Image de couverture de livre

Show Me What You Don't Know: Efficient Sampling from Invariant Sets for Model Validation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Rousselot, Armand, Wendebourg, Joran, Köthe, Ullrich
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

Experts Don't Cheat: Learning What You Don't Know By Predicting Pairs
par: Johnson, Daniel D., et autres
Publié: (2024)

Free-form Flows: Make Any Architecture a Normalizing Flow
par: Draxler, Felix, et autres
Publié: (2023)

Learning Distributions on Manifolds with Free-Form Flows
par: Sorrenson, Peter, et autres
Publié: (2023)

TRADE: Transfer of Distributions between External Conditions with Normalizing Flows
par: Wahl, Stefan, et autres
Publié: (2024)

Know What You Don't Know: Uncertainty Calibration of Process Reward Models
par: Park, Young-Jin, et autres
Publié: (2025)

Knowing What You Know Is Not Enough: Large Language Model Confidences Don't Align With Their Actions
par: Pal, Arka, et autres
Publié: (2025)

Know What You Don't Know: Selective Prediction for Early Exit DNNs
par: Bajpai, Divya Jyoti, et autres
Publié: (2025)

Lifting Architectural Constraints of Injective Flows
par: Sorrenson, Peter, et autres
Publié: (2023)

Large Language Models Must Be Taught to Know What They Don't Know
par: Kapoor, Sanyam, et autres
Publié: (2024)

First, Learn What You Don't Know: Active Information Gathering for Driving at the Limits of Handling
par: Davydov, Alexander, et autres
Publié: (2024)

Bayesian Mixture-of-Experts: Towards Making LLMs Know What They Don't Know
par: Li, Albus Yizhuo
Publié: (2025)

Analyzing Generative Models by Manifold Entropic Metrics
par: Galperin, Daniel, et autres
Publié: (2024)

Can Molecular Foundation Models Know What They Don't Know? A Simple Remedy with Preference Optimization
par: He, Langzhou, et autres
Publié: (2025)

From Core to Detail: Unsupervised Disentanglement with Entropy-Ordered Flows
par: Galperin, Daniel, et autres
Publié: (2026)

Don't Stop Me Yet: Sampling Loss Minima via Dissipative Riemannian Mechanics
par: Jacobsen, Albert Kjøller, et autres
Publié: (2026)

xAI-Drop: Don't Use What You Cannot Explain
par: De Luca, Vincenzo Marco, et autres
Publié: (2024)

I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Token
par: Cohen, Roi, et autres
Publié: (2024)

What LLMs Think When You Don't Tell Them What to Think About?
par: Kwon, Yongchan, et autres
Publié: (2026)

Breaking the Simplification Bottleneck in Amortized Neural Symbolic Regression
par: Saegert, Paul, et autres
Publié: (2026)

If You Don't Understand It, Don't Use It: Eliminating Trojans with Filters Between Layers
par: Hernandez, Adriano
Publié: (2024)

Don't Stop Me Now: Embedding Based Scheduling for LLMs
par: Shahout, Rana, et autres
Publié: (2024)

OOD Detection with immature Models
par: Montazeran, Behrooz, et autres
Publié: (2025)

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs
par: Janjua, Muhammad Kamran, et autres
Publié: (2026)

Attention Is All You Need But You Don't Need All Of It For Inference of Large Language Models
par: Tyukin, Georgy, et autres
Publié: (2024)

Reasoning Models Don't Always Say What They Think
par: Chen, Yanda, et autres
Publié: (2025)

Show, Don't Tell: Detecting Novel Objects by Watching Human Videos
par: Akl, James, et autres
Publié: (2026)

Generative Invertible Quantum Neural Networks
par: Rousselot, Armand, et autres
Publié: (2023)

Don't Fool Me Twice: Adapting to Adversity in the Wild with Experience-Driven Reasoning
par: Ravie, Navin Sriram, et autres
Publié: (2026)

Split-Flows: Measure Transport and Information Loss Across Molecular Resolutions
par: Hummerich, Sander, et autres
Publié: (2025)

On the Universality of Volume-Preserving and Coupling-Based Normalizing Flows
par: Draxler, Felix, et autres
Publié: (2024)

Beyond Diagonal Covariance: Flexible Posterior VAEs via Free-Form Injective Flows
par: Sorrenson, Peter, et autres
Publié: (2025)

I Know What I Don't Know: Latent Posterior Factor Models for Multi-Evidence Probabilistic Reasoning
par: Alege, Aliyu Agboola
Publié: (2026)

Learning Distances from Data with Normalizing Flows and Score Matching
par: Sorrenson, Peter, et autres
Publié: (2024)

Sample, Don't Search: Rethinking Test-Time Alignment for Language Models
par: Faria, Gonçalo, et autres
Publié: (2025)

Don't stop me now: Rethinking Validation Criteria for Model Parameter Selection
par: Apicella, Andrea, et autres
Publié: (2026)

Don't Waste Your Time: Early Stopping Cross-Validation
par: Bergman, Edward, et autres
Publié: (2024)

You Don't Need Prompt Engineering Anymore: The Prompting Inversion
par: Khan, Imran
Publié: (2025)

Use What You Know: Causal Foundation Models with Partial Graphs
par: Reuter, Arik, et autres
Publié: (2026)

Detecting Model Misspecification in Amortized Bayesian Inference with Neural Networks: An Extended Investigation
par: Schmitt, Marvin, et autres
Publié: (2024)

Visually Dehallucinative Instruction Generation: Know What You Don't Know
par: Cha, Sungguk, et autres
Publié: (2024)