# BioVid: Autoregressive Video Generation with Biological Behavior Semantic Comprehension

arXiv: https://arxiv.org/abs/2606.08674 · HTML: https://mlsanity.com/paper/2606.08674/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 21 references that are in the map.
- First posted on arXiv 7 Jun 2026.

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

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [MaskGIT: Masked Generative Image Transformer](https://mlsanity.com/paper/2202.04200/) (2022)
- [NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis](https://mlsanity.com/paper/1604.02808/) (2016)
- [Which Training Methods for GANs do actually Converge?](https://mlsanity.com/paper/1801.04406/) (2018)
- [VideoGPT: Video Generation using VQ-VAE and Transformers](https://mlsanity.com/paper/2104.10157/) (2021)
- [VideoPoet: A Large Language Model for Zero-Shot Video Generation](https://mlsanity.com/paper/2312.14125/) (2023)
- [Finite Scalar Quantization: VQ-VAE Made Simple](https://mlsanity.com/paper/2309.15505/) (2023)
- [Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer](https://mlsanity.com/paper/2204.03638/) (2022)
- [The relativistic discriminator: a key element missing from standard GAN](https://mlsanity.com/paper/1807.00734/) (2018)
- [The GAN is dead; long live the GAN! A Modern GAN Baseline](https://mlsanity.com/paper/2501.05441/) (2025)
- [HARP: Autoregressive Latent Video Prediction with High-Fidelity Image Generator](https://mlsanity.com/paper/2209.07143/) (2022)
- [Beyond Data Scarcity Optimizing R3GAN for Medical Image Generation from Small Datasets](https://mlsanity.com/paper/2510.26828/) (2025)

## Abstract (arXiv)

Video generation for biological behavior requires more than visually plausible motion: the duration of an action is itself a semantic property. Existing models usually rely on fixed temporal windows, external continuation, or prompt-driven stories, so length is specified externally rather than learned from behavior. To address this gap, we propose BioVid, a data-driven autoregressive framework for adaptive-length biological behavior generation. BioVid uses a 2D-encode/3D-decode tokenizer: a two-dimensional FSQ-R3GAN encoder converts each frame into discrete visual tokens, preserving single-frame information suited for next-token prediction and EOS-based termination, while a temporally inflated and video-finetuned three-dimensional decoder reconstructs generated tokens with temporal context to reduce flickering. A causal Transformer then models the frame-wise token sequence and, conditioned only on the first frame, stops generation when it emits an End-of-Sequence token, allowing duration to emerge from the learned behavior distribution. We evaluate BioVid on the A001 drinking action from NTU RGB+D. On 94 held-out clips, BioVid achieves a Wasserstein-1 distance of 1.24 frames from the real duration distribution. In comparison, fixed-length baselines yield distances of approximately 6-7 frames even when configured to the available length closest to the dataset mean, and approximately 15 frames when using the conventional 16-frame generation length. These results demonstrate the ability of BioVid to learn and reproduce the intrinsic duration distribution of biological behavior.