Copertina

Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Yiheng, Liang, Feng, Kondratyuk, Dan, Tomizuka, Masayoshi, Keutzer, Kurt, Xu, Chenfeng
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Immiscible Diffusion: Accelerating Diffusion Training with Noise Assignment
di: Li, Yiheng, et al.
Pubblicazione: (2024)

A Lesson in Splats: Teacher-Guided Diffusion for 3D Gaussian Splats Generation with 2D Supervision
di: Peng, Chensheng, et al.
Pubblicazione: (2024)

Looking Backward: Streaming Video-to-Video Translation with Feature Banks
di: Liang, Feng, et al.
Pubblicazione: (2024)

StreamDiffusion: A Pipeline-level Solution for Real-time Interactive Generation
di: Kodaira, Akio, et al.
Pubblicazione: (2023)

Q-SLAM: Quadric Representations for Monocular SLAM
di: Peng, Chensheng, et al.
Pubblicazione: (2024)

DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes
di: Peng, Chensheng, et al.
Pubblicazione: (2024)

Pre-training on Synthetic Driving Data for Trajectory Prediction
di: Li, Yiheng, et al.
Pubblicazione: (2023)

Rethinking Image-to-3D Generation with Sparse Queries: Efficiency, Capacity, and Input-View Bias
di: Xu, Zhiyuan, et al.
Pubblicazione: (2026)

What Matters to You? Towards Visual Representation Alignment for Robot Learning
di: Tian, Ran, et al.
Pubblicazione: (2023)

Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
di: Xi, Haocheng, et al.
Pubblicazione: (2025)

DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving
di: Lu, Hao, et al.
Pubblicazione: (2024)

SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Execution
di: Liang, Zhixuan, et al.
Pubblicazione: (2023)

HallE-Control: Controlling Object Hallucination in Large Multimodal Models
di: Zhai, Bohan, et al.
Pubblicazione: (2023)

R3D2: Realistic 3D Asset Insertion via Diffusion for Autonomous Driving Simulation
di: Ljungbergh, William, et al.
Pubblicazione: (2025)

PixelGaussian: Generalizable 3D Gaussian Reconstruction from Arbitrary Views
di: Fei, Xin, et al.
Pubblicazione: (2024)

Driv3R: Learning Dense 4D Reconstruction for Autonomous Driving
di: Fei, Xin, et al.
Pubblicazione: (2024)

TrajSSL: Trajectory-Enhanced Semi-Supervised 3D Object Detection
di: Jacobson, Philip, et al.
Pubblicazione: (2024)

Segment Any Motion in Videos
di: Huang, Nan, et al.
Pubblicazione: (2025)

$\textit{S}^3$Gaussian: Self-Supervised Street Gaussians for Autonomous Driving
di: Huang, Nan, et al.
Pubblicazione: (2024)

Reimagination with Test-time Observation Interventions: Distractor-Robust World Model Predictions for Visual Model Predictive Control
di: Chen, Yuxin, et al.
Pubblicazione: (2025)

StreamDiffusionV2: A Streaming System for Dynamic and Interactive Video Generation
di: Feng, Tianrui, et al.
Pubblicazione: (2025)

DSLO: Deep Sequence LiDAR Odometry Based on Inconsistent Spatio-temporal Propagation
di: Zhang, Huixin, et al.
Pubblicazione: (2024)

Maximizing Alignment with Minimal Feedback: Efficiently Learning Rewards for Visuomotor Robot Policy Alignment
di: Tian, Ran, et al.
Pubblicazione: (2024)

Sparse Refinement for Efficient High-Resolution Semantic Segmentation
di: Liu, Zhijian, et al.
Pubblicazione: (2024)

CompGS: Unleashing 2D Compositionality for Compositional Text-to-3D via Dynamically Optimizing 3D Gaussians
di: Ge, Chongjian, et al.
Pubblicazione: (2024)

X-Drive: Cross-modality consistent multi-sensor data synthesis for driving scenarios
di: Xie, Yichen, et al.
Pubblicazione: (2024)

Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation
di: Yang, Shuo, et al.
Pubblicazione: (2025)

ODE$_t$(ODE$_l$): Shortcutting the Time and the Length in Diffusion and Flow Models for Faster Sampling
di: Gudovskiy, Denis, et al.
Pubblicazione: (2025)

Trajectory-Consistent Calibration for Cache-Accelerated Diffusion Models
di: Liang, Mingyu, et al.
Pubblicazione: (2026)

Optimizing Diffusion Models for Joint Trajectory Prediction and Controllable Generation
di: Wang, Yixiao, et al.
Pubblicazione: (2024)

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers
di: Ren, Sucheng, et al.
Pubblicazione: (2025)

Magic-Me: Identity-Specific Video Customized Diffusion
di: Ma, Ze, et al.
Pubblicazione: (2024)

Training-free Diffusion Acceleration with Bottleneck Sampling
di: Tian, Ye, et al.
Pubblicazione: (2025)

Less is Enough: Training-Free Video Diffusion Acceleration via Runtime-Adaptive Caching
di: Zhou, Xin, et al.
Pubblicazione: (2025)

Just-in-Time: Training-Free Spatial Acceleration for Diffusion Transformers
di: Sun, Wenhao, et al.
Pubblicazione: (2026)

UniDrive: Towards Universal Driving Perception Across Camera Configurations
di: Li, Ye, et al.
Pubblicazione: (2024)

Denoising as Path Planning: Training-Free Acceleration of Diffusion Models with DPCache
di: Cui, Bowen, et al.
Pubblicazione: (2026)

LDGNet: A Lightweight Difference Guiding Network for Remote Sensing Change Detection
di: Xu, Chenfeng
Pubblicazione: (2025)

MALT Diffusion: Memory-Augmented Latent Transformers for Any-Length Video Generation
di: Yu, Sihyun, et al.
Pubblicazione: (2025)

DexHandDiff: Interaction-aware Diffusion Planning for Adaptive Dexterous Manipulation
di: Liang, Zhixuan, et al.
Pubblicazione: (2024)