Imagen de Portada

FastSTAR: Spatiotemporal Token Pruning for Efficient Autoregressive Video Synthesis

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yune, Sungwoong, Jeong, Suheon, Kim, Joo-Young
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruning
por: Guo, Hang, et al.
Publicado: (2025)

MEVG: Multi-event Video Generation with Text-to-Video Models
por: Oh, Gyeongrok, et al.
Publicado: (2023)

TokenTrim: Inference-Time Token Pruning for Autoregressive Long Video Generation
por: Shaulov, Ariel, et al.
Publicado: (2026)

ORBIS: Output-Guided Token Reduction with Distribution-Aware Matching for Video Diffusion Acceleration
por: Lee, Hangyeol, et al.
Publicado: (2026)

PruneVid: Visual Token Pruning for Efficient Video Large Language Models
por: Huang, Xiaohu, et al.
Publicado: (2024)

EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation
por: Xiong, Tianwei, et al.
Publicado: (2026)

LightSplat: Fast and Memory-Efficient Open-Vocabulary 3D Scene Understanding in Five Seconds
por: Bang, Jaehun, et al.
Publicado: (2026)

Language-Guided Temporal Token Pruning for Efficient VideoLLM Processing
por: Kumar, Yogesh
Publicado: (2025)

Video Patch Pruning: Efficient Video Instance Segmentation via Early Token Reduction
por: Glandorf, Patrick, et al.
Publicado: (2026)

HieraVid: Hierarchical Token Pruning for Fast Video Large Language Models
por: Guo, Yansong, et al.
Publicado: (2026)

DocPrune:Efficient Document Question Answering via Background, Question, and Comprehension-aware Token Pruning
por: Choi, Joonmyung, et al.
Publicado: (2026)

Rethinking Token Reduction for Diffusion Models via Output-Similarity-Awareness
por: Lee, Hangyeol, et al.
Publicado: (2026)

EgoPrune: Efficient Token Pruning for Egomotion Video Reasoning in Embodied Agent
por: Li, Jiaao, et al.
Publicado: (2025)

Fast SAM2 with Text-Driven Token Pruning
por: Mandal, Avilasha, et al.
Publicado: (2025)

Efficient Video Sampling: Pruning Temporally Redundant Tokens for Faster VLM Inference
por: Bagrov, Natan, et al.
Publicado: (2025)

Autoregressive Universal Video Segmentation Model
por: Heo, Miran, et al.
Publicado: (2025)

Adaptive Begin-of-Video Tokens for Autoregressive Video Diffusion Models
por: Cheng, Tianle, et al.
Publicado: (2025)

Efficient Token Pruning for LLaDA-V
por: Wan, Zhewen, et al.
Publicado: (2026)

HiPrune: Hierarchical Attention for Efficient Token Pruning in Vision-Language Models
por: Liu, Jizhihui, et al.
Publicado: (2025)

EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens
por: Hwang, Sunil, et al.
Publicado: (2022)

VideoMAR: Autoregressive Video Generatio with Continuous Tokens
por: Yu, Hu, et al.
Publicado: (2025)

TokenDial: Continuous Attribute Control in Text-to-Video via Spatiotemporal Token Offsets
por: Liu, Zhixuan, et al.
Publicado: (2026)

PPT: Token Pruning and Pooling for Efficient Vision Transformers
por: Wu, Xinjian, et al.
Publicado: (2023)

Less is More: Token-Efficient Video-QA via Adaptive Frame-Pruning and Semantic Graph Integration
por: Wang, Shaoguang, et al.
Publicado: (2025)

StreamingAssistant: Efficient Visual Token Pruning for Accelerating Online Video Understanding
por: Jin, Xinqi, et al.
Publicado: (2025)

FastVID: Dynamic Density Pruning for Fast Video Large Language Models
por: Shen, Leqi, et al.
Publicado: (2025)

ERASE: Eliminating Redundant Visual Tokens via Adaptive Two-Stage Token Pruning
por: Lee, Yuna, et al.
Publicado: (2026)

ReDiPrune: Relevance-Diversity Pre-Projection Token Pruning for Efficient Multimodal LLMs
por: Yu, An, et al.
Publicado: (2026)

Unified Spatiotemporal Token Compression for Video-LLMs at Ultra-Low Retention
por: Du, Junhao, et al.
Publicado: (2026)

Token Merging via Spatiotemporal Information Mining for Surgical Video Understanding
por: Jiang, Xixi, et al.
Publicado: (2025)

From Slow Bidirectional to Fast Autoregressive Video Diffusion Models
por: Yin, Tianwei, et al.
Publicado: (2024)

Beyond Surrogate Gradients: Fully Differentiable Token Pruning for Vision-Language Models
por: He, Landi, et al.
Publicado: (2026)

Fast-Slow Efficient Training for Multimodal Large Language Models via Visual Token Pruning
por: Zhang, Dingkun, et al.
Publicado: (2026)

OSPO: Object-Centric Self-Improving Preference Optimization for Text-to-Image Generation
por: Oh, Yoonjin, et al.
Publicado: (2025)

Efficient Autoregressive Video Diffusion with Dummy Head
por: Guo, Hang, et al.
Publicado: (2026)

EventPrune: Cascaded Event-Assisted Token Pruning for Efficient First-Person Dynamic Spatial Reasoning
por: Ma, Pengtao, et al.
Publicado: (2026)

Efficient Autoregressive Shape Generation via Octree-Based Adaptive Tokenization
por: Deng, Kangle, et al.
Publicado: (2025)

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis
por: Zheng, Peng, et al.
Publicado: (2025)

MVFormer: Diversifying Feature Normalization and Token Mixing for Efficient Vision Transformers
por: Bae, Jongseong, et al.
Publicado: (2024)

Geometry-Guided 3D Visual Token Pruning for Video-Language Models
por: Li, Han, et al.
Publicado: (2026)