# Learning Adaptive and Temporally Causal Video Tokenization in a 1D Latent Space

arXiv: https://arxiv.org/abs/2505.17011 · HTML: https://mlsanity.com/paper/2505.17011/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 39 references that are in the map.
- First posted on arXiv 22 May 2025.

## Builds on (most cited first, 30 of 35)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers](https://mlsanity.com/paper/2205.15868/) (2022)
- [Cosmos World Foundation Model Platform for Physical AI](https://mlsanity.com/paper/2501.03575/) (2025)
- [Emu3: Next-Token Prediction is All You Need](https://mlsanity.com/paper/2409.18869/) (2024)
- [VideoGPT: Video Generation using VQ-VAE and Transformers](https://mlsanity.com/paper/2104.10157/) (2021)
- [Vector-quantized Image Modeling with Improved VQGAN](https://mlsanity.com/paper/2110.04627/) (2021)
- [Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation](https://mlsanity.com/paper/2310.05737/) (2023)
- [Phenaki: Variable Length Video Generation From Open Domain Textual Description](https://mlsanity.com/paper/2210.02399/) (2022)
- [Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation](https://mlsanity.com/paper/2410.13848/) (2024)
- [Finite Scalar Quantization: VQ-VAE Made Simple](https://mlsanity.com/paper/2309.15505/) (2023)
- [MAGVIT: Masked Generative Video Transformer](https://mlsanity.com/paper/2212.05199/) (2022)
- [A Short Note about Kinetics-600](https://mlsanity.com/paper/1808.01340/) (2018)
- [An Image is Worth 32 Tokens for Reconstruction and Generation](https://mlsanity.com/paper/2406.07550/) (2024)
- [N"UWA: Visual Synthesis Pre-training for Neural visUal World creAtion](https://mlsanity.com/paper/2111.12417/) (2021)
- [Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer](https://mlsanity.com/paper/2204.03638/) (2022)
- [OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation](https://mlsanity.com/paper/2406.09399/) (2024)
- [MaskViT: Masked Visual Pre-Training for Video Prediction](https://mlsanity.com/paper/2206.11894/) (2022)
- [FlexTok: Resampling Images into 1D Token Sequences of Flexible Length](https://mlsanity.com/paper/2502.13967/) (2025)
- [Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization](https://mlsanity.com/paper/2402.03161/) (2024)
- [Online Clustered Codebook](https://mlsanity.com/paper/2307.15139/) (2023)
- [One-D-Piece: Image Tokenizer Meets Quality-Controllable Compression](https://mlsanity.com/paper/2501.10064/) (2025)
- [Regularized Vector Quantization for Tokenized Image Synthesis](https://mlsanity.com/paper/2303.06424/) (2023)
- [ElasticTok: Adaptive Tokenization for Image and Video](https://mlsanity.com/paper/2410.08368/) (2024)

## Built on by (most cited first, 16 of 16)

- [A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens](https://mlsanity.com/paper/2604.04913/) (2026)
- [MotionStrata: Hierarchical Motion Latents for Compact Video Autoencoding](https://mlsanity.com/paper/2506.07136/) (2025)
- [EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation](https://mlsanity.com/paper/2603.12267/) (2026)
- [DeRA: Decoupled Representation Alignment for Video Tokenization](https://mlsanity.com/paper/2512.04483/) (2025)
- [One Model, Many Budgets: Elastic Latent Interfaces for Diffusion Transformers](https://mlsanity.com/paper/2603.12245/) (2026)
- [Adaptive 1D Video Diffusion Autoencoder](https://mlsanity.com/paper/2602.04220/) (2026)
- [TaskTok: Delving into Task Tokens for Task-driven Image Restoration](https://mlsanity.com/paper/2606.26615/) (2026)
- [Swift Sampling: Selecting Temporal Surprises via Taylor Series](https://mlsanity.com/paper/2605.22678/) (2026)
- [Soft Tail-dropping for Adaptive Visual Tokenization](https://mlsanity.com/paper/2601.14246/) (2026)
- [TivTok: Broadcasting Time-Invariant Tokens for Scalable Video Tokenization](https://mlsanity.com/paper/2606.17590/) (2026)
- [AVTok: 1D Unified Tokenization for Holistic Audio-Video Generation](https://mlsanity.com/paper/2606.30811/) (2026)
- [ZipTok3D: High-Fidelity 3D Tokenization with Compact Token Prefixes](https://mlsanity.com/paper/2609.01740/) (2026)
- [Adaptive Tokenisation Via Temporal Redundancy Masking And Latent Inpainting](https://mlsanity.com/paper/2606.06158/) (2026)
- [MOSAIK: Multi-Patch Content-Aware Spatial Allocation of Image Tokens for Efficient Generation](https://mlsanity.com/paper/2608.05450/) (2026)
- [Keep-or-Drop? Adaptive Tokenizer for Compact Video Representation](https://mlsanity.com/paper/2608.24293/) (2026)
- [V-ICAL Bench: Evaluating Video In-Context Learning for Multimodal Agents in Interactive Environments](https://mlsanity.com/paper/2609.15683/) (2026)

## Abstract (arXiv)

We propose AdapTok, an adaptive temporal causal video tokenizer that can flexibly allocate tokens for different frames based on video content. AdapTok is equipped with a block-wise masking strategy that randomly drops tail tokens of each block during training, and a block causal scorer to predict the reconstruction quality of video frames using different numbers of tokens. During inference, an adaptive token allocation strategy based on integer linear programming is further proposed to adjust token usage given predicted scores. Such design allows for sample-wise, content-aware, and temporally dynamic token allocation under a controllable overall budget. Extensive experiments for video reconstruction and generation on UCF-101 and Kinetics-600 demonstrate the effectiveness of our approach. Without additional image data, AdapTok consistently improves reconstruction quality and generation performance under different token budgets, allowing for more scalable and token-efficient generative video modeling.