Image de couverture de livre

Promoting Ensemble Diversity with Interactive Bayesian Distributional Robustness for Fine-tuning Foundation Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Pham, Ngoc-Quan, Truong, Tuan, Tran, Quyen, Nguyen, Tan, Phung, Dinh, Le, Trung
Format:	Preprint
Publié:	2025
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

Improving Generalization with Flat Hilbert Bayesian Inference
par: Truong, Tuan, et autres
Publié: (2024)

Class-Prototype Conditional Diffusion Model with Gradient Projection for Continual Learning
par: Doan, Khanh, et autres
Publié: (2023)

Agnostic Sharpness-Aware Minimization
par: Nguyen, Van-Anh, et autres
Publié: (2024)

Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective
par: Phan, Hoang, et autres
Publié: (2022)

Diversity-Aware Agnostic Ensemble of Sharpness Minimizers
par: Bui, Anh, et autres
Publié: (2024)

Leveraging Hierarchical Taxonomies in Prompt-based Continual Learning
par: Tran, Quyen, et autres
Publié: (2024)

Model and Feature Diversity for Bayesian Neural Networks in Mutual Learning
par: Pham, Cuong, et autres
Publié: (2024)

A Class-aware Optimal Transport Approach with Higher-Order Moment Matching for Unsupervised Domain Adaptation
par: Nguyen, Tuan, et autres
Publié: (2024)

Explicit Eigenvalue Regularization Improves Sharpness-Aware Minimization
par: Luo, Haocheng, et autres
Publié: (2025)

Generalization Bounds for Robust Contrastive Learning: From Theory to Practice
par: Tran, Ngoc N., et autres
Publié: (2023)

Sharpness-Aware Teleportation on Riemannian Manifolds
par: Truong, Tuan, et autres
Publié: (2023)

Connective Viewpoints of Signal-to-Noise Diffusion Models
par: Doan, Khanh, et autres
Publié: (2024)

Test-Time Instance-Specific Parameter Composition: A New Paradigm for Adaptive Generative Modeling
par: Tran, Minh-Tuan, et autres
Publié: (2026)

Revisiting Prefix-tuning: Statistical Benefits of Reparameterization among Prompts
par: Le, Minh, et autres
Publié: (2024)

KOPPA: Improving Prompt-based Continual Learning with Key-Query Orthogonal Projection and Prototype-based One-Versus-All
par: Tran, Quyen, et autres
Publié: (2023)

An Optimal Transport-driven Approach for Cultivating Latent Space in Online Incremental Learning
par: Tran, Quyen, et autres
Publié: (2022)

UB-SMoE: Universally Balanced Sparse Mixture-of-Experts for Resource-adaptive Federated Fine-tuning of Foundation Models
par: Tran, Van-Tuan, et autres
Publié: (2026)

Text-Enhanced Data-free Approach for Federated Class-Incremental Learning
par: Tran, Minh-Tuan, et autres
Publié: (2024)

Base‐Promoted Construction of Benzo[4,5]imidazo[1,2‐c][1,3]thiazinethiones via C−N/C−S Cyclization
par: Quynh Nhu Tran, et autres
Publié: (2025)

Bayesian Low-Rank Factorization for Robust Model Adaptation
par: Ugan, Enes Yavuz, et autres
Publié: (2025)

Enhancing Domain Adaptation through Prompt Gradient Alignment
par: Phan, Hoang, et autres
Publié: (2024)

BSO: Safety Alignment Is Density Ratio Matching
par: Nguyen, Tien-Phat, et autres
Publié: (2026)

Gap Safe Screening Rules for Fast Training of Robust Support Vector Machines under Feature Noise
par: Nguyen, Tan-Hau, et autres
Publié: (2026)

Unveiling m-Sharpness Through the Structure of Stochastic Gradient Noise
par: Luo, Haocheng, et autres
Publié: (2025)

NAYER: Noisy Layer Data Generation for Efficient and Effective Data-free Knowledge Distillation
par: Tran, Minh-Tuan, et autres
Publié: (2023)

RepLoRA: Reparameterizing Low-Rank Adaptation via the Perspective of Mixture of Experts
par: Truong, Tuan, et autres
Publié: (2025)

Hypernetwork-Driven Low-Rank Adaptation Across Attention Heads
par: Diep, Nghiem T., et autres
Publié: (2025)

Optimizing Specific and Shared Parameters for Efficient Parameter Tuning
par: Nguyen, Van-Anh, et autres
Publié: (2025)

VFOG: Variance-Reduced Fast Optimistic Gradient Methods for a Class of Nonmonotone Generalized Equations
par: Tran-Dinh, Quoc, et autres
Publié: (2025)

One-Prompt Strikes Back: Sparse Mixture of Experts for Prompt-based Continual Learning
par: Le, Minh, et autres
Publié: (2025)

Fine-tuning CLIP Text Encoders with Two-step Paraphrasing
par: Kim, Hyunjae, et autres
Publié: (2024)

A Class of Accelerated Fixed-Point-Based Methods with Delayed Inexact Oracles and Its Applications
par: Nguyen-Trung, Nghia, et autres
Publié: (2025)

Unbiased and Biased Variance-Reduced Forward-Reflected-Backward Splitting Methods for Stochastic Composite Inclusions
par: Tran-Dinh, Quoc, et autres
Publié: (2026)

Accelerated Extragradient-Type Methods -- Part 2: Generalization and Sublinear Convergence Rates under Co-Hypomonotonicity
par: Tran-Dinh, Quoc, et autres
Publié: (2025)

Revisiting Extragradient-Type Methods -- Part 1: Generalizations and Sublinear Convergence Rates
par: Tran-Dinh, Quoc, et autres
Publié: (2024)

MetaAug: Meta-Data Augmentation for Post-Training Quantization
par: Pham, Cuong, et autres
Publié: (2024)

Antibody: Strengthening Defense Against Harmful Fine-Tuning for Large Language Models via Attenuating Harmful Gradient Influence
par: Nguyen, Quoc Minh, et autres
Publié: (2026)

Rethinking Cross-Modal Fine-Tuning: Optimizing the Interaction Between Feature Alignment and Target Fitting
par: Tran, Trong Khiem, et autres
Publié: (2026)

Enhancing Dataset Distillation via Non-Critical Region Refinement
par: Tran, Minh-Tuan, et autres
Publié: (2025)

Exploiting Layer Normalization Fine-tuning in Visual Transformer Foundation Models for Classification
par: Tan, Zhaorui, et autres
Publié: (2025)