# Composable Text Controls in Latent Space with ODEs

arXiv: https://arxiv.org/abs/2208.00638 · HTML: https://mlsanity.com/paper/2208.00638/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 68 references that are in the map.
- First posted on arXiv 1 Aug 2022.

## Builds on (most cited first, 30 of 44)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Diffusion-LM Improves Controllable Text Generation](https://mlsanity.com/paper/2205.14217/) (2022)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://mlsanity.com/paper/1909.05858/) (2019)
- [Score-based Generative Modeling in Latent Space](https://mlsanity.com/paper/2106.05931/) (2021)
- [Generating Sentences from a Continuous Space](https://mlsanity.com/paper/1511.06349/) (2015)
- [Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering](https://mlsanity.com/paper/1602.01585/) (2016)
- [MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers](https://mlsanity.com/paper/2102.01454/) (2021)
- [Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One](https://mlsanity.com/paper/1912.03263/) (2019)
- [GeDi: Generative Discriminator Guided Sequence Generation](https://mlsanity.com/paper/2009.06367/) (2020)
- [FUDGE: Controlled Text Generation With Future Discriminators](https://mlsanity.com/paper/2104.05218/) (2021)
- [Toward Controlled Generation of Text](https://mlsanity.com/paper/1703.00955/) (2017)
- [Style Transfer from Non-Parallel Text by Cross-Alignment](https://mlsanity.com/paper/1705.09655/) (2017)
- [Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfer](https://mlsanity.com/paper/1803.06535/) (2018)
- [Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer](https://mlsanity.com/paper/1804.06437/) (2018)
- [COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics](https://mlsanity.com/paper/2202.11705/) (2022)
- [Well-Read Students Learn Better: On the Importance of Pre-training Compact Models](https://mlsanity.com/paper/1908.08962/) (2019)
- [A Distributional Approach to Controlled Text Generation](https://mlsanity.com/paper/2012.11635/) (2020)
- [Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space](https://mlsanity.com/paper/2004.04092/) (2020)
- [Residual Energy-Based Models for Text Generation](https://mlsanity.com/paper/2004.11714/) (2020)
- [Interacting particle solutions of Fokker-Planck equations through gradient-log-density estimation](https://mlsanity.com/paper/2006.00702/) (2020)
- [Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representation](https://mlsanity.com/paper/1905.05621/) (2019)
- [Transforming Delete, Retrieve, Generate Approach for Controlled Text Style Transfer](https://mlsanity.com/paper/1908.09368/) (2019)
- [Politeness Transfer: A Tag and Generate Approach](https://mlsanity.com/paper/2004.14257/) (2020)
- [Controlled Text Generation as Continuous Optimization with Multiple Constraints](https://mlsanity.com/paper/2108.01850/) (2021)
- [Sampling Can Be Faster Than Optimization](https://mlsanity.com/paper/1811.08413/) (2018)

