: Boundary Guidance for Filtered Generation
par: Ball, Sarah, et autres
Publié: (2025)

Don't Lag, RAG: Training-Free Adversarial Detection Using RAG
par: Kazoom, Roie, et autres
Publié: (2025)

Don't Half-listen: Capturing Key-part Information in Continual Instruction Tuning
par: He, Yongquan, et autres
Publié: (2024)

(Don't) Mind the Gap
par: Frank, Natalie Priebe, et autres
Publié: (2025)

Don't Run with Scissors: Pruning Breaks VLA Models but They Can Be Recovered
par: Jabbour, Jason, et autres
Publié: (2025)

Frictional Agent Alignment Framework: Slow Down and Don't Break Things
par: Nath, Abhijnan, et autres
Publié: (2025)

Affordance-First Decomposition for Continual Learning in Video-Language Understanding
par: Xu, Mengzhu, et autres
Publié: (2025)

Don't be salesmen
Publié: (1997)

Dos and Don'ts When Seeking Free Printing
Publié: (2024)

Don't Forget the Critic: Value-Based Data Rehearsal for Multi-Cyclic Continual Reinforcement Learning
par: Poole, Benjamin, et autres
Publié: (2026)

Don't Freeze, Don't Crash: Extending the Safe Operating Range of Neural Navigation in Dense Crowds
par: Zhang, Jiefu, et autres
Publié: (2026)

Don't Break the Cache: An Evaluation of Prompt Caching for Long-Horizon Agentic Tasks
par: Lumer, Elias, et autres
Publié: (2026)

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations
par: Mayne, Harry, et autres
Publié: (2025)

FEVER-OOD: Free Energy Vulnerability Elimination for Robust Out-of-Distribution Detection
par: Isaac-Medina, Brian K. S., et autres
Publié: (2024)

What Librarians Still Don't Know about Free Software
par: Chudnov, Daniel
Publié: (2009)

Don’t Burn it Here
par: Walsh, Ed, et autres
Publié: (2026)

Don't Look Away
par: Cohen, Brianne
Publié: (2023)

Don't Forget Imagination!
par: Vityaev, Evgenii E., et autres
Publié: (2025)

Don't Pay Attention
par: Hammoud, Mohammad, et autres
Publié: (2025)

Don't ban the bomb
Publié: (1997)