Copertina

Block Cascading: Training Free Acceleration of Block-Causal Video Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Bandyopadhyay, Hmrishav, Pinnaparaju, Nikhil, Entezari, Rahim, Scott, Jim, Song, Yi-Zhe, Jampani, Varun
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

SD3.5-Flash: Distribution-Guided Distillation of Generative Flows
di: Bandyopadhyay, Hmrishav, et al.
Pubblicazione: (2025)

FlipSketch: Flipping Static Drawings to Text-Guided Sketch Animations
di: Bandyopadhyay, Hmrishav, et al.
Pubblicazione: (2024)

NitroFusion: High-Fidelity Single-Step Diffusion through Dynamic Adversarial Training
di: Chen, Dar-Yen, et al.
Pubblicazione: (2024)

Normalized Attention Guidance: Universal Negative Guidance for Diffusion Models
di: Chen, Dar-Yen, et al.
Pubblicazione: (2025)

What Sketch Explainability Really Means for Downstream Tasks
di: Bandyopadhyay, Hmrishav, et al.
Pubblicazione: (2024)

Stable Cinemetrics : Structured Taxonomy and Evaluation for Professional Video Generation
di: Chatterjee, Agneet, et al.
Pubblicazione: (2025)

Do Generalised Classifiers really work on Human Drawn Sketches?
di: Bandyopadhyay, Hmrishav, et al.
Pubblicazione: (2024)

SketchINR: A First Look into Sketches as Implicit Neural Representations
di: Bandyopadhyay, Hmrishav, et al.
Pubblicazione: (2024)

HumANDiff: Articulated Noise Diffusion for Motion-Consistent Human Video Generation
di: Hu, Tao, et al.
Pubblicazione: (2026)

BWCache: Accelerating Video Diffusion Transformers through Block-Wise Caching
di: Cui, Hanshuai, et al.
Pubblicazione: (2025)

Doodle Your 3D: From Abstract Freehand Sketches to Precise 3D Shapes
di: Bandyopadhyay, Hmrishav, et al.
Pubblicazione: (2023)

SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer
di: Chen, Junsong, et al.
Pubblicazione: (2025)

Next Block Prediction: Video Generation via Semi-Autoregressive Modeling
di: Ren, Shuhuai, et al.
Pubblicazione: (2025)

Incremental Open-set Domain Adaptation
di: Rakshit, Sayan, et al.
Pubblicazione: (2024)

FAIRT2V: Training-Free Debiasing for Text-to-Video Diffusion Models
di: Zhong, Haonan, et al.
Pubblicazione: (2026)

CorGi: Contribution-Guided Block-Wise Interval Caching for Training-Free Acceleration of Diffusion Transformers
di: Son, Yonglak, et al.
Pubblicazione: (2025)

Frame Guidance: Training-Free Guidance for Frame-Level Control in Video Diffusion Models
di: Jang, Sangwon, et al.
Pubblicazione: (2025)

Q-HyViT: Post-Training Quantization of Hybrid Vision Transformers with Bridge Block Reconstruction for IoT Systems
di: Lee, Jemin, et al.
Pubblicazione: (2023)

Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs
di: Hyun, Jeongseok, et al.
Pubblicazione: (2025)

Computational Tradeoffs in Image Synthesis: Diffusion, Masked-Token, and Next-Token Prediction
di: Kilian, Maciej, et al.
Pubblicazione: (2024)

HASTE: Training-Free Video Diffusion Acceleration via Head-Wise Adaptive Sparse Attention
di: Zheng, Xuzhe, et al.
Pubblicazione: (2026)

Blocks as Probes: Dissecting Categorization Ability of Large Multimodal Models
di: Fu, Bin, et al.
Pubblicazione: (2024)

FlashBlock: Attention Caching for Efficient Long-Context Block Diffusion
di: Chen, Zhuokun, et al.
Pubblicazione: (2026)

SketchDeco: Training-Free Latent Composition for Precise Sketch Colourisation
di: Utintu, Chaitat, et al.
Pubblicazione: (2024)

Foley Control: Aligning a Frozen Latent Text-to-Audio Model to Video
di: Rowles, Ciara, et al.
Pubblicazione: (2025)

Prism: Spectral-Aware Block-Sparse Attention
di: Wang, Xinghao, et al.
Pubblicazione: (2026)

FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality
di: Lv, Zhengyao, et al.
Pubblicazione: (2024)

PhyBlock: A Progressive Benchmark for Physical Understanding and Planning via 3D Block Assembly
di: Ma, Liang, et al.
Pubblicazione: (2025)

FreeVA: Offline MLLM as Training-Free Video Assistant
di: Wu, Wenhao
Pubblicazione: (2024)

Stable Part Diffusion 4D: Multi-View RGB and Kinematic Parts Video Generation
di: Zhang, Hao, et al.
Pubblicazione: (2025)

Partial Forward Blocking: A Novel Data Pruning Paradigm for Lossless Training Acceleration
di: Wu, Dongyue, et al.
Pubblicazione: (2025)

Unified Dense Prediction of Video Diffusion
di: Yang, Lehan, et al.
Pubblicazione: (2025)

BLADE: Block-Sparse Attention Meets Step Distillation for Efficient Video Generation
di: Gu, Youping, et al.
Pubblicazione: (2025)

BlockVid: Block Diffusion for High-Quality and Consistent Minute-Long Video Generation
di: Zhang, Zeyu, et al.
Pubblicazione: (2025)

Where is the Watermark? Interpretable Watermark Detection at the Block Level
di: Bulychev, Maria, et al.
Pubblicazione: (2025)

Prefix-Adaptive Block Diffusion for Efficient Document Recognition
di: Chai, Mingxu, et al.
Pubblicazione: (2026)

SV4D 2.0: Enhancing Spatio-Temporal Consistency in Multi-View Video Diffusion for High-Quality 4D Generation
di: Yao, Chun-Han, et al.
Pubblicazione: (2025)

$h$-control: Training-Free Camera Control via Block-Conditional Gibbs Refinement
di: Wang, Yuzhu, et al.
Pubblicazione: (2026)

Sparser Block-Sparse Attention via Token Permutation
di: Wang, Xinghao, et al.
Pubblicazione: (2025)

VMoBA: Mixture-of-Block Attention for Video Diffusion Models
di: Wu, Jianzong, et al.
Pubblicazione: (2025)