Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Bendel, Matthew, Bailey, Stephen W., Vaidya, Mithilesh, Badam, Sumukh, He, Xingzhe
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

PoDAR: Power-Disentangled Audio Representation for Generative Modeling
par: Luebs, Alejandro, et autres
Publié: (2026)

Entropy-Guided k-Guard Sampling for Long-Horizon Autoregressive Video Generation
par: Han, Yizhao, et autres
Publié: (2026)

Learning a Particle Dynamics Model with Real-world Videos
par: Kim, Chanho, et autres
Publié: (2026)

RELIC: Interactive Video World Model with Long-Horizon Memory
par: Hong, Yicong, et autres
Publié: (2025)

Event-Anchored Frame Selection for Effective Long-Video Understanding
par: Chen, Wang, et autres
Publié: (2026)

OmniRoam: World Wandering via Long-Horizon Panoramic Video Generation
par: Liu, Yuheng, et autres
Publié: (2026)

Long-Horizon Streaming Video Generation via Hybrid Attention with Decoupled Distillation
par: Li, Ruibin, et autres
Publié: (2026)

WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception
par: Liu, Zhiheng, et autres
Publié: (2025)

Train Short, Inference Long: Training-free Horizon Extension for Autoregressive Video Generation
par: Li, Jia, et autres
Publié: (2026)

LongVPO: From Anchored Cues to Self-Reasoning for Long-Form Video Preference Optimization
par: Huang, Zhenpeng, et autres
Publié: (2026)

Anchored Video Generation: Decoupling Scene Construction and Temporal Synthesis in Text-to-Video Diffusion Models
par: Hassan, Mariam, et autres
Publié: (2025)

Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video Generation
par: Guo, Yanjun, et autres
Publié: (2026)

RoboEnvision: A Long-Horizon Video Generation Model for Multi-Task Robot Manipulation
par: Yang, Liudi, et autres
Publié: (2025)

Anchored Diffusion for Video Face Reenactment
par: Kligvasser, Idan, et autres
Publié: (2024)

SurgLQA: Scalable Long-Horizon Surgical Video Question Answering
par: Guo, Diandian, et autres
Publié: (2026)

MedHorizon: Towards Long-context Medical Video Understanding in the Wild
par: Du, Bodong, et autres
Publié: (2026)

VideoSeek: Long-Horizon Video Agent with Tool-Guided Seeking
par: Lin, Jingyang, et autres
Publié: (2026)

VTAgent: Agentic Keyframe Anchoring for Evidence-Aware Video TextVQA
par: He, Haibin, et autres
Publié: (2026)

Multi-sentence Video Grounding for Long Video Generation
par: Feng, Wei, et autres
Publié: (2024)

VideoAuteur: Towards Long Narrative Video Generation
par: Xiao, Junfei, et autres
Publié: (2025)

MagicWorld: Towards Long-Horizon Stability for Interactive Video World Exploration
par: Li, Guangyuan, et autres
Publié: (2025)

AndroTMem: From Interaction Trajectories to Anchored Memory in Long-Horizon GUI Agents
par: Shi, Yibo, et autres
Publié: (2026)

LatentKeypointGAN: Controlling Images via Latent Keypoints
par: He, Xingzhe, et autres
Publié: (2021)

VideoMerge: Towards Training-free Long Video Generation
par: Zhang, Siyang, et autres
Publié: (2025)

SAGE: Training Smart Any-Horizon Agents for Long Video Reasoning with Reinforcement Learning
par: Jain, Jitesh, et autres
Publié: (2025)

Long Context Tuning for Video Generation
par: Guo, Yuwei, et autres
Publié: (2025)

pcaGAN: Improving Posterior-Sampling cGANs via Principal Component Regularization
par: Bendel, Matthew C., et autres
Publié: (2024)

VideoForest: Person-Anchored Hierarchical Reasoning for Cross-Video Question Answering
par: Meng, Yiran, et autres
Publié: (2025)

AR2-4FV: Anchored Referring and Re-identification for Long-Term Grounding in Fixed-View Videos
par: Yan, Teng, et autres
Publié: (2026)

Moment Sampling in Video LLMs for Long-Form Video QA
par: Chasmai, Mustafa, et autres
Publié: (2025)

Towards Long Video Understanding via Fine-detailed Video Story Generation
par: You, Zeng, et autres
Publié: (2024)

VideoSSM: Autoregressive Long Video Generation with Hybrid State-Space Memory
par: Yu, Yifei, et autres
Publié: (2025)

Video-Infinity: Distributed Long Video Generation
par: Tan, Zhenxiong, et autres
Publié: (2024)

SpatialMem: Metric-Aligned Long-Horizon Video Memory for Language Grounding and QA
par: Zheng, Xinyi, et autres
Publié: (2026)

PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference
par: Mao, Xiaofeng, et autres
Publié: (2026)

LongLive: Real-time Interactive Long Video Generation
par: Yang, Shuai, et autres
Publié: (2025)

Towards Chunk-Wise Generation for Long Videos
par: Zhang, Siyang, et autres
Publié: (2024)

QueST: Persistent Queries as Semantic Monitors for Drift Suppression in Long-Horizon Tracking
par: Anand, Mayank, et autres
Publié: (2026)

VideoOdyssey: A Benchmark for Ultra-Long-Context and Omni-Modal Video Understanding
par: He, Haichen, et autres
Publié: (2026)

Dual-Anchoring: Addressing State Drift in Vision-Language Navigation
par: Wu, Kangyi, et autres
Publié: (2026)