Imagen de Portada

Toward Theoretical Insights into Diffusion Trajectory Distillation via Operator Merging

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Gao, Weiguo, Li, Ming
Formato:	Preprint
Publicado:	2025
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

How Do Flow Matching Models Memorize and Generalize in Sample Data Subspaces?
por: Gao, Weiguo, et al.
Publicado: (2024)

Model Merging via Multi-Teacher Knowledge Distillation
por: Dalili, Seyed Arshan, et al.
Publicado: (2025)

MEP: Multiple Kernel Learning Enhancing Relative Positional Encoding Length Extrapolation
por: Gao, Weiguo
Publicado: (2024)

Convergence Dynamics and Stabilization Strategies of Co-Evolving Generative Models
por: Gao, Weiguo, et al.
Publicado: (2025)

Accelerating Diffusion Planners in Offline RL via Reward-Aware Consistency Trajectory Distillation
por: Duan, Xintong, et al.
Publicado: (2025)

Merge-of-Thought Distillation
por: Shen, Zhanming, et al.
Publicado: (2025)

SimMerge: Learning to Select Merge Operators from Similarity Signals
por: Bolton, Oliver, et al.
Publicado: (2026)

ProFlow: Zero-Shot Physics-Consistent Sampling via Proximal Flow Guidance
por: Yu, Zichao, et al.
Publicado: (2026)

VISTA: Validation-Informed Trajectory Adaptation via Self-Distillation
por: Corn, Eli, et al.
Publicado: (2026)

d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation
por: Qian, Yu-Yang, et al.
Publicado: (2026)

MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
por: Duan, Wenchang, et al.
Publicado: (2026)

Modelling Customer Trajectories with Reinforcement Learning for Practical Retail Insights
por: Lee, Ken Ming, et al.
Publicado: (2026)

MemCollab: Cross-Model Memory Collaboration via Contrastive Trajectory Distillation
por: Chang, Yurui, et al.
Publicado: (2026)

World Models via Policy-Guided Trajectory Diffusion
por: Rigter, Marc, et al.
Publicado: (2023)

FedNano: Toward Lightweight Federated Tuning for Pretrained Multimodal Large Language Models
por: Zhang, Yao, et al.
Publicado: (2025)

Learning without Global Backpropagation via Synergistic Information Distillation
por: Ye, Chenhao, et al.
Publicado: (2025)

ES-Merging: Biological MLLM Merging via Embedding Space Signals
por: Lee, Wonbin, et al.
Publicado: (2026)

Beyond the Proxy: Trajectory-Distilled Guidance for Offline GFlowNet Training
por: Chen, Ruishuo, et al.
Publicado: (2025)

ToMA: Token Merge with Attention for Diffusion Models
por: Lu, Wenbo, et al.
Publicado: (2025)

EM Distillation for One-step Diffusion Models
por: Xie, Sirui, et al.
Publicado: (2024)

Constraint-Guided Prediction Refinement via Deterministic Diffusion Trajectories
por: Dogoulis, Pantelis, et al.
Publicado: (2025)

Toward a Holistic Approach to Continual Model Merging
por: Phan, Hoang, et al.
Publicado: (2025)

One Fits All: General Mobility Trajectory Modeling via Masked Conditional Diffusion
por: Long, Qingyue, et al.
Publicado: (2025)

DiffMove: Group Mobility Tendency Enhanced Trajectory Recovery via Diffusion Model
por: Long, Qingyue, et al.
Publicado: (2025)

MIN-Merging: Merge the Important Neurons for Model Merging
por: Liang, Yunfei
Publicado: (2025)

Improving Classifier-Free Guidance in Masked Diffusion: Low-Dim Theoretical Insights with High-Dim Impact
por: Rojas, Kevin, et al.
Publicado: (2025)

Bridging Smoothness and Approximation: Theoretical Insights into Over-Smoothing in Graph Neural Networks
por: Yang, Guangrui, et al.
Publicado: (2024)

MergeMix: Optimizing Mid-Training Data Mixtures via Learnable Model Merging
por: Wang, Jiapeng, et al.
Publicado: (2026)

CAT Merging: A Training-Free Approach for Resolving Conflicts in Model Merging
por: Sun, Wenju, et al.
Publicado: (2025)

Towards Understanding Text Hallucination of Diffusion Models via Local Generation Bias
por: Lu, Rui, et al.
Publicado: (2025)

Representations Shape Weak-to-Strong Generalization: Theoretical Insights and Empirical Predictions
por: Xue, Yihao, et al.
Publicado: (2025)

One-Step Offline Distillation of Diffusion-based Models via Koopman Modeling
por: Berman, Nimrod, et al.
Publicado: (2025)

Bayesian Model Merging
por: Li, Kaiyang, et al.
Publicado: (2026)

Physics Informed Distillation for Diffusion Models
por: Tee, Joshua Tian Jin, et al.
Publicado: (2024)

On the Memorization of Consistency Distillation for Diffusion Models
por: Jiang, Bingqing, et al.
Publicado: (2026)

Operator-Theoretic Framework for Gradient-Free Federated Learning
por: Kumar, Mohit, et al.
Publicado: (2025)

Dynamic Population Distribution Aware Human Trajectory Generation with Diffusion Model
por: Long, Qingyue, et al.
Publicado: (2025)

Merging Smarter, Generalizing Better: Enhancing Model Merging on OOD Data
por: Zhang, Bingjie, et al.
Publicado: (2025)

Merge to Mix: Mixing Datasets via Model Merging
por: Tao, Zhixu Silvia, et al.
Publicado: (2025)

Towards the Law of Capacity Gap in Distilling Language Models
por: Zhang, Chen, et al.
Publicado: (2023)