Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count% of corpus
0111 · Oct 202319922001200920172026
1 result for “text-to-video”
Ground-A-Video: Zero-shot Grounded Video Editing using Text-to-image Diffusion Modelscs.CV

Ground-A-Video edits videos without training, preserving intended changes.

problem Complex multi-attribute video editing with omitted or wrong changes.
method Grounding-guided video-to-video translation with Cross-Frame Gated Attention.
result Zero-shot multi-attribute video editing with improved accuracy and frame consistency.
video editingzero-shot learninggroundingtext-to-videodiffusion models
2023-10-02abs ↗pdf ↗