Prompt-Adapter Context Routing for Parameter-Efficient Multi-Shot Long Video Extrapolation
We present PACR-Video, a parameter-efficient framework for multi-shot long video extrapolation that preserves recurring entities, scene structure, visual style, and causal progression without full generator fine-tuning. PACR-Video keeps a text-to-video diffusion transformer frozen and augments it with low-rank temporal adapters conditioned by learned shot-role prompt tokens. To maintain long-horizon coherence, it builds a recursive prompt bank that stores compact entity, location, action, and style prompts from previous shots, then routes them through adapter gates according to predicted narra
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
- Linked via arxiv authorAnna Cordoba →
Prompt-Adapter Context Routing for Parameter-Efficient Multi-Shot Long Video Extrapolation
- Linked via arxiv authorAdam Puente Tercero →
Prompt-Adapter Context Routing for Parameter-Efficient Multi-Shot Long Video Extrapolation
- Linked via arxiv authorNerea Angulo Hijo →
Prompt-Adapter Context Routing for Parameter-Efficient Multi-Shot Long Video Extrapolation
- Linked via arxiv authorMar Linares Tercero →
Prompt-Adapter Context Routing for Parameter-Efficient Multi-Shot Long Video Extrapolation
- Linked via arxiv authorJulia Barrientos →
Prompt-Adapter Context Routing for Parameter-Efficient Multi-Shot Long Video Extrapolation
- Linked via arxiv authorAinhoa Miranda →
Prompt-Adapter Context Routing for Parameter-Efficient Multi-Shot Long Video Extrapolation
- Linked via arxiv authorJesus Olivera →
Prompt-Adapter Context Routing for Parameter-Efficient Multi-Shot Long Video Extrapolation