Copertina

BSO: Safety Alignment Is Density Ratio Matching

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Nguyen, Tien-Phat, Nguyen, Truong, Nguyen, Thin, Nguyen, Duy Minh Ho, Dinh, Ngoc-Thanh, Le, Trung
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Spectral Flattening Is All Muon Needs: How Orthogonalization Controls Learning Rate and Convergence
di: Nguyen, Tien-Phat, et al.
Pubblicazione: (2026)

TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching
di: Nguyen, Truong, et al.
Pubblicazione: (2026)

Fake Advertisements Detection Using Automated Multimodal Learning: A Case Study for Vietnamese Real Estate Data
di: Nguyen, Duy, et al.
Pubblicazione: (2025)

Enhancing Time Series Forecasting via a Parallel Hybridization of ARIMA and Polynomial Classifiers
di: Nguyen, Thanh Son, et al.
Pubblicazione: (2025)

Variational Flow Models: Flowing in Your Style
di: Do, Kien, et al.
Pubblicazione: (2024)

Amortized Optimal Transport from Sliced Potentials
di: Truong, Minh-Phuc, et al.
Pubblicazione: (2026)

Empowering Contrastive Federated Sequential Recommendation with LLMs
di: Nguyen, Thi Minh Chau, et al.
Pubblicazione: (2026)

A Class-aware Optimal Transport Approach with Higher-Order Moment Matching for Unsupervised Domain Adaptation
di: Nguyen, Tuan, et al.
Pubblicazione: (2024)

Generative Conditional Distributions by Neural (Entropic) Optimal Transport
di: Nguyen, Bao, et al.
Pubblicazione: (2024)

Learning Reconfigurable Representations for Multimodal Federated Learning with Missing Data
di: Nguyen, Duong M., et al.
Pubblicazione: (2025)

Spectral Text Fusion: A Frequency-Aware Approach to Multimodal Time-Series Forecasting
di: Nguyen, Huu Hiep, et al.
Pubblicazione: (2026)

Generating Realistic Tabular Data with Large Language Models
di: Nguyen, Dang, et al.
Pubblicazione: (2024)

How Transformers Learn In-Context Recall Tasks? Optimality, Training Dynamics and Generalization
di: Nguyen, Quan, et al.
Pubblicazione: (2025)

A Survey of Privacy-Preserving Model Explanations: Privacy Risks, Attacks, and Countermeasures
di: Nguyen, Thanh Tam, et al.
Pubblicazione: (2024)

Enabling Causal Discovery in Post-Nonlinear Models with Normalizing Flows
di: Hoang, Nu, et al.
Pubblicazione: (2024)

Scalable Variational Causal Discovery Unconstrained by Acyclicity
di: Hoang, Nu, et al.
Pubblicazione: (2024)

Improving Generalization in Heterogeneous Federated Continual Learning via Spatio-Temporal Gradient Matching with Prototypical Coreset
di: Nguyen, Minh-Duong, et al.
Pubblicazione: (2025)

XEdgeAI: A Human-centered Industrial Inspection Framework with Data-centric Explainable Edge AI Approach
di: Nguyen, Truong Thanh Hung, et al.
Pubblicazione: (2024)

A Survey of Machine Unlearning
di: Nguyen, Thanh Tam, et al.
Pubblicazione: (2022)

Beyond Low-rank Decomposition: A Shortcut Approach for Efficient On-Device Learning
di: Nguyen, Le-Trung, et al.
Pubblicazione: (2025)

Rethinking Cross-Modal Fine-Tuning: Optimizing the Interaction Between Feature Alignment and Target Fitting
di: Tran, Trong Khiem, et al.
Pubblicazione: (2026)

Multi-level Phenotypic Models of Cardiovascular Disease and Obstructive Sleep Apnea Comorbidities: A Longitudinal Wisconsin Sleep Cohort Study
di: Nguyen, Duy, et al.
Pubblicazione: (2024)

Sharpness-Aware Teleportation on Riemannian Manifolds
di: Truong, Tuan, et al.
Pubblicazione: (2023)

Revisiting Kernel Attention with Correlated Gaussian Process Representation
di: Bui, Long Minh, et al.
Pubblicazione: (2025)

Advancing Vietnamese Information Retrieval with Learning Objective and Benchmark
di: Nguyen, Phu-Vinh, et al.
Pubblicazione: (2025)

Causal Graph Learning via Distributional Invariance of Cause-Effect Relationship
di: Nguyen, Nang Hung, et al.
Pubblicazione: (2026)

Universal Multi-Domain Translation via Diffusion Routers
di: Kieu, Duc, et al.
Pubblicazione: (2025)

Improving Chain-of-Thought for Logical Reasoning via Attention-Aware Intervention
di: Phuong, Nguyen Minh, et al.
Pubblicazione: (2026)

SegMaFormer: A Hybrid State-Space and Transformer Model for Efficient Segmentation
di: Nguyen, Duy D., et al.
Pubblicazione: (2026)

MP-MoE: Matrix Profile-Guided Mixture of Experts for Precipitation Forecasting
di: Tran, Huyen Ngoc, et al.
Pubblicazione: (2026)

EquiCPI: SE(3)-Equivariant Geometric Deep Learning for Structure-Aware Prediction of Compound-Protein Interactions
di: Nguyen, Ngoc-Quang
Pubblicazione: (2025)

Semi-Supervised Semantic Segmentation using Redesigned Self-Training for White Blood Cells
di: Luu, Vinh Quoc, et al.
Pubblicazione: (2024)

MisoDICE: Multi-Agent Imitation from Unlabeled Mixed-Quality Demonstrations
di: Bui, The Viet, et al.
Pubblicazione: (2025)

Generalized knowledge-enhanced framework for biomedical entity and relation extraction
di: Nguyen, Minh, et al.
Pubblicazione: (2024)

Point Cloud Compression with Bits-back Coding
di: Hieu, Nguyen Quang, et al.
Pubblicazione: (2024)

Revisiting Incremental Stochastic Majorization-Minimization Algorithms with Applications to Mixture of Experts
di: Tran, TrungKhang, et al.
Pubblicazione: (2026)

Fast-FedUL: A Training-Free Federated Unlearning with Provable Skew Resilience
di: Huynh, Thanh Trung, et al.
Pubblicazione: (2024)

The Blessing and Curse of Dimensionality in Safety Alignment
di: Teo, Rachel S. Y., et al.
Pubblicazione: (2025)

Large Language Models for Imbalanced Classification: Diversity makes the difference
di: Nguyen, Dang, et al.
Pubblicazione: (2025)

Energy-Efficient and Real-Time Sensing for Federated Continual Learning via Sample-Driven Control
di: Luu, Minh Ngoc, et al.
Pubblicazione: (2023)