# When Physical Preferences Meet Semantic Constraints: Physical and Semantic Direct Preference Optimization for Text-to-Video Generation

arXiv: https://arxiv.org/abs/2607.16947 · HTML: https://mlsanity.com/paper/2607.16947/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and multimodal model alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 41 of its 54 references that are in the map.
- First posted on arXiv 18 Jul 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/)

## Builds on (most cited first, 30 of 41)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [WorldSimBench: Towards Video Generation Models as World Simulators](https://mlsanity.com/paper/2410.18072/) (2024)
- [VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding](https://mlsanity.com/paper/2109.14084/) (2021)
- [LTX-Video: Realtime Video Latent Diffusion](https://mlsanity.com/paper/2501.00103/) (2024)
- [InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation](https://mlsanity.com/paper/2307.06942/) (2023)
- [PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics](https://mlsanity.com/paper/2311.12198/) (2023)
- [EvalCrafter: Benchmarking and Evaluating Large Video Generation Models](https://mlsanity.com/paper/2310.11440/) (2023)
- [VideoPhy: Evaluating Physical Commonsense for Video Generation](https://mlsanity.com/paper/2406.03520/) (2024)
- [A Note on the Inception Score](https://mlsanity.com/paper/1801.01973/) (2018)
- [How Far is Video Generation from World Model: A Physical Law Perspective](https://mlsanity.com/paper/2411.02385/) (2024)
- [PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation](https://mlsanity.com/paper/2409.18964/) (2024)
- [Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation](https://mlsanity.com/paper/2410.05363/) (2024)
- [Understanding World or Predicting Future? A Comprehensive Survey of World Models](https://mlsanity.com/paper/2411.14499/) (2024)
- [VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation](https://mlsanity.com/paper/2503.06800/) (2025)
- [VideoDPO: Omni-Preference Alignment for Video Diffusion Generation](https://mlsanity.com/paper/2412.14167/) (2024)
- [WISA: World Simulator Assistant for Physics-Aware Text-to-Video Generation](https://mlsanity.com/paper/2503.08153/) (2025)
- [PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation](https://mlsanity.com/paper/2412.00596/) (2024)

## Built on by (most cited first, 4 of 4)

- [Multi-Branch Policy Optimization for Multimodal Large Language Models](https://mlsanity.com/paper/2608.07581/) (2026)
- [Beyond Visual Similarity: Entity-Aligned Retrieval for Knowledge-Based Visual Question Answering](https://mlsanity.com/paper/2608.21450/) (2026)
- [Physis-Lang: Self-Evolving Language as a Physical Representation for Video World Model](https://mlsanity.com/paper/2609.40358/) (2026)
- [PhyMetric: Diagnosing Physical Plausibility in Text-to-Video Generation via Scene-Level QA](https://mlsanity.com/paper/2610.19823/) (2026)

## Abstract (arXiv)

Text-to-video (T2V) generation models have achieved strong visual realism, but improving physical plausibility can come at the cost of semantic consistency with the input text. This tension arises because physical preference is typically determined by comparing dynamics between two videos, without accounting for whether either video faithfully depicts the scene specified by the prompt, making physical-semantic conflict a systematic tendency under this supervision paradigm. We formulate this challenge as a constrained preference optimization problem and propose Physical and Semantic Direct Preference Optimization (PSDPO), which modulates each preference pair's contribution based on the agreement between its physical and semantic signals. A gradient-level analysis shows that PSDPO bounds the semantic drift from conflicting pairs to a controllable residual, and further motivates a staged optimization protocol that provably reduces cumulative drift. The resulting method operates entirely within the standard DPO framework, requiring no auxiliary models or additional loss terms. Experiments show that PSDPO improves physical plausibility by up to 2× over the baseline on VideoPhy-2, while maintaining strong semantic consistency on VBench, achieving a more reliable balance than existing preference-based methods.