Dawei Leng

Chunyu Xie, Heng Cai, Jincheng Li et al.

Vision-language pre-training (VLP) on large-scale datasets has shown premier performance on various downstream tasks. In contrast to plenty of available benchmarks with English corpus, large-scale pre-training datasets and downstream datasets with Chinese corpus remain largely unexplored. In this work, we build a large-scale high-quality Chinese Cross-Modal Benchmark named CCMB for the research community, which contains the currently largest public pre-training dataset Zero and five human-annotated fine-tuning datasets for downstream tasks. Zero contains 250 million images paired with 750 million text descriptions, plus two of the five fine-tuning datasets are also currently the largest ones for Chinese cross-modal downstream tasks. Along with the CCMB, we also develop a VLP framework named R2D2, applying a pre-Ranking + Ranking strategy to learn powerful vision-language representations and a two-way distillation method (i.e., target-guided Distillation and feature-guided Distillation) to further enhance the learning capability. With the Zero and the R2D2 VLP framework, we achieve state-of-the-art performance on twelve downstream datasets from five broad categories of tasks including image-text retrieval, image-text matching, image caption, text-to-image generation, and zero-shot image classification. The datasets, models, and codes are available at https://github.com/yuxie11/R2D2

Bin Wang, Chunyu Xie, Dawei Leng et al.

In the field of multimodal large language models (MLLMs), common methods typically involve unfreezing the language model during training to foster profound visual understanding. However, the fine-tuning of such models with vision-language data often leads to a diminution of their natural language processing (NLP) capabilities. To avoid this performance degradation, a straightforward solution is to freeze the language model while developing multimodal competencies. Unfortunately, previous works have not attained satisfactory outcomes. Building on the strategy of freezing the language model, we conduct thorough structural exploration and introduce the Inner-Adaptor Architecture (IAA). Specifically, the architecture incorporates multiple multimodal adaptors at varying depths within the large language model to facilitate direct interaction with the inherently text-oriented transformer layers, thereby enabling the frozen language model to acquire multimodal capabilities. Unlike previous approaches of freezing language models that require large-scale aligned data, our proposed architecture is able to achieve superior performance on small-scale datasets. We conduct extensive experiments to improve the general multimodal capabilities and visual grounding abilities of the MLLM. Our approach remarkably outperforms previous state-of-the-art methods across various vision-language benchmarks without sacrificing performance on NLP tasks. Code and models are available at https://github.com/360CVGroup/Inner-Adaptor-Architecture.

Weijian Jian, Yajun Zhang, Dawei Liang et al.

The rapid advancement of Multimodal Large Language Models (MLLMs) has extended CLIP-based frameworks to produce powerful, universal embeddings for retrieval tasks. However, existing methods primarily focus on natural images, offering limited support for other crucial visual modalities such as videos and visual documents. To bridge this gap, we introduce RzenEmbed, a unified framework to learn embeddings across a diverse set of modalities, including text, images, videos, and visual documents. We employ a novel two-stage training strategy to learn discriminative representations. The first stage focuses on foundational text and multimodal retrieval. In the second stage, we introduce an improved InfoNCE loss, incorporating two key enhancements. Firstly, a hardness-weighted mechanism guides the model to prioritize challenging samples by assigning them higher weights within each batch. Secondly, we implement an approach to mitigate the impact of false negatives and alleviate data noise. This strategy not only enhances the model's discriminative power but also improves its instruction-following capabilities. We further boost performance with learnable temperature parameter and model souping. RzenEmbed sets a new state-of-the-art on the MMEB benchmark. It not only achieves the best overall score but also outperforms all prior work on the challenging video and visual document retrieval tasks. Our models are available in https://huggingface.co/qihoo360/RzenEmbed.

Yue Gong, Hongyu Li, Shanyuan Liu et al.

