# Video Analysis and Generation via a Semantic Progress Function

arXiv: https://arxiv.org/abs/2604.22554 · HTML: https://mlsanity.com/paper/2604.22554/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 32 references that are in the map.
- First posted on arXiv 24 Apr 2026.

## Builds on (most cited first, 19 of 19)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation](https://mlsanity.com/paper/2008.00951/) (2020)
- [LTX-Video: Realtime Video Latent Diffusion](https://mlsanity.com/paper/2501.00103/) (2024)
- [Designing an Encoder for StyleGAN Image Manipulation](https://mlsanity.com/paper/2102.02766/) (2021)
- [ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement](https://mlsanity.com/paper/2104.02699/) (2021)
- [LTX-2: Efficient Joint Audio-Visual Foundation Model](https://mlsanity.com/paper/2601.03233/) (2026)
- [DiffMorpher: Unleashing the Capability of Diffusion Models for Image Morphing](https://mlsanity.com/paper/2312.07409/) (2023)
- [RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers](https://mlsanity.com/paper/2502.15894/) (2025)
- [VideoRoPE: What Makes for Good Video Rotary Position Embedding?](https://mlsanity.com/paper/2502.05173/) (2025)
- [Interpolating between Images with Diffusion Models](https://mlsanity.com/paper/2307.12560/) (2023)
- [LoViC: Efficient Long Video Generation with Context Compression](https://mlsanity.com/paper/2507.12952/) (2025)
- [FreeMorph: Tuning-Free Generalized Image Morphing with Diffusion Model](https://mlsanity.com/paper/2507.01953/) (2025)
- [RoPECraft: Training-Free Motion Transfer with Trajectory-Guided RoPE Optimization on Diffusion Transformers](https://mlsanity.com/paper/2505.13344/) (2025)
- [Image Morphing with Perceptual Constraints and STN Alignment](https://mlsanity.com/paper/2004.14071/) (2020)
- [STREAM: Spatio-TempoRal Evaluation and Analysis Metric for Video Generative Models](https://mlsanity.com/paper/2403.09669/) (2024)
- [TempoControl: Temporal Attention Guidance for Text-to-Video Models](https://mlsanity.com/paper/2510.02226/) (2025)

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

- [Token-to-Token Alignment of Text Embeddings for Semantic Blending](https://mlsanity.com/paper/2606.24021/) (2026)

## Abstract (arXiv)

Transformations produced by image and video generation models often evolve in a highly non-linear manner: long stretches where the content barely changes are followed by sudden, abrupt semantic jumps. To analyze and correct this behavior, we introduce a Semantic Progress Function, a one-dimensional representation that captures how the meaning of a given sequence evolves over time. For each frame, we compute distances between semantic embeddings and fit a smooth curve that reflects the cumulative semantic shift across the sequence. Departures of this curve from a straight line reveal uneven semantic pacing. Building on this insight, we propose a semantic linearization procedure that reparameterizes (or retimes) the sequence so that semantic change unfolds at a constant rate, yielding smoother and more coherent transitions. Beyond linearization, our framework provides a model-agnostic foundation for identifying temporal irregularities, comparing semantic pacing across different generators, and steering both generated and real-world video sequences toward arbitrary target pacing.