Curriculum Group Policy Optimization: Adaptive Sampling for Unleashing the Potential of Text-to-Image Generation

• URL: http://arxiv.org/abs/2605.17807v1
• Date: Mon, 18 May 2026 03:30:14 GMT
• Title: Curriculum Group Policy Optimization: Adaptive Sampling for Unleashing the Potential of Text-to-Image Generation
• Abstract summary: We argue that improving training efficiency requires continuously prioritizing prompts that match the model's evolving capability.<n>We propose Curriculum Group Policy Optimization (CGPO), an adaptive curriculum training framework.<n> Experiments on GenEval, T2I-CompBench++, and DPG Bench demonstrate that our framework effectively improves generation performance.
• Score: 45.28944966622482
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Text-to-Image (T2I) generation has achieved remarkable progress in recent years. Meanwhile, reinforcement learning methods, particularly those based on Group Relative Policy Optimization (GRPO), have attracted widespread attention and been successfully applied to T2I tasks. However, the uniform sampling strategy commonly used during training often ignores the match between sample difficulty and the model's current learning capability, leading to low training efficiency. We argue that improving training efficiency requires continuously prioritizing prompts that match the model's evolving capability and remain actively learnable. To this end, we propose Curriculum Group Policy Optimization (CGPO), an adaptive curriculum training framework. During training, each prompt produces a group of images scored by a reward model. We use the variance of group rewards as an online proxy for prompt inconsistency. A higher variance suggests that the model has partially captured the prompt requirements but has not yet achieved stable mastery. Such prompts are more likely to provide useful learning signals, so we increase their sampling probabilities accordingly. Additionally, to address data imbalance in multi-category datasets, we design a category calibration method based on proportional fairness optimization, which balances training difficulty across categories. Experiments on GenEval, T2I-CompBench++, and DPG Bench demonstrate that our framework effectively improves generation performance.

Related papers

• Learning at the Right Pace: Adaptive Data Scheduling Improves LLM Reinforcement Learning [60.83841532299041]
  We propose Adaptive Data Scheduling (ADS), a dual-level data scheduling framework for pacing reinforcement learning post-training.<n>ADS organizes samples according to semantic patterns and maintains an adaptive inter-cluster distribution to solidify current training progress.<n> Experimental results across three LLMs and seven reasoning benchmarks demonstrate that ADS improves average accuracy by 5.2% over Group Relative Policy Optimization.
  arXiv  Detail & Related papers  (2026-06-21T02:19:17Z)
• TTA-Vid: Generalized Test-Time Adaptation for Video Reasoning [54.70019148172847]
  We leverage the paradigm of Test-Time Reinforcement Learning on video-language data to allow for adapting a pretrained model to incoming video samples at test-time without explicit labels.<n>The proposed test-time adaptation for video approach (TTA-Vid) combines two components that work simultaneously.<n>TTA-Vid yields consistent improvements across various video reasoning tasks and is able to outperform current state-of-the-art methods trained on large-scale data.
  arXiv  Detail & Related papers  (2026-04-01T09:52:57Z)
• Bagging-Based Model Merging for Robust General Text Embeddings [73.51674133699196]
  General-purpose text embedding models underpin a wide range of NLP and information retrieval applications.<n>We present a systematic study of multi-task training for text embeddings from two perspectives: data scheduling and model merging.<n>We propose Bagging-based rObust mOdel Merging (BOOM), which trains multiple embedding models on sampled subsets and merges them into a single model.
  arXiv  Detail & Related papers  (2026-02-05T15:45:08Z)
• Curriculum Direct Preference Optimization for Diffusion and Consistency Models [110.08057135882356]
  We propose a novel and enhanced version of DPO based on curriculum learning for text-to-image generation.<n>Our approach, Curriculum DPO, is compared against state-of-the-art fine-tuning approaches on nine benchmarks.
  arXiv  Detail & Related papers  (2024-05-22T13:36:48Z)
• Make Prompts Adaptable: Bayesian Modeling for Vision-Language Prompt Learning with Data-Dependent Prior [14.232144691524528]
  Recent Vision-Language Pretrained models have become the backbone for many downstream tasks. MLE training can lead the context vector to over-fit dominant image features in the training data. This paper presents a Bayesian-based framework of prompt learning, which could alleviate the overfitting issues on few-shot learning application.
  arXiv  Detail & Related papers  (2024-01-09T10:15:59Z)
• Improving Generalization of Alignment with Human Preferences through Group Invariant Learning [56.19242260613749]
  Reinforcement Learning from Human Feedback (RLHF) enables the generation of responses more aligned with human preferences. Previous work shows that Reinforcement Learning (RL) often exploits shortcuts to attain high rewards and overlooks challenging samples. We propose a novel approach that can learn a consistent policy via RL across various data groups or domains.
  arXiv  Detail & Related papers  (2023-10-18T13:54:15Z)
• Flipped Classroom: Effective Teaching for Time Series Forecasting [0.0]
  Sequence-to-sequence models based on LSTM and GRU are a most popular choice for forecasting time series data. The two most common training strategies within this context are teacher forcing (TF) and free running (FR) We propose several new curricula, and systematically evaluate their performance in two experimental sets.
  arXiv  Detail & Related papers  (2022-10-17T11:53:25Z)
• Adaptive Consistency Regularization for Semi-Supervised Transfer Learning [31.66745229673066]
  We consider semi-supervised learning and transfer learning jointly, leading to a more practical and competitive paradigm. To better exploit the value of both pre-trained weights and unlabeled target examples, we introduce adaptive consistency regularization. Our proposed adaptive consistency regularization outperforms state-of-the-art semi-supervised learning techniques such as Pseudo Label, Mean Teacher, and MixMatch.
  arXiv  Detail & Related papers  (2021-03-03T05:46:39Z)

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.