## Built on by (most cited first, 28 of 28)

- [COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability](https://mlsanity.com/paper/2402.08679/) (2024)
- [GameGen-X: Interactive Open-world Game Video Generation](https://mlsanity.com/paper/2411.00769/) (2024)
- [A Survey on Diffusion Language Models](https://mlsanity.com/paper/2508.10875/) (2025)
- [DINOISER: Diffused Conditional Sequence Learning by Manipulating Noises](https://mlsanity.com/paper/2302.10025/) (2023)
- [Controllable Text Generation via Probability Density Estimation in the Latent Space](https://mlsanity.com/paper/2212.08307/) (2022)
- [MacLaSa: Multi-Aspect Controllable Text Generation via Efficient Sampling from Compact Latent Space](https://mlsanity.com/paper/2305.12785/) (2023)
- [Unified Generation, Reconstruction, and Representation: Generalized Diffusion with Adaptive Latent Encoding-Decoding](https://mlsanity.com/paper/2402.19009/) (2024)
- [Preference Diffusion for Recommendation](https://mlsanity.com/paper/2410.13117/) (2024)
- [Learning Disentangled Semantic Spaces of Explanations via Invertible Neural Networks](https://mlsanity.com/paper/2305.01713/) (2023)
- [DiffusionDialog: A Diffusion Model for Diverse Dialog Generation with Latent Space](https://mlsanity.com/paper/2404.06760/) (2024)
- [Quasi-symbolic Semantic Geometry over Transformer-based Variational AutoEncoder](https://mlsanity.com/paper/2210.06230/) (2022)
- [ZeroGen: Zero-shot Multimodal Controllable Text Generation with Multiple Oracles](https://mlsanity.com/paper/2306.16649/) (2023)
- [MORPHEUS: Modeling Role from Personalized Dialogue History by Exploring and Utilizing Latent Space](https://mlsanity.com/paper/2407.02345/) (2024)
- [Revealing the Attention Floating Mechanism in Masked Diffusion Models](https://mlsanity.com/paper/2601.07894/) (2026)
- [Text Diffusion with Reinforced Conditioning](https://mlsanity.com/paper/2402.14843/) (2024)
- [Multi-Aspect Controllable Text Generation with Disentangled Counterfactual Augmentation](https://mlsanity.com/paper/2405.19958/) (2024)
- [LangVAE and LangSpace: Building and Probing for Language Model VAEs](https://mlsanity.com/paper/2505.00004/) (2025)
- [C3TG: Conflict-aware, Composite, and Collaborative Controlled Text Generation](https://mlsanity.com/paper/2511.09292/) (2025)
- [UniModel: A Visual-Only Framework for Unified Multimodal Understanding and Generation](https://mlsanity.com/paper/2511.16917/) (2025)
- [GlyphDiffusion: Text Generation as Image Generation](https://mlsanity.com/paper/2304.12519/) (2023)
- [Linguistically-Controlled Paraphrase Generation](https://mlsanity.com/paper/2410.24199/) (2024)
- [Dior-CVAE: Pre-trained Language Models and Diffusion Priors for Variational Dialog Generation](https://mlsanity.com/paper/2305.15025/) (2023)
- [LingGen: Scalable Multi-Attribute Linguistic Control via Power-Law Masking](https://mlsanity.com/paper/2410.24201/) (2024)
- [Multi-Attribute Constraint Satisfaction via Language Model Rewriting](https://mlsanity.com/paper/2412.19198/) (2024)
- [JTreeformer: Graph-Transformer via Latent-Diffusion Model for Molecular Generation](https://mlsanity.com/paper/2504.20770/) (2025)
- [Bridging Compositional and Distributional Semantics: A Survey on Latent Semantic Geometry via AutoEncoder](https://mlsanity.com/paper/2506.20083/) (2025)
- [OLLM: Options-based Large Language Models](https://mlsanity.com/paper/2604.19087/) (2026)
- [The Illusion of Control: Why Bare Classifier Inversion Silently Fails in Concept-Bottleneck Text Generation](https://mlsanity.com/paper/2608.22956/) (2026)

## Abstract (arXiv)

Real-world text applications often involve composing a wide range of text control operations, such as editing the text w.r.t. an attribute, manipulating keywords and structure, and generating new text of desired properties. Prior work typically learns/finetunes a language model (LM) to perform individual or specific subsets of operations. Recent research has studied combining operations in a plug-and-play manner, often with costly search or optimization in the complex sequence space. This paper proposes a new efficient approach for composable text operations in the compact latent space of text. The low-dimensionality and differentiability of the text latent vector allow us to develop an efficient sampler based on ordinary differential equations (ODEs) given arbitrary plug-in operators (e.g., attribute classifiers). By connecting pretrained LMs (e.g., GPT2) to the latent space through efficient adaption, we then decode the sampled vectors into desired text sequences. The flexible approach permits diverse control operators (sentiment, tense, formality, keywords, etc.) acquired using any relevant data from different domains. Experiments show that composing those operators within our approach manages to generate or edit high-quality text, substantially improving over previous methods in terms of generation quality and efficiency.