Cover Image

From Coefficients to Directions: Rethinking Model Merging with Directional Alignment

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Zhikang, Cui, Sen, Ye, Deheng, Zhang, Min, Niu, Gang, Zhang, Yu, Sugiyama, Masashi, Zhu, Tingting
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Think Consistently, Reason Efficiently: Energy-Based Calibration for Implicit Chain-of-Thought
by: Chen, Zhikang, et al.
Published: (2025)

Merging without Forgetting: Continual Fusion of Task-Specific Models via Optimal Transport
by: Pan, Zecheng, et al.
Published: (2025)

Direct Distillation between Different Domains
by: Tang, Jialiang, et al.
Published: (2024)

Robust Multi-View Learning via Representation Fusion of Sample-Level Attention and Alignment of Simulated Perturbation
by: Xu, Jie, et al.
Published: (2025)

Accurate Forgetting for Heterogeneous Federated Continual Learning
by: Wuerkaixi, Abudukelimu, et al.
Published: (2025)

Generating Chain-of-Thoughts with a Pairwise-Comparison Approach to Searching for the Most Promising Intermediate Thought
by: Zhang, Zhen-Yu, et al.
Published: (2024)

From Generative Engines to Actionable Simulators: The Imperative of Physical Grounding in World Models
by: Chen, Zhikang, et al.
Published: (2026)

ECG-WM: A Physiology-Informed ECG World Model for Clinical Intervention Simulation
by: Chen, Zhikang, et al.
Published: (2026)

CALM: Consensus-Aware Localized Merging for Multi-Task Learning
by: Yan, Kunda, et al.
Published: (2025)

From Coordinate Matching to Structural Alignment: Rethinking Prototype Alignment in Heterogeneous Federated Learning
by: Wu, Xinghao, et al.
Published: (2026)

Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers
by: Cai, Xin-Qiang, et al.
Published: (2025)

Sharpness-Aware Black-Box Optimization
by: Ye, Feiyang, et al.
Published: (2024)

On Symmetric Losses for Robust Policy Optimization with Noisy Preferences
by: Nishimori, Soichiro, et al.
Published: (2025)

Reward-Augmented Data Enhances Direct Preference Alignment of LLMs
by: Zhang, Shenao, et al.
Published: (2024)

Learning Robust Diffusion Models from Imprecise Supervision
by: Wu, Dong-Dong, et al.
Published: (2025)

VI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance Reduction
by: Cai, Xin-Qiang, et al.
Published: (2026)

Rethinking Link Prediction for Directed Graphs
by: He, Mingguo, et al.
Published: (2025)

Direct Alignment with Heterogeneous Preferences
by: Shirali, Ali, et al.
Published: (2025)

IterIS: Iterative Inference-Solving Alignment for LoRA Merging
by: Chen, Hongxu, et al.
Published: (2024)

SGDPO: Self-Guided Direct Preference Optimization for Language Model Alignment
by: Zhu, Wenqiao, et al.
Published: (2025)

Off-Policy Corrected Reward Modeling for Reinforcement Learning from Human Feedback
by: Ackermann, Johannes, et al.
Published: (2025)

Offline Reinforcement Learning from Datasets with Structured Non-Stationarity
by: Ackermann, Johannes, et al.
Published: (2024)

Graph Prompting for Graph Learning Models: Recent Advances and Future Directions
by: Fu, Xingbo, et al.
Published: (2025)

Inference-Time Alignment of Diffusion Models with Direct Noise Optimization
by: Tang, Zhiwei, et al.
Published: (2024)

A Principled Loss Function for Direct Language Model Alignment
by: Tan, Yuandong
Published: (2025)

PSO-Merging: Merging Models Based on Particle Swarm Optimization
by: Zhang, Kehao, et al.
Published: (2025)

DAG-AFL:Directed Acyclic Graph-based Asynchronous Federated Learning
by: Zhang, Shuaipeng, et al.
Published: (2025)

On the Overlooked Pitfalls of Weight Decay and How to Mitigate Them: A Gradient-Norm Perspective
by: Xie, Zeke, et al.
Published: (2020)

More Agents Is All You Need
by: Li, Junyou, et al.
Published: (2024)

Towards Scalable Oversight via Partitioned Human Supervision
by: Yin, Ren, et al.
Published: (2025)

Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging
by: Yang, Jinluan, et al.
Published: (2025)

Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms
by: Rafailov, Rafael, et al.
Published: (2024)

Multi-Label Knowledge Distillation
by: Yang, Penghui, et al.
Published: (2023)

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

Weight Scope Alignment: A Frustratingly Easy Method for Model Merging
by: Xu, Yichu, et al.
Published: (2024)

Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization
by: Zhou, Zhanhui, et al.
Published: (2023)

Sparsity-Aware Evolution for Model Merging
by: Zhang, Huan, et al.
Published: (2026)

Automated Graph Machine Learning: Approaches, Libraries, Benchmarks and Directions
by: Wang, Xin, et al.
Published: (2022)

Differentiated Directional Intervention A Framework for Evading LLM Safety Alignment
by: Zhang, Peng, et al.
Published: (2025)

DirectMultiStep: Direct Route Generation for Multistep Retrosynthesis
by: Shee, Yu, et al.
Published: (2024)