# MotiMotion: Motion-Controlled Video Generation with Visual Reasoning

arXiv: https://arxiv.org/abs/2605.22818 · HTML: https://mlsanity.com/paper/2605.22818/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 23 of its 94 references that are in the map.
- First posted on arXiv 21 May 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 23 of 23)

- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [Emerging Properties in Unified Multimodal Pretraining](https://mlsanity.com/paper/2505.14683/) (2025)
- [Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling](https://mlsanity.com/paper/2501.17811/) (2025)
- [DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory](https://mlsanity.com/paper/2308.08089/) (2023)
- [OmniGen2: Towards Instruction-Aligned Multimodal Generation](https://mlsanity.com/paper/2506.18871/) (2025)
- [Video models are zero-shot learners and reasoners](https://mlsanity.com/paper/2509.20328/) (2025)
- [Motion-Conditioned Diffusion Model for Controllable Video Synthesis](https://mlsanity.com/paper/2304.14404/) (2023)
- [UniVideo: Unified Understanding, Generation, and Editing for Videos](https://mlsanity.com/paper/2510.08377/) (2025)
- [MotionStream: Real-Time Video Generation with Interactive Motion Controls](https://mlsanity.com/paper/2511.01266/) (2025)
- [Inference-time Physics Alignment of Video Generative Models with Latent World Models](https://mlsanity.com/paper/2601.10553/) (2026)
- [VChain: Chain-of-Visual-Thought for Reasoning in Video Generation](https://mlsanity.com/paper/2510.05094/) (2025)
- [VideoAgent: Self-Improving Video Generation](https://mlsanity.com/paper/2410.10076/) (2024)
- [VidCRAFT3: Camera, Object, and Lighting Control for Image-to-Video Generation](https://mlsanity.com/paper/2502.07531/) (2025)
- [Generative Video Motion Editing with 3D Point Tracks](https://mlsanity.com/paper/2512.02015/) (2025)
- [Self-Correcting Text-to-Video Generation with Misalignment Detection and Localized Refinement](https://mlsanity.com/paper/2411.15115/) (2024)
- [MotionV2V: Editing Motion in a Video](https://mlsanity.com/paper/2511.20640/) (2025)
- [PhysMaster: Mastering Physical Representation for Video Generation via Reinforcement Learning](https://mlsanity.com/paper/2510.13809/) (2025)
- [Goal Force: Teaching Video Models To Accomplish Physics-Conditioned Goals](https://mlsanity.com/paper/2601.05848/) (2026)
- [MotionEdit: Benchmarking and Learning Motion-Centric Image Editing](https://mlsanity.com/paper/2512.10284/) (2025)
- [LAMP: Language-Assisted Motion Planning for Controllable Video Generation](https://mlsanity.com/paper/2512.03619/) (2025)
- [Plan-X: Instruct Video Generation via Semantic Planning](https://mlsanity.com/paper/2511.17986/) (2025)

## Built on by (most cited first, 1 of 1)

- [Physically Plausible Video Generation via Visual-Semantic Chain-of-Events Conditioning](https://mlsanity.com/paper/2609.00656/) (2026)

## Abstract (arXiv)

Current motion-controlled image-to-video generation models rigidly follow user-provided trajectories that are often sparse, imprecise, and causally incomplete. Such reliance often yields unnatural or implausible outcomes, especially by missing secondary causal consequences. To address this, we introduce MotiMotion, a novel framework that reformulates motion control as a reasoning-then-generation problem. To encourage causally grounded and commonsense-consistent interactions, we leverage a training-free vision-language reasoner to refine image-space coordinates of primary trajectories and to hallucinate plausible secondary motions. To further improve motion naturalness, we propose a confidence-aware control scheme that modulates guidance strength, enabling the model to closely follow high-confidence plans while correcting artifacts under low-confidence inputs with its internal generative priors. To support systematic evaluation, we curate a new image-to-video benchmark, MotiBench, consisting of interaction-centric scenes where new events are triggered by motion. Both VLM-based evaluation and a human study on MotiBench demonstrate that MotiMotion produces videos with more plausible object behaviors and interaction, and is preferred over existing approaches.