Diffusion models have become the dominant paradigm for image generation and editing, with latent diffusion models shifting denoising to a compact latent space for efficiency and scalability. Recent attempts to leverage pretrained visual representation models as tokenizer priors either align diffusion features to representation features or directly reuse representation encoders as frozen tokenizers. Although such approaches can improve generation metrics, they often suffer from limited reconstruction fidelity due to frozen encoders, which in turn degrades editing quality, as well as overly high-dimensional latents that make diffusion modeling difficult. To address these limitations, We propose Representation-Pivoted AutoEncoder, a representation-based tokenizer that improves both generation and editing. We introduce Representation-Pivot Regularization, a training strategy that enables a representation-initialized encoder to be fine-tuned for reconstruction while preserving the semantic structure of the pretrained representation space, followed by a variational bridge which compress latent space into a compact one for better diffusion modeling. We adopt an objective-decoupled stage-wise training strategy that sequentially optimizes generative tractability and reconstruction-fidelity objectives. Together, these components yield a tokenizer that preserves strong semantics, reconstructs faithfully, and produces latents with reduced diffusion modeling complexity. Experiments demonstrate that RPiAE outperforms other visual tokenizers on text-to-image generation and image editing, while delivering the best reconstruction fidelity among representation-based tokenizers.

Jing Wang, Ao Ma, Jiasong Feng et al.

The global self-attention mechanism in diffusion transformers involves redundant computation due to the sparse and redundant nature of visual information, and the attention map of tokens within a spatial window shows significant similarity. To address this redundancy, we propose the Proxy-Tokenized Diffusion Transformer (PT-DiT), which employs sparse representative token attention (where the number of representative tokens is much smaller than the total number of tokens) to model global visual information efficiently. Specifically, within each transformer block, we compute an averaging token from each spatial-temporal window to serve as a proxy token for that region. The global semantics are captured through the self-attention of these proxy tokens and then injected into all latent tokens via cross-attention. Simultaneously, we introduce window and shift window attention to address the limitations in detail modeling caused by the sparse attention mechanism. Building on the well-designed PT-DiT, we further develop the Qihoo-T2X family, which includes a variety of models for T2I, T2V, and T2MV tasks. Experimental results show that PT-DiT achieves competitive performance while reducing the computational complexity in both image and video generation tasks (e.g., a 49% reduction compared to DiT and a 34% reduction compared to PixArt-$α$). The visual exhibition and source code of Qihoo-T2X is available at https://360cvgroup.github.io/Qihoo-T2X/.

Bo Cheng, Yuhang Ma, Liebucha Wu et al.

The task of layout-to-image generation involves synthesizing images based on the captions of objects and their spatial positions. Existing methods still struggle in complex layout generation, where common bad cases include object missing, inconsistent lighting, conflicting view angles, etc. To effectively address these issues, we propose a \textbf{Hi}erarchical \textbf{Co}ntrollable (HiCo) diffusion model for layout-to-image generation, featuring object seperable conditioning branch structure. Our key insight is to achieve spatial disentanglement through hierarchical modeling of layouts. We use a multi branch structure to represent hierarchy and aggregate them in fusion module. To evaluate the performance of multi-objective controllable layout generation in natural scenes, we introduce the HiCo-7K benchmark, derived from the GRIT-20M dataset and manually cleaned. https://github.com/360CVGroup/HiCo_T2I.

Chunyu Xie, Bin Wang, Fanjing Kong et al.

Contrastive Language-Image Pre-training (CLIP) excels in multimodal tasks such as image-text retrieval and zero-shot classification but struggles with fine-grained understanding due to its focus on coarse-grained short captions. To address this, we propose Fine-Grained CLIP (FG-CLIP), which enhances fine-grained understanding through three key innovations. First, we leverage large multimodal models to generate 1.6 billion long caption-image pairs for capturing global-level semantic details. Second, a high-quality dataset is constructed with 12 million images and 40 million region-specific bounding boxes aligned with detailed captions to ensure precise, context-rich representations. Third, 10 million hard fine-grained negative samples are incorporated to improve the model's ability to distinguish subtle semantic differences. We construct a comprehensive dataset, termed FineHARD, by integrating high-quality region-specific annotations with hard fine-grained negative samples. Corresponding training methods are meticulously designed for these data. Extensive experiments demonstrate that FG-CLIP outperforms the original CLIP and other state-of-the-art methods across various downstream tasks, including fine-grained understanding, open-vocabulary object detection, image-text retrieval, and general multimodal benchmarks. These results highlight FG-CLIP's effectiveness in capturing fine-grained image details and improving overall model performance. The data, code, and models are available at https://github.com/360CVGroup/FG-CLIP.

Runze He, Bo Cheng, Yuhang Ma et al.

