Imagen de Portada

DiffPro: Joint Timestep and Layer-Wise Precision Optimization for Efficient Diffusion Inference

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Amin, Farhana, Afroz, Sabiha, Gharami, Kanchon, Moghadampanah, Mona, Nikolopoulos, Dimitrios S.
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Modality Inflation: Energy Characterization and Optimization Opportunities for MLLM Inference
por: Moghadampanah, Mona, et al.
Publicado: (2025)

An Efficient Privacy-preserving Intrusion Detection Scheme for UAV Swarm Networks
por: Gharami, Kanchon, et al.
Publicado: (2025)

LLM-Guided Runtime Parameter Optimization for Energy-Efficient Model Inference
por: Crumpacker, Katelyn, et al.
Publicado: (2026)

TMPQ-DM: Joint Timestep Reduction and Quantization Precision Selection for Efficient Diffusion Models
por: Sun, Haojun, et al.
Publicado: (2024)

Diff-TONE: Timestep Optimization for iNstrument Editing in Text-to-Music Diffusion Models
por: Baoueb, Teysir, et al.
Publicado: (2025)

Depth-Wise Attention (DWAtt): A Layer Fusion Method for Data-Efficient Classification
por: ElNokrashy, Muhammad, et al.
Publicado: (2022)

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers
por: You, Haoran, et al.
Publicado: (2024)

KVTuner: Sensitivity-Aware Layer-Wise Mixed-Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference
por: Li, Xing, et al.
Publicado: (2025)

ProDiff: Prototype-Guided Diffusion for Minimal Information Trajectory Imputation
por: Bu, Tianci, et al.
Publicado: (2025)

KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing
por: Yang, Yifei, et al.
Publicado: (2024)

DepCap: Adaptive Block-Wise Parallel Decoding for Efficient Diffusion LM Inference
por: Xia, Xiang, et al.
Publicado: (2026)

Adaptive Layer Selection for Layer-Wise Token Pruning in LLM Inference
por: Taniguchi, Rei, et al.
Publicado: (2026)

Fine-tuning Diffusion Policies with Backpropagation Through Diffusion Timesteps
por: Yang, Ningyuan, et al.
Publicado: (2025)

TMRL: Diffusion Timestep-Modulated Pretraining Enables Exploration for Efficient Policy Finetuning
por: Hong, Matthew M., et al.
Publicado: (2026)

Optimizing Personalized Federated Learning through Adaptive Layer-Wise Learning
por: Chen, Weihang, et al.
Publicado: (2024)

Data Attribution for Diffusion Models: Timestep-induced Bias in Influence Estimation
por: Xie, Tong, et al.
Publicado: (2024)

MPQ-Diff: Mixed Precision Quantization for Diffusion Models
por: Maruzzelli, Rocco Manz, et al.
Publicado: (2024)

MaRVIn: A Cross-Layer Mixed-Precision RISC-V Framework for DNN Inference, from ISA Extension to Hardware Acceleration
por: Armeniakos, Giorgos, et al.
Publicado: (2025)

10Cache: Heterogeneous Resource-Aware Tensor Caching and Migration for LLM Training
por: Afroz, Sabiha, et al.
Publicado: (2025)

OrScale: Orthogonalised Optimization with Layer-Wise Trust-Ratio Scaling
por: Lou, Yuxuan, et al.
Publicado: (2026)

Bayesian Modeling for Uncertainty Management in Financial Risk Forecasting and Compliance
por: Mamun, Sharif Al, et al.
Publicado: (2025)

FuseDiff: Symmetry-Preserving Joint Diffusion for Dual-Target Structure-Based Drug Design
por: Wu, Jianliang, et al.
Publicado: (2026)

DiffKnock: Diffusion-based Knockoff Statistics for Neural Networks Inference
por: Ge, Heng, et al.
Publicado: (2025)

Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approach
por: Liu, Yaofang, et al.
Publicado: (2024)

SpecDiff: Accelerating Diffusion Model Inference with Self-Speculation
por: Pan, Jiayi, et al.
Publicado: (2025)

QPART: Adaptive Model Quantization and Dynamic Workload Balancing for Accuracy-aware Edge Inference
por: Li, Xiangchen, et al.
Publicado: (2025)

Layer-Wise High-Impact Parameter Ratio Optimization in Post-Training Quantization for Large Language Models
por: Pham, Cuong, et al.
Publicado: (2025)

Adaptive Non-uniform Timestep Sampling for Accelerating Diffusion Model Training
por: Kim, Myunsoo, et al.
Publicado: (2024)

AutoQRA: Joint Optimization of Mixed-Precision Quantization and Low-rank Adapters for Efficient LLM Fine-Tuning
por: Zhou, Changhai, et al.
Publicado: (2026)

Connecting Independently Trained Modes via Layer-Wise Connectivity
por: Tian, Yongding, et al.
Publicado: (2025)

Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation
por: Gharami, Kanchon, et al.
Publicado: (2025)

CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification
por: He, Junhui, et al.
Publicado: (2024)

RefiDiff: Progressive Refinement Diffusion for Efficient Missing Data Imputation
por: Ahamed, Md Atik, et al.
Publicado: (2025)

BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference
por: Kou, Siqi, et al.
Publicado: (2023)

ART for Diffusion Sampling: A Reinforcement Learning Approach to Timestep Schedule
por: Huang, Yilie, et al.
Publicado: (2026)

Joint Embedding Variational Bayes
por: Oji, Amin, et al.
Publicado: (2026)

DiffER: Categorical Diffusion for Chemical Retrosynthesis
por: Current, Sean, et al.
Publicado: (2025)

Dual Path Attribution: Efficient Attribution for SwiGLU-Transformers through Layer-Wise Target Propagation
por: Jantsch, Lasse Marten, et al.
Publicado: (2026)

DiffATS: Diffusion in Aligned Tensor Space
por: Lyu, Jinhua, et al.
Publicado: (2026)

DNN Memory Footprint Reduction via Post-Training Intra-Layer Multi-Precision Quantization
por: Ghavami, Behnam, et al.
Publicado: (2024)