Imagen de Portada

Goodbye Drift: Anchored Tree Sampling for Long-Horizon Video-to-Video Generation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Bendel, Matthew, Bailey, Stephen W., Vaidya, Mithilesh, Badam, Sumukh, He, Xingzhe
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

PoDAR: Power-Disentangled Audio Representation for Generative Modeling
por: Luebs, Alejandro, et al.
Publicado: (2026)

Entropy-Guided k-Guard Sampling for Long-Horizon Autoregressive Video Generation
por: Han, Yizhao, et al.
Publicado: (2026)

Learning a Particle Dynamics Model with Real-world Videos
por: Kim, Chanho, et al.
Publicado: (2026)

RELIC: Interactive Video World Model with Long-Horizon Memory
por: Hong, Yicong, et al.
Publicado: (2025)

Event-Anchored Frame Selection for Effective Long-Video Understanding
por: Chen, Wang, et al.
Publicado: (2026)

OmniRoam: World Wandering via Long-Horizon Panoramic Video Generation
por: Liu, Yuheng, et al.
Publicado: (2026)

Long-Horizon Streaming Video Generation via Hybrid Attention with Decoupled Distillation
por: Li, Ruibin, et al.
Publicado: (2026)

WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception
por: Liu, Zhiheng, et al.
Publicado: (2025)

Train Short, Inference Long: Training-free Horizon Extension for Autoregressive Video Generation
por: Li, Jia, et al.
Publicado: (2026)

LongVPO: From Anchored Cues to Self-Reasoning for Long-Form Video Preference Optimization
por: Huang, Zhenpeng, et al.
Publicado: (2026)

Anchored Video Generation: Decoupling Scene Construction and Temporal Synthesis in Text-to-Video Diffusion Models
por: Hassan, Mariam, et al.
Publicado: (2025)

Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video Generation
por: Guo, Yanjun, et al.
Publicado: (2026)

RoboEnvision: A Long-Horizon Video Generation Model for Multi-Task Robot Manipulation
por: Yang, Liudi, et al.
Publicado: (2025)

Anchored Diffusion for Video Face Reenactment
por: Kligvasser, Idan, et al.
Publicado: (2024)

SurgLQA: Scalable Long-Horizon Surgical Video Question Answering
por: Guo, Diandian, et al.
Publicado: (2026)

MedHorizon: Towards Long-context Medical Video Understanding in the Wild
por: Du, Bodong, et al.
Publicado: (2026)

VideoSeek: Long-Horizon Video Agent with Tool-Guided Seeking
por: Lin, Jingyang, et al.
Publicado: (2026)

VTAgent: Agentic Keyframe Anchoring for Evidence-Aware Video TextVQA
por: He, Haibin, et al.
Publicado: (2026)

Multi-sentence Video Grounding for Long Video Generation
por: Feng, Wei, et al.
Publicado: (2024)

VideoAuteur: Towards Long Narrative Video Generation
por: Xiao, Junfei, et al.
Publicado: (2025)

MagicWorld: Towards Long-Horizon Stability for Interactive Video World Exploration
por: Li, Guangyuan, et al.
Publicado: (2025)

AndroTMem: From Interaction Trajectories to Anchored Memory in Long-Horizon GUI Agents
por: Shi, Yibo, et al.
Publicado: (2026)

LatentKeypointGAN: Controlling Images via Latent Keypoints
por: He, Xingzhe, et al.
Publicado: (2021)

VideoMerge: Towards Training-free Long Video Generation
por: Zhang, Siyang, et al.
Publicado: (2025)

SAGE: Training Smart Any-Horizon Agents for Long Video Reasoning with Reinforcement Learning
por: Jain, Jitesh, et al.
Publicado: (2025)

Long Context Tuning for Video Generation
por: Guo, Yuwei, et al.
Publicado: (2025)

pcaGAN: Improving Posterior-Sampling cGANs via Principal Component Regularization
por: Bendel, Matthew C., et al.
Publicado: (2024)

VideoForest: Person-Anchored Hierarchical Reasoning for Cross-Video Question Answering
por: Meng, Yiran, et al.
Publicado: (2025)

AR2-4FV: Anchored Referring and Re-identification for Long-Term Grounding in Fixed-View Videos
por: Yan, Teng, et al.
Publicado: (2026)

Moment Sampling in Video LLMs for Long-Form Video QA
por: Chasmai, Mustafa, et al.
Publicado: (2025)

Video-Infinity: Distributed Long Video Generation
por: Tan, Zhenxiong, et al.
Publicado: (2024)

Towards Long Video Understanding via Fine-detailed Video Story Generation
por: You, Zeng, et al.
Publicado: (2024)

VideoSSM: Autoregressive Long Video Generation with Hybrid State-Space Memory
por: Yu, Yifei, et al.
Publicado: (2025)

SpatialMem: Metric-Aligned Long-Horizon Video Memory for Language Grounding and QA
por: Zheng, Xinyi, et al.
Publicado: (2026)

PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference
por: Mao, Xiaofeng, et al.
Publicado: (2026)

LongLive: Real-time Interactive Long Video Generation
por: Yang, Shuai, et al.
Publicado: (2025)

Towards Chunk-Wise Generation for Long Videos
por: Zhang, Siyang, et al.
Publicado: (2024)

QueST: Persistent Queries as Semantic Monitors for Drift Suppression in Long-Horizon Tracking
por: Anand, Mayank, et al.
Publicado: (2026)

VideoOdyssey: A Benchmark for Ultra-Long-Context and Omni-Modal Video Understanding
por: He, Haichen, et al.
Publicado: (2026)

Dual-Anchoring: Addressing State Drift in Vision-Language Navigation
por: Wu, Kangyi, et al.
Publicado: (2026)