Copertina

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

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Amin, Farhana, Afroz, Sabiha, Gharami, Kanchon, Moghadampanah, Mona, Nikolopoulos, Dimitrios S.
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Joint Embedding Variational Bayes
di: Oji, Amin, et al.
Pubblicazione: (2026)

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

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

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

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