repoGitHubTrust 82 · PrimaryPublished 1mo agoLive · 1mo ago
FennelFetish/qapyq
AI-assisted media curator for large image/video datasets. Streamlined captioning, cropping, masking for LoRA/diffusion training workflows.
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 54%HumanForge: A Human-Centric Deepfake Video Benchmark with Multi-Agent Forgery Rationales →
- PossiblePossibly related (embedding) · 54%Whareformer: Learning to Track What is Where in Long Egocentric Videos →
- PossiblePossibly related (embedding) · 54%Dataset Biases and Shortcut Learning in Motion-Based AI-Generated Video Detection →
- PossiblePossibly related (embedding) · 51%Prompt-Adapter Context Routing for Parameter-Efficient Multi-Shot Long Video Extrapolation →
- PossiblePossibly related (embedding) · 51%RSICCLLM: A Multimodal Large Language Model for Remote Sensing Image Change Captioning →
- PossiblePossibly related (embedding) · 51%Evidence-Backed Video Question Answering →
Implements
paperHumanForge: A Human-Centric Deepfake Video Benchmark with Multi-Agent Forgery RationalespaperWhareformer: Learning to Track What is Where in Long Egocentric VideospaperDataset Biases and Shortcut Learning in Motion-Based AI-Generated Video DetectionpaperPrompt-Adapter Context Routing for Parameter-Efficient Multi-Shot Long Video ExtrapolationpaperRSICCLLM: A Multimodal Large Language Model for Remote Sensing Image Change Captioning
Implements (incoming)
Related across the graph
paperEvidence-Backed Video Question AnsweringpaperPrompt-Adapter Context Routing for Parameter-Efficient Multi-Shot Long Video ExtrapolationpaperHumanForge: A Human-Centric Deepfake Video Benchmark with Multi-Agent Forgery RationalespaperRSICCLLM: A Multimodal Large Language Model for Remote Sensing Image Change CaptioningpaperWhareformer: Learning to Track What is Where in Long Egocentric VideospaperDataset Biases and Shortcut Learning in Motion-Based AI-Generated Video Detection