Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation

• URL: http://arxiv.org/abs/2604.18168v1
• Date: Mon, 20 Apr 2026 12:28:58 GMT
• Title: Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation
• Abstract summary: We develop a text-conditioned MeanFlow generation process for the first time.<n>We find that integrating powerful text encoders using conventional training strategies results in unsatisfactory performance.<n>We hope this work provides a general and practical reference for future research on text-conditioned MeanFlow generation.
• Score: 37.78791777901399
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Few-step generation has been a long-standing goal, with recent one-step generation methods exemplified by MeanFlow achieving remarkable results. Existing research on MeanFlow primarily focuses on class-to-image generation. However, an intuitive yet unexplored direction is to extend the condition from fixed class labels to flexible text inputs, enabling richer content creation. Compared to the limited class labels, text conditions pose greater challenges to the model's understanding capability, necessitating the effective integration of powerful text encoders into the MeanFlow framework. Surprisingly, although incorporating text conditions appears straightforward, we find that integrating powerful LLM-based text encoders using conventional training strategies results in unsatisfactory performance. To uncover the underlying cause, we conduct detailed analyses and reveal that, due to the extremely limited number of refinement steps in the MeanFlow generation, such as only one step, the text feature representations are required to possess sufficiently high discriminability. This also explains why discrete and easily distinguishable class features perform well within the MeanFlow framework. Guided by these insights, we leverage a powerful LLM-based text encoder validated to possess the required semantic properties and adapt the MeanFlow generation process to this framework, resulting in efficient text-conditioned synthesis for the first time. Furthermore, we validate our approach on the widely used diffusion model, demonstrating significant generation performance improvements. We hope this work provides a general and practical reference for future research on text-conditioned MeanFlow generation. The code is available at https://github.com/AMAP-ML/EMF.

Related papers

• Flow of Spans: Generalizing Language Models to Dynamic Span-Vocabulary via GFlowNets [54.06320619464273]
  Flow of SpanS (FOSS) is a principled GFlowNets framework for span generation.<n>FOSS constructs a dynamic span vocabulary by segmenting the retrieved text flexibly.<n>With specialized reward models, FoSS generates diverse, high-quality text.
  arXiv  Detail & Related papers  (2026-02-11T07:17:41Z)
• OneFlow: Concurrent Mixed-Modal and Interleaved Generation with Edit Flows [59.052955667723985]
  We present OneFlow, the first non-autoregressive multimodal model that enables variable-length and concurrent mixed-modal generation.<n>Unlike autoregressive models that enforce rigid causal ordering between text and image generation, OneFlow combines an insertion-based Edit Flow for discrete text tokens with Flow Matching for image latents.
  arXiv  Detail & Related papers  (2025-10-03T20:40:30Z)
• Resource-Efficient Adaptation of Large Language Models for Text Embeddings via Prompt Engineering and Contrastive Fine-tuning [3.9914181590063884]
  Large Language Models (LLMs) have become a cornerstone in Natural Language Processing (NLP)<n>We explore several adaptation strategies for pre-trained, decoder-only LLMs.
  arXiv  Detail & Related papers  (2025-07-30T14:49:30Z)
• ESTR-CoT: Towards Explainable and Accurate Event Stream based Scene Text Recognition with Chain-of-Thought Reasoning [57.767536707234036]
  We propose a novel chain-of-thought reasoning based event stream scene text recognition framework, termed ESTR-CoT.<n>Specifically, we first adopt the vision encoder EVA-CLIP to transform the input event stream into tokens and utilize a Llama tokenizer to encode the given generation prompt.<n>A Q-former is used to align the vision token to the pre-trained large language model Vicuna-7B and output both the answer and chain-of-thought (CoT) reasoning process simultaneously.
  arXiv  Detail & Related papers  (2025-07-02T23:41:31Z)
• Beyond End-to-End VLMs: Leveraging Intermediate Text Representations for Superior Flowchart Understanding [9.267156820352996]
  Flowcharts are typically presented as images, driving the trend of using vision-language models (VLMs) for end-to-end flowchart understanding.<n>Two key challenges arise: (i) Limited controllability--users have minimal influence over the downstream task, while the training of VLMs is often out of reach.<n>We propose TextFlow, addressing aforementioned issues with two stages: Vision Textualizer and Textual Reasoner.
  arXiv  Detail & Related papers  (2024-12-21T00:52:41Z)
• STAGE: Simplified Text-Attributed Graph Embeddings Using Pre-trained LLMs [1.4624458429745086]
  We present a method for enhancing node features in Graph Neural Network (GNN) models that encode Text-Attributed Graphs (TAGs) Our approach leverages Large-Language Models (LLMs) to generate embeddings for textual attributes. We show that utilizing pre-trained LLMs as embedding generators provides robust features for ensemble GNN training.
  arXiv  Detail & Related papers  (2024-07-10T08:50:25Z)
• LRANet: Towards Accurate and Efficient Scene Text Detection with Low-Rank Approximation Network [63.554061288184165]
  We propose a novel parameterized text shape method based on low-rank approximation. By exploring the shape correlation among different text contours, our method achieves consistency, compactness, simplicity, and robustness in shape representation. We implement an accurate and efficient arbitrary-shaped text detector named LRANet.
  arXiv  Detail & Related papers  (2023-06-27T02:03:46Z)
• POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-training [93.79766670391618]
  We present POINTER, a novel insertion-based approach for hard-constrained text generation. The proposed method operates by progressively inserting new tokens between existing tokens in a parallel manner. The resulting coarse-to-fine hierarchy makes the generation process intuitive and interpretable.
  arXiv  Detail & Related papers  (2020-05-01T18:11:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.