Immune2V immunizes images against dual-stream I2V generation by enforcing temporally balanced latent divergence and aligning generative features to a precomputed collapse trajectory, yielding stronger persistent degradation than image-level baselines.
Animatediff: Animate your personalized text-to-image diffusion models without specific tuning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
LingBot-Video is an open-source MoE video foundation model for embodied intelligence that scales to 120B parameters, integrates robot data, and uses multi-dimensional RL to improve physical plausibility.
citing papers explorer
-
Immune2V: Image Immunization Against Dual-Stream Image-to-Video Generation
Immune2V immunizes images against dual-stream I2V generation by enforcing temporally balanced latent divergence and aligning generative features to a precomputed collapse trajectory, yielding stronger persistent degradation than image-level baselines.
-
Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence
LingBot-Video is an open-source MoE video foundation model for embodied intelligence that scales to 120B parameters, integrates robot data, and uses multi-dimensional RL to improve physical plausibility.