# SweetTok: Semantic-Aware Spatial-Temporal Tokenizer for Compact Video Discretization

arXiv: https://arxiv.org/abs/2412.10443 · HTML: https://mlsanity.com/paper/2412.10443/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 56 references that are in the map.
- First posted on arXiv 11 Dec 2024.

## Builds on (most cited first, 30 of 45)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [MaskGIT: Masked Generative Image Transformer](https://mlsanity.com/paper/2202.04200/) (2022)
- [CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers](https://mlsanity.com/paper/2205.15868/) (2022)
- [Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation](https://mlsanity.com/paper/2406.06525/) (2024)
- [Autoregressive Image Generation using Residual Quantization](https://mlsanity.com/paper/2203.01941/) (2022)
- [Multimodal Few-Shot Learning with Frozen Language Models](https://mlsanity.com/paper/2106.13884/) (2021)
- [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)
- [MAGVIT: Masked Generative Video Transformer](https://mlsanity.com/paper/2212.05199/) (2022)

## Built on by (most cited first, 12 of 12)

- [Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey](https://mlsanity.com/paper/2507.22920/) (2025)
- [DINO-Tok: Adapting DINO for Visual Tokenizers](https://mlsanity.com/paper/2511.20565/) (2025)
- [DeRA: Decoupled Representation Alignment for Video Tokenization](https://mlsanity.com/paper/2512.04483/) (2025)
- [PyraTok: Language-Aligned Pyramidal Tokenizer for Video Understanding and Generation](https://mlsanity.com/paper/2601.16210/) (2026)
- [TaskTok: Delving into Task Tokens for Task-driven Image Restoration](https://mlsanity.com/paper/2606.26615/) (2026)
- [VideoRAE: Taming Video Foundation Models for Generative Modeling via Representation Autoencoders](https://mlsanity.com/paper/2607.14088/) (2026)
- [V-RAE: Rethinking Video Latent Spaces for Generation](https://mlsanity.com/paper/2608.13556/) (2026)
- [Versatile Video Representation via Feed-Forward 2D Gaussian Splatting Tokenization](https://mlsanity.com/paper/2508.11183/) (2025)
- [Best of Both Worlds: Multimodal Reasoning and Generation via Unified Discrete Flow Matching](https://mlsanity.com/paper/2602.12221/) (2026)
- [PhyEdit: Towards Real-World Object Manipulation via Physically-Grounded Image Editing](https://mlsanity.com/paper/2604.07230/) (2026)
- [TivTok: Broadcasting Time-Invariant Tokens for Scalable Video Tokenization](https://mlsanity.com/paper/2606.17590/) (2026)
- [Keep-or-Drop? Adaptive Tokenizer for Compact Video Representation](https://mlsanity.com/paper/2608.24293/) (2026)

## Abstract (arXiv)

This paper presents the Semantic-aWarE spatial-tEmporal Tokenizer (SweetTok), a novel video tokenizer to overcome the limitations in current video tokenization methods for compacted yet effective discretization. Unlike previous approaches that process flattened local visual patches via direct discretization or adaptive query tokenization, SweetTok proposes a decoupling framework, compressing visual inputs through distinct spatial and temporal queries via Decoupled Query AutoEncoder (DQAE). This design allows SweetTok to efficiently compress video token count while achieving superior fidelity by capturing essential information across spatial and temporal dimensions. Furthermore, we design a Motion-enhanced Language Codebook (MLC) tailored for spatial and temporal compression to address the differences in semantic representation between appearance and motion information. SweetTok significantly improves video reconstruction results by 42.8% w.r.t rFVD on UCF-101 dataset. With a better token compression strategy, it also boosts downstream video generation results by 15.1% w.r.t gFVD. Additionally, the compressed decoupled tokens are imbued with semantic information, enabling few-shot recognition capabilities powered by LLMs in downstream applications.