In this paper, we propose a unified layout planning and image generation model, PlanGen, which can pre-plan spatial layout conditions before generating images. Unlike previous diffusion-based models that treat layout planning and layout-to-image as two separate models, PlanGen jointly models the two tasks into one autoregressive transformer using only next-token prediction. PlanGen integrates layout conditions into the model as context without requiring specialized encoding of local captions and bounding box coordinates, which provides significant advantages over the previous embed-and-pool operations on layout conditions, particularly when dealing with complex layouts. Unified prompting allows PlanGen to perform multitasking training related to layout, including layout planning, layout-to-image generation, image layout understanding, etc. In addition, PlanGen can be seamlessly expanded to layout-guided image manipulation thanks to the well-designed modeling, with teacher-forcing content manipulation policy and negative layout guidance. Extensive experiments verify the effectiveness of our PlanGen in multiple layoutrelated tasks, showing its great potential. Code is available at: https://360cvgroup.github.io/PlanGen.

Tongfei Chen, Shuo Yang, Yuguang Yang et al.

Referring Image Segmentation (RIS) aims to segment an object in an image identified by a natural language expression. The paper introduces Alignment-Aware Masked Learning (AML), a training strategy to enhance RIS by explicitly estimating pixel-level vision-language alignment, filtering out poorly aligned regions during optimization, and focusing on trustworthy cues. This approach results in state-of-the-art performance on RefCOCO datasets and also enhances robustness to diverse descriptions and scenarios

Rongji Li, Jian Xu, Xueqing Chen et al.

In domains such as biomedicine, materials, and finance, high-stakes deployment of large language models (LLMs) requires injecting private, domain-specific knowledge that is proprietary, fast-evolving, and under-represented in public pretraining. However, the two dominant paradigms for private knowledge injection each have pronounced drawbacks: fine-tuning is expensive to iterate, and continual updates risk catastrophic forgetting and general-capability regression; retrieval-augmented generation (RAG) keeps the base model intact but is brittle in specialized private corpora due to chunk-induced evidence fragmentation, retrieval drift, and long-context pressure that yields query-dependent prompt inflation. Inspired by how multimodal LLMs align heterogeneous modalities into a shared semantic space, we propose Generation-Augmented Generation (GAG), which treats private expertise as an additional expert modality and injects it via a compact, representation-level interface aligned to the frozen base model, avoiding prompt-time evidence serialization while enabling plug-and-play specialization and scalable multi-domain composition with reliable selective activation. Across two private scientific QA benchmarks (immunology adjuvant and catalytic materials) and mixed-domain evaluations, GAG improves specialist performance over strong RAG baselines by 15.34% and 14.86% on the two benchmarks, respectively, while maintaining performance on six open general benchmarks and enabling near-oracle selective activation for scalable multi-domain deployment.

Liuzhuozheng Li, Yue Gong, Shanyuan Liu et al.

We introduce RefTON, a flux-based person-to-person virtual try-on framework that enhances garment realism through unpaired visual references. Unlike conventional approaches that rely on complex auxiliary inputs such as body parsing and warped mask or require finely designed extract branches to process various input conditions, RefTON streamlines the process by directly generating try-on results from a source image and a target garment, without the need for structural guidance or auxiliary components to handle diverse inputs. Moreover, inspired by human clothing selection behavior, RefTON leverages additional reference images (the target garment worn on different individuals) to provide powerful guidance for refining texture alignment and maintaining the garment details. To enable this capability, we built a dataset containing unpaired reference images for training. Extensive experiments on public benchmarks demonstrate that RefTON achieves competitive or superior performance compared to state-of-the-art methods, while maintaining a simple and efficient person-to-person design.

Jincheng Li, Chunyu Xie, Ji Ao et al.

