Imagen de Portada

Towards Disentangled Preference Optimization Dynamics: Suppress the Loser, Preserve the Winner

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chen, Wei, Wu, Yubing, Yang, Junmei, Zeng, Delu, Zhao, Qibin, Paisley, John, Chen, Min, Wang, Zhou
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Fully Bayesian Differential Gaussian Processes through Stochastic Differential Equations
por: Xu, Jian, et al.
Publicado: (2024)

Neural Bridge Processes
por: Xu, Jian, et al.
Publicado: (2025)

Consist-Retinex: One-Step Noise-Emphasized Consistency Training Accelerates High-Quality Retinex Enhancement
por: Xu, Jian, et al.
Publicado: (2025)

Flexible Bayesian Last Layer Models Using Implicit Priors and Diffusion Posterior Sampling
por: Xu, Jian, et al.
Publicado: (2024)

One-Step Score-Based Density Ratio Estimation
por: Chen, Wei, et al.
Publicado: (2026)

A Minimum Variance Path Principle for Accurate and Stable Score-Based Density Ratio Estimation
por: Chen, Wei, et al.
Publicado: (2026)

Variational Learning of Gaussian Process Latent Variable Models through Stochastic Gradient Annealed Importance Sampling
por: Xu, Jian, et al.
Publicado: (2024)

Sparse Variational Student-t Processes for Heavy-tailed Modeling
por: Xu, Jian, et al.
Publicado: (2024)

Sparse Inducing Points in Deep Gaussian Processes: Enhancing Modeling with Denoising Diffusion Variational Inference
por: Xu, Jian, et al.
Publicado: (2024)

Diffusion Bridge Variational Inference for Deep Gaussian Processes
por: Xu, Jian, et al.
Publicado: (2025)

Onsager-Machlup Posterior Transport for Deep Gaussian Processes
por: Xu, Jian, et al.
Publicado: (2026)

Dequantified Diffusion-Schr{ö}dinger Bridge for Density Ratio Estimation
por: Chen, Wei, et al.
Publicado: (2025)

Diffusion Secant Alignment for Score-Based Density Ratio Estimation
por: Chen, Wei, et al.
Publicado: (2025)

AQKA: Active Quantum Kernel Acquisition Under a Shot Budget
por: Xu, Jian, et al.
Publicado: (2026)

Sparse Variational Student-t Processes
por: Xu, Jian, et al.
Publicado: (2023)

Bayesian Gaussian Process ODEs via Double Normalizing Flows
por: Xu, Jian, et al.
Publicado: (2023)

An Explainable Gaussian Process Auto-encoder for Tabular Data
por: Zhang, Wei, et al.
Publicado: (2025)

Gaussian Process Neural Additive Models
por: Zhang, Wei, et al.
Publicado: (2024)

SHAPE : Self-Improved Visual Preference Alignment by Iteratively Generating Holistic Winner
por: Chen, Kejia, et al.
Publicado: (2025)

GED-Consistent Disentanglement of Aligned and Unaligned Substructures for Graph Similarity Learning
por: Zhan, Zhentao, et al.
Publicado: (2025)

DynamicPO: Dynamic Preference Optimization for Recommendation
por: Hu, Xingyu, et al.
Publicado: (2026)

Breaking $\textit{Winner-Takes-All}$: Cooperative Policy Optimization Improves Diverse LLM Reasoning
por: Chen, Haoxuan, et al.
Publicado: (2026)

Winners and Losers of Regional Growth in Mexico and their Dynamics
por: Eduardo Rodríguez-Oreggia
Publicado: (2007)

Towards Reliable LLM Evaluation: Correcting the Winner's Curse in Adaptive Benchmarking
por: Xu, Yang, et al.
Publicado: (2026)

Improving Code Translation with Syntax-Guided and Semantic-aware Preference Optimization
por: Wu, Yuhan, et al.
Publicado: (2026)

Intermediate Condorcet Winners and Losers
por: Salvador Barberà, et al.
Publicado: (2025)

Stochastic Schrödinger Diffusion Models for Pure-State Ensemble Generation
por: Xu, Jian, et al.
Publicado: (2026)

AI and Collective Decisions: Strengthening Legitimacy and Losers' Consent
por: Fulay, Suyash, et al.
Publicado: (2026)

$β$-DPO: Direct Preference Optimization with Dynamic $β$
por: Wu, Junkang, et al.
Publicado: (2024)

Preference-Driven Multi-Objective Combinatorial Optimization with Conditional Computation
por: Fan, Mingfeng, et al.
Publicado: (2025)

Entropy-Informed Weighting Channel Normalizing Flow for Deep Generative Models
por: Chen, Wei, et al.
Publicado: (2024)

Triple Disentangled Representation Learning for Multimodal Affective Analysis
por: Zhou, Ying, et al.
Publicado: (2024)

Improving Safety Alignment via Balanced Direct Preference Optimization
por: Zhao, Shiji, et al.
Publicado: (2026)

Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization
por: Wu, Junkang, et al.
Publicado: (2024)

Spectral Anatomy of Quantum Gaussian Process Kernels
por: Xu, Jian, et al.
Publicado: (2026)

Preferred-Action-Optimized Diffusion Policies for Offline Reinforcement Learning
por: Zhang, Tianle, et al.
Publicado: (2024)

Not a Great Winner, but an Ordinary Loser
por: Lucía Villanea Morales
Publicado: (2020)

Time-Aware Diffusion based on Preference Disentanglement for Generative Recommendation
por: Zhu, Bangguo, et al.
Publicado: (2026)

Token-level Direct Preference Optimization
por: Zeng, Yongcheng, et al.
Publicado: (2024)

Towards Self-Improvement of Diffusion Models via Group Preference Optimization
por: Chen, Renjie, et al.
Publicado: (2025)