Xue Xu

Wei Li, Xue Xu, Xinyan Xiao et al. · baidu

Diffusion generative models have recently greatly improved the power of text-conditioned image generation. Existing image generation models mainly include text conditional diffusion model and cross-modal guided diffusion model, which are good at small scene image generation and complex scene image generation respectively. In this work, we propose a simple yet effective approach, namely UPainting, to unify simple and complex scene image generation, as shown in Figure 1. Based on architecture improvements and diverse guidance schedules, UPainting effectively integrates cross-modal guidance from a pretrained image-text matching model into a text conditional diffusion model that utilizes a pretrained Transformer language model as the text encoder. Our key findings is that combining the power of large-scale Transformer language model in understanding language and image-text matching model in capturing cross-modal semantics and style, is effective to improve sample fidelity and image-text alignment of image generation. In this way, UPainting has a more general image generation capability, which can generate images of both simple and complex scenes more effectively. To comprehensively compare text-to-image models, we further create a more general benchmark, UniBench, with well-written Chinese and English prompts in both simple and complex scenes. We compare UPainting with recent models and find that UPainting greatly outperforms other models in terms of caption similarity and image fidelity in both simple and complex scenes. UPainting project page \url{https://upainting.github.io/}.

Haifeng Wang, Hua Wu, Tian Wu et al.

In this report, we introduce ERNIE 5.0, a natively autoregressive foundation model desinged for unified multimodal understanding and generation across text, image, video, and audio. All modalities are trained from scratch under a unified next-group-of-tokens prediction objective, based on an ultra-sparse mixture-of-experts (MoE) architecture with modality-agnostic expert routing. To address practical challenges in large-scale deployment under diverse resource constraints, ERNIE 5.0 adopts a novel elastic training paradigm. Within a single pre-training run, the model learns a family of sub-models with varying depths, expert capacities, and routing sparsity, enabling flexible trade-offs among performance, model size, and inference latency in memory- or time-constrained scenarios. Moreover, we systematically address the challenges of scaling reinforcement learning to unified foundation models, thereby guaranteeing efficient and stable post-training under ultra-sparse MoE architectures and diverse multimodal settings. Extensive experiments demonstrate that ERNIE 5.0 achieves strong and balanced performance across multiple modalities. To the best of our knowledge, among publicly disclosed models, ERNIE 5.0 represents the first production-scale realization of a trillion-parameter unified autoregressive model that supports both multimodal understanding and generation. To facilitate further research, we present detailed visualizations of modality-agnostic expert routing in the unified model, alongside comprehensive empirical analysis of elastic training, aiming to offer profound insights to the community.

Fuqiang Zhao, Jionghua Yu, Enjun Xing et al.

It is an extremely challenging task to detect arbitrary shape text in natural scenes on high accuracy and efficiency. In this paper, we propose a scene text detection framework, namely GWNet, which mainly includes two modules: Global module and RCNN module. Specifically, Global module improves the adaptive performance of the DB (Differentiable Binarization) module by adding k submodule and shift submodule. Two submodules enhance the adaptability of amplifying factor k, accelerate the convergence of models and help to produce more accurate detection results. RCNN module fuses global-level and word-level features. The word-level label is generated by obtaining the minimum axis-aligned rectangle boxes of the shrunk polygon. In the inference period, GWNet only uses global-level features to output simple polygon detections. Experiments on four benchmark datasets, including the MSRA-TD500, Total-Text, ICDAR2015 and CTW-1500, demonstrate that our GWNet outperforms the state-of-the-art detectors. Specifically, with a backbone of ResNet-50, we achieve an F-measure of 88.6% on MSRA- TD500, 87.9% on Total-Text, 89.2% on ICDAR2015 and 87.5% on CTW-1500.

Zhiyuan Yan, Kaiqing Lin, Zongjian Li et al.

The pursuit of unified multimodal models (UMMs) has long been hindered by a fundamental schism between multimodal understanding and generation. Current approaches typically disentangle the two and treat them as separate endeavors with disjoint objectives, missing the mutual benefits. We argue that true unification requires more than just merging two tasks. It requires a unified, foundational objective that intrinsically links them. In this paper, we introduce an insightful paradigm through the Auto-Encoder lens, i.e., regarding understanding as the encoder (I2T) that compresses images into text, and generation as the decoder (T2I) that reconstructs images from that text. To implement this, we propose UAE, where we begin by pre-training the decoder with the proposed 700k long-context image-caption pairs to direct it to "understand" the fine-grained and complex semantics from the text. We then propose Unified-GRPO via reinforcement learning (RL) to unify the two, which covers two complementary stages: (1) Generation for Understanding, where the encoder is trained to generate informative captions that maximize the decoder's reconstruction quality, enhancing its visual perception; (2) Understanding for Generation, where the decoder is refined to reconstruct from these captions, forcing it to leverage every detail and improving its long-context instruction following and generation fidelity. Our empirical results suggest that understanding can largely enhance generation (verified on GenEval), while generation, in turn, notably strengthens fine-grained visual perception like small object and color recognition (verified on MMT-Bench). This bidirectional improvement reveals a deep synergy: under the unified reconstruction objective, generation and understanding can mutually benefit each other, moving closer to truly unified multimodal intelligence.

Wei Li, Xue Xu, Jiachen Liu et al.

Existing text-to-image diffusion models primarily generate images from text prompts. However, the inherent conciseness of textual descriptions poses challenges in faithfully synthesizing images with intricate details, such as specific entities or scenes. This paper presents UNIMO-G, a simple multimodal conditional diffusion framework that operates on multimodal prompts with interleaved textual and visual inputs, which demonstrates a unified ability for both text-driven and subject-driven image generation. UNIMO-G comprises two core components: a Multimodal Large Language Model (MLLM) for encoding multimodal prompts, and a conditional denoising diffusion network for generating images based on the encoded multimodal input. We leverage a two-stage training strategy to effectively train the framework: firstly pre-training on large-scale text-image pairs to develop conditional image generation capabilities, and then instruction tuning with multimodal prompts to achieve unified image generation proficiency. A well-designed data processing pipeline involving language grounding and image segmentation is employed to construct multi-modal prompts. UNIMO-G excels in both text-to-image generation and zero-shot subject-driven synthesis, and is notably effective in generating high-fidelity images from complex multimodal prompts involving multiple image entities.