CausalCine enables real-time causal autoregressive multi-shot video generation via multi-shot training, content-aware memory routing for coherence, and distillation to few-step inference.
Laion-5b: An open large-scale dataset for training next generation image-text models.Advances in neural information processing systems, 35:25278–25294
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
BAF reduces memorization in diffusion LoRAs by filtering spectral channels of the adaptation weights that show weak alignment with the base model's principal subspace.
SPACE induces sparsity in cross-attention parameters via closed-form iterative updates to erase target concepts more effectively than dense baselines in large diffusion models.
citing papers explorer
-
CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives
CausalCine enables real-time causal autoregressive multi-shot video generation via multi-shot training, content-aware memory routing for coherence, and distillation to few-step inference.
-
Filtering Memorization from Parameter-Space in Diffusion Models
BAF reduces memorization in diffusion LoRAs by filtering spectral channels of the adaptation weights that show weak alignment with the base model's principal subspace.
-
Empty SPACE: Cross-Attention Sparsity for Concept Erasure in Diffusion Models
SPACE induces sparsity in cross-attention parameters via closed-form iterative updates to erase target concepts more effectively than dense baselines in large diffusion models.