AI Paper Atlas

Research map / Video / Video generation

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

Jiancheng Huang, Gengwei Zhang, Zequn Jie, Siyu Jiao, Yinlong Qian, Ling Chen, Yunchao Wei, Lin Ma

CVPR 2026 · Video › Video generation · approach: Compositional text-to-video diffusion · 15 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add text token re-composition (ablation)M4V MM-DiM block · VBench subset (fast eval)Overall-Cons: 19.77 -> 21.23Mixed
add per-frame visual registers (ablation)M4V MM-DiM block · VBench subset (fast eval)average score: 55.70 -> 56.79Improved
add temporal branch to text+register model (ablation)M4V MM-DiM block · VBench subset (fast eval)average score: 57.10 -> 58.75Improved
replace attention with Mamba in all blocks (Full) instead of full attention (ablation)PyramidFlow · VBench subset (fast eval, block design)average score: 59.84 -> 57.10 (TFLOPs 55.44 -> 26.64)Mixed
add parallel Mamba and attention in each block (ablation)full attention model · VBench subset (fast eval, block design)average score: 59.84 -> 59.97No clear effect
add reward learning post-training (ablation)M4V (PyramidFlow) · VBenchTotal Score: 81.55 -> 81.71Improved
add HunyuanVideo-generated training videos (ablation)M4V (PyramidFlow) · VBenchTotal Score: 81.55 -> 81.59No clear effect
combine reward learning with generated data (ablation)M4V (PyramidFlow) · VBenchSemantic Score: 74.47 -> 76.10Improved
replace Wan2.1 self-attention with MM-DiM blocksWan2.1 · VBenchTotal Score: 84.70 -> 86.14Improved
replace PyramidFlow attention with MM-DiM blocksPyramidFlow · VBenchTotal Score: 81.61 -> 81.55No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy