M²-REPA decouples modality-specific features from diffusion intermediates and aligns them to complementary expert foundation models via a multi-modal alignment loss and modality-specific decoupling regularization for improved multimodal video generation.
arXiv preprint arXiv:2508.15720 , year=
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.CV 6roles
background 2polarities
background 2representative citing papers
HYDRA-X presents the first unified multimodal model using a single ViT for holistic image-video tokenization, with ablations on attention and compression plus a latent-level editing improvement.
TunerDiT adds event-partitioned masking and cross-event prompt fusion to diffusion transformers for training-free multi-event video generation, with gains scaling by event count on a new Meve benchmark.
SWIFT introduces a semantic injection cache with head-wise updates and an adaptive dynamic window plus segment anchors to achieve efficient multi-prompt long video generation at 22.6 FPS while preserving quality in causal diffusion models.
Self-Forcing++ scales autoregressive video diffusion to over 4 minutes by using self-generated segments for guidance, reducing error accumulation and outperforming baselines in fidelity and consistency.
Rolling Forcing generates multi-minute videos in real time by jointly denoising frames at increasing noise levels, anchoring attention to early frames, and using windowed distillation to limit error accumulation.
citing papers explorer
-
Divide and Conquer: Decoupled Representation Alignment for Multimodal World Models
M²-REPA decouples modality-specific features from diffusion intermediates and aligns them to complementary expert foundation models via a multi-modal alignment loss and modality-specific decoupling regularization for improved multimodal video generation.
-
HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers
HYDRA-X presents the first unified multimodal model using a single ViT for holistic image-video tokenization, with ablations on attention and compression plus a latent-level editing improvement.
-
TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Video Generation
TunerDiT adds event-partitioned masking and cross-event prompt fusion to diffusion transformers for training-free multi-event video generation, with gains scaling by event count on a new Meve benchmark.
-
SWIFT: Prompt-Adaptive Memory for Efficient Interactive Long Video Generation
SWIFT introduces a semantic injection cache with head-wise updates and an adaptive dynamic window plus segment anchors to achieve efficient multi-prompt long video generation at 22.6 FPS while preserving quality in causal diffusion models.
-
Self-Forcing++: Towards Minute-Scale High-Quality Video Generation
Self-Forcing++ scales autoregressive video diffusion to over 4 minutes by using self-generated segments for guidance, reducing error accumulation and outperforming baselines in fidelity and consistency.
-
Rolling Forcing: Autoregressive Long Video Diffusion in Real Time
Rolling Forcing generates multi-minute videos in real time by jointly denoising frames at increasing noise levels, anchoring attention to early frames, and using windowed distillation to limit error accumulation.