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
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
dataset 2
method 2
citation-polarity summary
representative citing papers
Base-Anchored Filtering suppresses weakly backbone-aligned LoRA spectral channels to cut memorization while preserving or improving generation quality, without data or re-training.
UniVL unifies vision and language into one mask-rendered input processed by an OCR backbone to condition diffusion models for spatially grounded image generation without a standalone text encoder.
InsightTok improves text and face fidelity in discrete image tokenization via content-aware perceptual losses, with gains transferring to autoregressive generation.
Emu3.5 is a native multimodal world model pre-trained on over 10 trillion vision-language tokens with next-token prediction, post-trained via reinforcement learning, and accelerated by Discrete Diffusion Adaptation for efficient interleaved generation and world exploration.
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.
Proposes Lipschitz regularization during fine-tuning to prevent distributional drift in personalized diffusion models, improving subject fidelity and prompt adherence.
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
Base-Anchored Filtering suppresses weakly backbone-aligned LoRA spectral channels to cut memorization while preserving or improving generation quality, without data or re-training.
-
UniVL: Unified Vision-Language Embedding for Spatially Grounded Contextual Image Generation
UniVL unifies vision and language into one mask-rendered input processed by an OCR backbone to condition diffusion models for spatially grounded image generation without a standalone text encoder.
-
InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation
InsightTok improves text and face fidelity in discrete image tokenization via content-aware perceptual losses, with gains transferring to autoregressive generation.
-
Emu3.5: Native Multimodal Models are World Learners
Emu3.5 is a native multimodal world model pre-trained on over 10 trillion vision-language tokens with next-token prediction, post-trained via reinforcement learning, and accelerated by Discrete Diffusion Adaptation for efficient interleaved generation and world exploration.
-
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.
-
Preserve and Personalize: Personalized Text-to-Image Diffusion Models without Distributional Drift
Proposes Lipschitz regularization during fine-tuning to prevent distributional drift in personalized diffusion models, improving subject fidelity and prompt adherence.