Large multimodal models (LMMs) have garnered wide-spread attention and interest within the artificial intelligence research and industrial communities, owing to their remarkable capability in multimodal understanding, reasoning, and in-context learning, among others. While LMMs have demonstrated promising results in tackling multimodal tasks like image captioning, visual question answering, and visual grounding, the object detection capabilities of LMMs exhibit a significant gap compared to specialist detectors. To bridge the gap, we depart from the conventional methods of integrating heavy detectors with LMMs and propose LMM-Det, a simple yet effective approach that leverages a Large Multimodal Model for vanilla object Detection without relying on specialized detection modules. Specifically, we conduct a comprehensive exploratory analysis when a large multimodal model meets with object detection, revealing that the recall rate degrades significantly compared with specialist detection models. To mitigate this, we propose to increase the recall rate by introducing data distribution adjustment and inference optimization tailored for object detection. We re-organize the instruction conversations to enhance the object detection capabilities of large multimodal models. We claim that a large multimodal model possesses detection capability without any extra detection modules. Extensive experiments support our claim and show the effectiveness of the versatile LMM-Det. The datasets, models, and codes are available at https://github.com/360CVGroup/LMM-Det.

Binhao Wang, Shihao Zhao, Bo Cheng et al.

Recent diffusion-based approaches have made substantial progress in image layer decomposition. However, accurately decomposing complex natural images remains challenging due to difficulties in occlusion completion, robust layer disentanglement, and precise foreground boundaries. Moreover, the scarcity of high-quality multi-layer natural image datasets limits advancement. To address these challenges, we propose RevealLayer, a diffusion-based framework that decomposes an RGB image into multiple RGBA layers, enabling precise layer separation and reliable recovery of occluded content in natural images. RevealLayer incorporates three key components: (1) a Region-Aware Attention module to disentangle hidden and visible layers; (2) an Occlusion-Guided Adapter to leverage contextual information to enhance overlapping regions; and (3) a composite loss to enforce sharp alpha boundaries and suppress residual artifacts. To support training and evaluation, we introduce RevealLayer-100K, a high-quality multi-layer natural image constructed through a collaboration between automated algorithms and human annotation, and further establish RevealLayerBench for benchmarking layer decomposition in general natural scenes. Extensive experiments demonstrate that RevealLayer consistently outperforms existing approaches in layer decomposition.

Jing Wang, Ao Ma, Ke Cao et al.

Recent rapid advancements in text-to-video (T2V) generation, such as SoRA and Kling, have shown great potential for building world simulators. However, current T2V models struggle to grasp abstract physical principles and generate videos that adhere to physical laws. This challenge arises primarily from a lack of clear guidance on physical information due to a significant gap between abstract physical principles and generation models. To this end, we introduce the World Simulator Assistant (WISA), an effective framework for decomposing and incorporating physical principles into T2V models. Specifically, WISA decomposes physical principles into textual physical descriptions, qualitative physical categories, and quantitative physical properties. To effectively embed these physical attributes into the generation process, WISA incorporates several key designs, including Mixture-of-Physical-Experts Attention (MoPA) and a Physical Classifier, enhancing the model's physics awareness. Furthermore, most existing datasets feature videos where physical phenomena are either weakly represented or entangled with multiple co-occurring processes, limiting their suitability as dedicated resources for learning explicit physical principles. We propose a novel video dataset, WISA-32K, collected based on qualitative physical categories. It consists of 32,000 videos, representing 17 physical laws across three domains of physics: dynamics, thermodynamics, and optics. Experimental results demonstrate that WISA can effectively enhance the compatibility of T2V models with real-world physical laws, achieving a considerable improvement on the VideoPhy benchmark. The visual exhibitions of WISA and WISA-32K are available in the https://360cvgroup.github.io/WISA/.

Ke Cao, Jing Wang, Ao Ma et al.

The Diffusion Transformer plays a pivotal role in advancing text-to-image and text-to-video generation, owing primarily to its inherent scalability. However, existing controlled diffusion transformer methods incur significant parameter and computational overheads and suffer from inefficient resource allocation due to their failure to account for the varying relevance of control information across different transformer layers. To address this, we propose the Relevance-Guided Efficient Controllable Generation framework, RelaCtrl, enabling efficient and resource-optimized integration of control signals into the Diffusion Transformer. First, we evaluate the relevance of each layer in the Diffusion Transformer to the control information by assessing the "ControlNet Relevance Score"-i.e., the impact of skipping each control layer on both the quality of generation and the control effectiveness during inference. Based on the strength of the relevance, we then tailor the positioning, parameter scale, and modeling capacity of the control layers to reduce unnecessary parameters and redundant computations. Additionally, to further improve efficiency, we replace the self-attention and FFN in the commonly used copy block with the carefully designed Two-Dimensional Shuffle Mixer (TDSM), enabling efficient implementation of both the token mixer and channel mixer. Both qualitative and quantitative experimental results demonstrate that our approach achieves superior performance with only 15% of the parameters and computational complexity compared to PixArt-delta.

