Cover Image

Exploiting the Asymmetric Uncertainty Structure of Pre-trained VLMs on the Unit Hypersphere

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ju, Li, Andersson, Max, Fredriksson, Stina, Glöckner, Edward, Hellander, Andreas, Vats, Ekta, Singh, Prashant
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Epistemic Uncertainty Quantification for Pre-trained VLMs via Riemannian Flow Matching
by: Ju, Li, et al.
Published: (2026)

GeoFlowVLM: Geometry-Aware Joint Uncertainty for Frozen Vision-Language Embedding
by: Nautiyal, Mayank, et al.
Published: (2026)

ConDiSim: Conditional Diffusion Models for Simulation Based Inference
by: Nautiyal, Mayank, et al.
Published: (2025)

Variational Autoencoders for Efficient Simulation-Based Inference
by: Nautiyal, Mayank, et al.
Published: (2024)

OneFlowSBI: One Model, Many Queries for Simulation-Based Inference
by: Nautiyal, Mayank, et al.
Published: (2026)

Uncertainty Estimation via Hyperspherical Confidence Mapping
by: Choi, Eunseo, et al.
Published: (2026)

PARIC: Probabilistic Attention Regularization for Language Guided Image Classification from Pre-trained Vison Language Models
by: Nautiyal, Mayank, et al.
Published: (2025)

Exploiting Vocabulary Frequency Imbalance in Language Model Pre-training
by: Chung, Woojin, et al.
Published: (2025)

HYPO: Hyperspherical Out-of-Distribution Generalization
by: Bai, Haoyue, et al.
Published: (2024)

Hyperspherical Forward-Forward with Prototypical Representations
by: Sarode, Shalini, et al.
Published: (2026)

O$n$ Learning Deep O($n$)-Equivariant Hyperspheres
by: Melnyk, Pavlo, et al.
Published: (2023)

SphUnc: Hyperspherical Uncertainty Decomposition and Causal Identification via Information Geometry
by: Fu, Rong, et al.
Published: (2026)

Toward efficient resource utilization at edge nodes in federated learning
by: Alawadi, Sadi, et al.
Published: (2023)

Exploiting Pre-trained Models for Drug Target Affinity Prediction with Nearest Neighbors
by: Pei, Qizhi, et al.
Published: (2024)

Energy-Balanced Hyperspherical Graph Representation Learning via Structural Binding and Entropic Dispersion
by: Chen, Rui, et al.
Published: (2025)

Exploring and Exploiting the Asymmetric Valley of Deep Neural Networks
by: Li, Xin-Chun, et al.
Published: (2024)

Hyperspherical Normalization for Scalable Deep Reinforcement Learning
by: Lee, Hojoon, et al.
Published: (2025)

Pre-training Epidemic Time Series Forecasters with Compartmental Prototypes
by: Liu, Zewen, et al.
Published: (2025)

Epistemic Uncertainty Quantification For Pre-trained Neural Network
by: Wang, Hanjing, et al.
Published: (2024)

HyperCore: Coreset Selection under Noise via Hypersphere Models
by: Moser, Brian B., et al.
Published: (2025)

Uncertainty-Aware Deployment of Pre-trained Language-Conditioned Imitation Learning Policies
by: Wu, Bo, et al.
Published: (2024)

Enhancing Diversity in Bayesian Deep Learning via Hyperspherical Energy Minimization of CKA
by: Smerkous, David, et al.
Published: (2024)

Deep Orthogonal Hypersphere Compression for Anomaly Detection
by: Zhang, Yunhe, et al.
Published: (2023)

Angular Regularization for Positive-Unlabeled Learning on the Hypersphere
by: Sevetlidis, Vasileios, et al.
Published: (2025)

Constrained Machine Learning Through Hyperspherical Representation
by: Signorelli, Gaetano, et al.
Published: (2025)

Rethinking Language Model Scaling under Transferable Hypersphere Optimization
by: Ren, Liliang, et al.
Published: (2026)

HoloByte: Continuous Hyperspherical Distillation for Tokenizer-Free Modeling
by: Khasia, Vladimer
Published: (2026)

Hyper-SET: Designing Transformers via Hyperspherical Energy Minimization
by: Hu, Yunzhe, et al.
Published: (2025)

Asymmetric Duos: Sidekicks Improve Uncertainty
by: Zhou, Tim G., et al.
Published: (2025)

Beyond Nearest Neighbors: Semantic Compression and Graph-Augmented Retrieval for Enhanced Vector Search
by: Raja, Rahul, et al.
Published: (2025)

Counterfactual Risk Minimization with IPS-Weighted BPR and Self-Normalized Evaluation in Recommender Systems
by: Raja, Rahul, et al.
Published: (2025)

nGPT: Normalized Transformer with Representation Learning on the Hypersphere
by: Loshchilov, Ilya, et al.
Published: (2024)

$\texttt{InfoHier}$: Hierarchical Information Extraction via Encoding and Embedding
by: Zhang, Tianru, et al.
Published: (2025)

Pre-Execution Query Slot-Time Prediction in Cloud Data Warehouses: A Feature-Scoped Machine Learning Approach
by: Pathak, Prashant Kumar
Published: (2026)

A Pre-training Framework for Relational Data with Information-theoretic Principles
by: Truong, Quang, et al.
Published: (2025)

Practical Feasibility of Gradient Inversion Attacks in Federated Learning
by: Valadi, Viktor, et al.
Published: (2025)

Constraint-based Pre-training: From Structured Constraints to Scalable Model Initialization
by: Feng, Fu, et al.
Published: (2026)

Probabilistic Contrastive Learning with Explicit Concentration on the Hypersphere
by: Li, Hongwei Bran, et al.
Published: (2024)

Improving the Generation of VAEs with High Dimensional Latent Spaces by the use of Hyperspherical Coordinates
by: Ascarate, Alejandro, et al.
Published: (2025)

Learning Hyperspherical Time-Frequency Representations for Time-Series Out-of-Distribution Detection
by: Lunardi, Willian T., et al.
Published: (2026)