classifier-free guidance 1diffusion models 1prompt conditioning 1temporal coherence 1text-to-video generation 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.CV2026
TPD: Temporal Prior Decoupling for Text-to-Video Diffusion Models
Taewon Kang, Matthias Zwicker
The paper introduces Temporal Prior Decoupling (TPD), a training‑free method that restores suppressed late‑segment information during diffusion sampling for text‑to‑video models, i…
cs.CV2026
DCR: Counterfactual Attractor Guidance for Rare Compositional Generation
Taewon Kang, Matthias Zwicker
Diffusion models generate realistic visual content, yet often fail to produce rare but plausible compositions. When prompted with combinations that are valid but underrepresented i…