Zhanjie Zhang, Ao Ma, Ke Cao et al.

Ultra-high quality artistic style transfer refers to repainting an ultra-high quality content image using the style information learned from the style image. Existing artistic style transfer methods can be categorized into style reconstruction-based and content-style disentanglement-based style transfer approaches. Although these methods can generate some artistic stylized images, they still exhibit obvious artifacts and disharmonious patterns, which hinder their ability to produce ultra-high quality artistic stylized images. To address these issues, we propose a novel artistic image style transfer method, U-StyDiT, which is built on transformer-based diffusion (DiT) and learns content-style disentanglement, generating ultra-high quality artistic stylized images. Specifically, we first design a Multi-view Style Modulator (MSM) to learn style information from a style image from local and global perspectives, conditioning U-StyDiT to generate stylized images with the learned style information. Then, we introduce a StyDiT Block to learn content and style conditions simultaneously from a style image. Additionally, we propose an ultra-high quality artistic image dataset, Aes4M, comprising 10 categories, each containing 400,000 style images. This dataset effectively solves the problem that the existing style transfer methods cannot produce high-quality artistic stylized images due to the size of the dataset and the quality of the images in the dataset. Finally, the extensive qualitative and quantitative experiments validate that our U-StyDiT can create higher quality stylized images compared to state-of-the-art artistic style transfer methods. To our knowledge, our proposed method is the first to address the generation of ultra-high quality stylized images using transformer-based diffusion.

Chunyu Xie, Bin Wang, Fanjing Kong et al.

Fine-grained vision-language understanding requires precise alignment between visual content and linguistic descriptions, a capability that remains limited in current models, particularly in non-English settings. While models like CLIP perform well on global alignment, they often struggle to capture fine-grained details in object attributes, spatial relations, and linguistic expressions, with limited support for bilingual comprehension. To address these challenges, we introduce FG-CLIP 2, a bilingual vision-language model designed to advance fine-grained alignment for both English and Chinese. Our approach leverages rich fine-grained supervision, including region-text matching and long-caption modeling, alongside multiple discriminative objectives. We further introduce the Textual Intra-modal Contrastive (TIC) loss to better distinguish semantically similar captions. Trained on a carefully curated mixture of large-scale English and Chinese data, FG-CLIP 2 achieves powerful bilingual performance. To enable rigorous evaluation, we present a new benchmark for Chinese multimodal understanding, featuring long-caption retrieval and bounding box classification. Extensive experiments on 29 datasets across 8 tasks show that FG-CLIP 2 outperforms existing methods, achieving state-of-the-art results in both languages. We release the model, code, and benchmark to facilitate future research on bilingual fine-grained alignment.

Yue Gong, Shanyuan Liu, Liuzhuozheng Li et al.

We proposed the Chinese Text Adapter-Flux (CTA-Flux). An adaptation method fits the Chinese text inputs to Flux, a powerful text-to-image (TTI) generative model initially trained on the English corpus. Despite the notable image generation ability conditioned on English text inputs, Flux performs poorly when processing non-English prompts, particularly due to linguistic and cultural biases inherent in predominantly English-centric training datasets. Existing approaches, such as translating non-English prompts into English or finetuning models for bilingual mappings, inadequately address culturally specific semantics, compromising image authenticity and quality. To address this issue, we introduce a novel method to bridge Chinese semantic understanding with compatibility in English-centric TTI model communities. Existing approaches relying on ControlNet-like architectures typically require a massive parameter scale and lack direct control over Chinese semantics. In comparison, CTA-flux leverages MultiModal Diffusion Transformer (MMDiT) to control the Flux backbone directly, significantly reducing the number of parameters while enhancing the model's understanding of Chinese semantics. This integration significantly improves the generation quality and cultural authenticity without extensive retraining of the entire model, thus maintaining compatibility with existing text-to-image plugins such as LoRA, IP-Adapter, and ControlNet. Empirical evaluations demonstrate that CTA-flux supports Chinese and English prompts and achieves superior image generation quality, visual realism, and faithful depiction of Chinese semantics.

