Pith. sign in

REVIEW 6 cited by

M4V: Multimodal Mamba for Efficient Text-to-Video Generation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2506.10915 v2 pith:F4TWELCR submitted 2025-06-12 cs.CV cs.AIcs.LG

M4V: Multimodal Mamba for Efficient Text-to-Video Generation

classification cs.CV cs.AIcs.LG
keywords multimodaltext-to-videogenerationmambaefficientmodelingspatiotemporalalternative
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Text-to-video generation has significantly enriched content creation and holds the potential to evolve into powerful world simulators. However, modeling the vast spatiotemporal space remains computationally demanding, particularly when employing Transformers, which incur quadratic complexity in sequence processing and thus limit practical applications. Recent advancements in linear-time sequence modeling, particularly the Mamba architecture, offer a more efficient alternative. Nevertheless, its plain design limits its direct applicability to multimodal and spatiotemporal video generation tasks. To address these challenges, we introduce M4V, a multimodal Mamba framework for efficient text-to-video generation. Specifically, a MultiModal diffusion Mamba (MM-DiM) block is designed within the framework to enable seamless integration of multimodal information and spatiotemporal modeling. In detail, we introduce a novel multimodal token re-composition design, which employs a bidirectional scheme for multimodal information integration through simple token arrangement, along with visual registers to enhance spatialtemporal consistency. As a result, the MM-DiM blocks in M4V reduce FLOPs by 45% compared with the attention-based alternative when generating videos at 768x1280 resolution. Additionally, several training strategies are explored in this work to provide a better understanding of training text-to-video models using only publicly available datasets. Extensive experiments on text-to-video benchmarks demonstrate M4V's ability to produce high-quality videos while significantly lowering computational costs. Project page: https://huangjch526.github.io/M4V_project/.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Setting the Stage: Text-Driven Scene-Consistent Image Generation

    cs.CV 2025-12 conditional novelty 7.0

    A new data pipeline using real photos, entity removal, and image-to-video models plus a cross-view attention loss enables text-driven generation of actors in reference scenes with improved alignment.

  2. MobileWan: Closing the Quality Gap for Mobile Video Diffusion

    cs.CV 2026-07 conditional novelty 6.0

    A 5B-parameter video diffusion transformer is made deployable on mobile hardware via recurrence distillation, learnable head pruning, step distillation, and decoder optimization, achieving 83.79 VBench at 20s latency.

  3. OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation

    cs.CV 2026-04 unverdicted novelty 6.0

    OmniShow unifies text, image, audio, and pose conditions into an end-to-end model for high-quality human-object interaction video generation and introduces the HOIVG-Bench benchmark, claiming state-of-the-art results.

  4. SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routing

    cs.CV 2026-03 conditional novelty 6.0

    Parameter-free centroid compensation plus error-aware block routing yields a better quality–density Pareto frontier for sparse attention in video DiTs than score-based sparsification.

  5. FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving

    cs.CV 2025-05 conditional novelty 6.0

    FSDrive uses a generated future scene frame as visual spatio-temporal CoT to improve VLA models for safer autonomous driving trajectory prediction.

  6. MobileWan: Closing the Quality Gap for Mobile Video Diffusion

    cs.CV 2026-07 conditional novelty 5.0

    A 5B-parameter video diffusion transformer can be compressed and reformulated as an RNN to generate 5s 480x832 videos on a Snapdragon 8 Gen 5 mobile NPU in about 20 seconds with a VBench score of 83.79.