# VIPER: Visual In-Context Physics Reasoning for Physically Plausible Video Generation

arXiv: https://arxiv.org/abs/2607.23472 · HTML: https://mlsanity.com/paper/2607.23472/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 21 of its 37 references that are in the map.
- First posted on arXiv 26 Jul 2026.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 21 of 21)

- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models](https://mlsanity.com/paper/2401.09047/) (2024)
- [VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness](https://mlsanity.com/paper/2503.21755/) (2025)
- [Open-Sora Plan: Open-Source Large Video Generation Model](https://mlsanity.com/paper/2412.00131/) (2024)
- [In-Context LoRA for Diffusion Transformers](https://mlsanity.com/paper/2410.23775/) (2024)
- [WISA: World Simulator Assistant for Physics-Aware Text-to-Video Generation](https://mlsanity.com/paper/2503.08153/) (2025)
- [UniVideo: Unified Understanding, Generation, and Editing for Videos](https://mlsanity.com/paper/2510.08377/) (2025)
- [UNIC: Unified In-Context Video Editing](https://mlsanity.com/paper/2506.04216/) (2025)
- [Force Prompting: Video Generation Models Can Learn and Generalize Physics-based Control Signals](https://mlsanity.com/paper/2505.19386/) (2025)
- [PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation](https://mlsanity.com/paper/2509.20358/) (2025)
- [NewtonGen: Physics-Consistent and Controllable Text-to-Video Generation via Neural Newtonian Dynamics](https://mlsanity.com/paper/2509.21309/) (2025)
- [RealWonder: Real-Time Physical Action-Conditioned Video Generation](https://mlsanity.com/paper/2603.05449/) (2026)
- [Video-As-Prompt: Unified Semantic Control for Video Generation](https://mlsanity.com/paper/2510.20888/) (2025)
- [Physical Simulator In-the-Loop Video Generation](https://mlsanity.com/paper/2603.06408/) (2026)
- [Phantom: Physics-Infused Video Generation via Joint Modeling of Visual and Latent Physical Dynamics](https://mlsanity.com/paper/2604.08503/) (2026)
- [PhysChoreo: Physics-Controllable Video Generation with Part-Aware Semantic Grounding](https://mlsanity.com/paper/2511.20562/) (2025)
- [Goal Force: Teaching Video Models To Accomplish Physics-Conditioned Goals](https://mlsanity.com/paper/2601.05848/) (2026)

## Abstract (arXiv)

Modern video generation models can synthesize visually compelling and temporally coherent clips, yet controlling their physical behavior remains difficult with standard text and image conditions. The core challenge is a conditioning bottleneck: material response, contact interaction, deformation, and motion trajectory are continuous and relational physical cues that are hard to specify exhaustively in language but can be demonstrated naturally by video. We propose VIPER, a Visual In-Context Physics Reasoning framework for reference-guided image-to-video generation. Given a target image, a brief target prompt, and a reference video, VIPER treats the reference as a dense visual demonstration of the desired physical process rather than an appearance template. It uses a Multimodal Large Language Model (MLLM) to extract reference-derived physical cues and guide a pretrained image-to-video generator through a hierarchical training strategy, enabling physical behavior transfer while preserving the visual prior of the base generator. To support this setting, we construct VIPER-19K, a curated dataset with material, trajectory, and physical-impact annotations, together with filtered reference-target pairs. Experiments on an unseen validation set show that VIPER achieves stronger reference-video physical similarity and higher human preference than representative video generation and video-as-prompt baselines, while maintaining competitive general video quality. Qualitative results further demonstrate that VIPER can transfer reference-derived physical behavior to new target scenes without requiring carefully engineered prompts.