Image de couverture de livre

Beyond Fixed Formulas: Data-Driven Linear Predictor for Efficient Diffusion Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Shen, Zhirong, Huang, Rui, Liu, Jiacheng, Zou, Chang, Cai, Peiliang, Zheng, Shikang, Shi, Zhengyi, Feng, Liang, Zhang, Linfeng
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers
par: Zheng, Shikang, et autres
Publié: (2025)

From Sketch to Fresco: Efficient Diffusion Transformer with Progressive Resolution
par: Zheng, Shikang, et autres
Publié: (2026)

Let Features Decide Their Own Solvers: Hybrid Feature Caching for Diffusion Transformers
par: Zheng, Shikang, et autres
Publié: (2025)

HiCache: A Plug-in Scaled-Hermite Upgrade for Taylor-Style Cache-then-Forecast Diffusion Acceleration
par: Feng, Liang, et autres
Publié: (2025)

FreqCa: Accelerating Diffusion Models via Frequency-Aware Caching
par: Liu, Jiacheng, et autres
Publié: (2025)

Focused Forcing: Content-Aware Per-Frame KV Selection for Efficient Autoregressive Video Diffusion
par: Cai, Peiliang, et autres
Publié: (2026)

Forecast the Principal, Stabilize the Residual: Subspace-Aware Feature Caching for Efficient Diffusion Transformers
par: Chen, Guantao, et autres
Publié: (2026)

A Survey on Cache Methods in Diffusion Models: Toward Efficient Multi-Modal Generation
par: Liu, Jiacheng, et autres
Publié: (2025)

MASC: Boosting Autoregressive Image Generation with a Manifold-Aligned Semantic Clustering
par: He, Lixuan, et autres
Publié: (2025)

SpecEdit: Training-Free Acceleration for Diffusion based Image Editing via Semantic Locking
par: Yan, Zhengan, et autres
Publié: (2026)

From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers
par: Liu, Jiacheng, et autres
Publié: (2025)

Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching
par: Zheng, Zhixin, et autres
Publié: (2025)

DreamOn: Diffusion Language Models For Code Infilling Beyond Fixed-size Canvas
par: Wu, Zirui, et autres
Publié: (2026)

SpeCa: Accelerating Diffusion Transformers with Speculative Feature Caching
par: Liu, Jiacheng, et autres
Publié: (2025)

Accelerating Diffusion Transformers with Token-wise Feature Caching
par: Zou, Chang, et autres
Publié: (2024)

Open Condensed Subgroups and Mackey's Formula
par: Tang, Jiacheng
Publié: (2024)

SAFE: Harnessing LLM for Scenario-Driven ADS Testing from Multimodal Crash Data
par: Luo, Siwei, et autres
Publié: (2025)

Tweedie's Formulae and Diffusion Generative Models Beyond Gaussian
par: Tang, Wenpin, et autres
Publié: (2026)

Predictor-Driven Diffusion for Spatiotemporal Generation
par: Yasuda, Yuki, et autres
Publié: (2026)

Beyond Linearization: Attributed Table Graphs for Table Reasoning
par: Wang, Yuxiang, et autres
Publié: (2026)

Distributional Shrinkage I: Universal Denoiser Beyond Tweedie's Formula
par: Liang, Tengyuan
Publié: (2025)

Counterfactual Data Augmentation with Denoising Diffusion for Graph Anomaly Detection
par: Xiao, Chunjing, et autres
Publié: (2024)

Efficient and Precise Force Field Optimization for Biomolecules Using DPA-2
par: Chang, Junhan, et autres
Publié: (2024)

ConFixGS: Learning to Fix Feedforward 3D Gaussian Splatting with Confidence-Aware Diffusion Priors in Driving Scenes
par: Song, Rui, et autres
Publié: (2026)

Fractional clique decompositions of dense balanced multipartite graphs
par: Feng, Tao, et autres
Publié: (2026)

Existence of magic rectangle sets over finite abelian groups
par: Yu, Shikang, et autres
Publié: (2024)

Efficient Trajectory Optimization for Autonomous Racing via Formula-1 Data-Driven Initialization
par: Shehadeh, Samir, et autres
Publié: (2026)

MARL-OT: Multi-Agent Reinforcement Learning Guided Online Fuzzing to Detect Safety Violation in Autonomous Driving Systems
par: Liang, Linfeng, et autres
Publié: (2025)

Integrability of Conformal Loop Ensemble: Imaginary DOZZ Formula and Beyond
par: Ang, Morris, et autres
Publié: (2021)

CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models
par: Dai, Runpeng, et autres
Publié: (2025)

A Difference Formula for Tensor-power Multiplicities
par: Shu, Hongfei, et autres
Publié: (2025)

Beyond Masks: Efficient, Flexible Diffusion Language Models via Deletion-Insertion Processes
par: Ding, Fangyu, et autres
Publié: (2026)

Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning
par: Ye, Jiacheng, et autres
Publié: (2024)

QAOA-Predictor: Forecasting Success Probabilities and Minimal Depths for Efficient Fixed-Parameter Optimization
par: Coelho, Rodrigo, et autres
Publié: (2026)

Joint Optimization of Data- and Model-Driven Probing Beams and Beam Predictor
par: Lu, Tianheng, et autres
Publié: (2024)

EEdit: Rethinking the Spatial and Temporal Redundancy for Efficient Image Editing
par: Yan, Zexuan, et autres
Publié: (2025)

CM-DQN: A Value-Based Deep Reinforcement Learning Model to Simulate Confirmation Bias
par: Shen, Jiacheng, et autres
Publié: (2024)

Readability Formulas, Systems and LLMs are Poor Predictors of Reading Ease
par: Klein, Keren Gruteke, et autres
Publié: (2025)

Private Credit Markets Theory, Evidence, and Emerging Frontiers
par: Zou, Jiacheng
Publié: (2026)

New Characterizations and Efficient Local Search for General Integer Linear Programming
par: Lin, Peng, et autres
Publié: (2023)