Shanyuan Liu, Jian Zhu, Junda Lu et al.

Diffusion Transformers (DiTs) have demonstrated exceptional capabilities in text-to-image synthesis. However, in the domain of controllable text-to-image generation using DiTs, most existing methods still rely on the ControlNet paradigm originally designed for UNet-based diffusion models. This paradigm introduces significant parameter overhead and increased computational costs. To address these challenges, we propose the Nano Control Diffusion Transformer (NanoControl), which employs Flux as the backbone network. Our model achieves state-of-the-art controllable text-to-image generation performance while incurring only a 0.024\% increase in parameter count and a 0.029\% increase in GFLOPs, thus enabling highly efficient controllable generation. Specifically, rather than duplicating the DiT backbone for control, we design a LoRA-style (low-rank adaptation) control module that directly learns control signals from raw conditioning inputs. Furthermore, we introduce a KV-Context Augmentation mechanism that integrates condition-specific key-value information into the backbone in a simple yet highly effective manner, facilitating deep fusion of conditional features. Extensive benchmark experiments demonstrate that NanoControl significantly reduces computational overhead compared to conventional control approaches, while maintaining superior generation quality and achieving improved controllability.

Jian Zhu, Shanyuan Liu, Liuzhuozheng Li et al.

Makeup transfer aims to apply the makeup style from a reference face to a target face and has been increasingly adopted in practical applications. Existing GAN-based approaches typically rely on carefully designed loss functions to balance transfer quality and facial identity consistency, while diffusion-based methods often depend on additional face-control modules or algorithms to preserve identity. However, these auxiliary components tend to introduce extra errors, leading to suboptimal transfer results. To overcome these limitations, we propose FLUX-Makeup, a high-fidelity, identity-consistent, and robust makeup transfer framework that eliminates the need for any auxiliary face-control components. Instead, our method directly leverages source-reference image pairs to achieve superior transfer performance. Specifically, we build our framework upon FLUX-Kontext, using the source image as its native conditional input. Furthermore, we introduce RefLoRAInjector, a lightweight makeup feature injector that decouples the reference pathway from the backbone, enabling efficient and comprehensive extraction of makeup-related information. In parallel, we design a robust and scalable data generation pipeline to provide more accurate supervision during training. The paired makeup datasets produced by this pipeline significantly surpass the quality of all existing datasets. Extensive experiments demonstrate that FLUX-Makeup achieves state-of-the-art performance, exhibiting strong robustness across diverse scenarios.

Yuhang Ma, Bo Cheng, Shanyuan Liu et al.

Flow-based Transformer models have achieved state-of-the-art image generation performance, but often suffer from high inference latency and computational cost due to their large parameter sizes. To improve inference efficiency without compromising quality, we propose Bridged Progressive Rectified Flow Transformers (NAMI), which decompose the generation process across temporal, spatial, and architectural demensions. We divide the rectified flow into different stages according to resolution, and use a BridgeFlow module to connect them. Fewer Transformer layers are used at low-resolution stages to generate image layouts and concept contours, and more layers are progressively added as the resolution increases. Experiments demonstrate that our approach achieves fast convergence and reduces inference time while ensuring generation quality. The main contributions of this paper are summarized as follows: (1) We introduce Bridged Progressive Rectified Flow Transformers that enable multi-resolution training, accelerating model convergence; (2) NAMI leverages piecewise flow and spatial cascading of Diffusion Transformer (DiT) to rapidly generate images, reducing inference time by 64% for generating 1024 resolution images; (3) We propose a BridgeFlow module to align flows between different stages; (4) We propose the NAMI-1K benchmark to evaluate human preference performance, aiming to mitigate distributional bias and comprehensively assess model effectiveness. The results show that our model is competitive with state-of-the-art models.

Yuguang Yang, Tongfei Chen, Haoyu Huang et al.

Zero-shot medical detection can further improve detection performance without relying on annotated medical images even upon the fine-tuned model, showing great clinical value. Recent studies leverage grounded vision-language models (GLIP) to achieve this by using detailed disease descriptions as prompts for the target disease name during the inference phase. However, these methods typically treat prompts as equivalent context to the target name, making it difficult to assign specific disease knowledge based on visual information, leading to a coarse alignment between images and target descriptions. In this paper, we propose StructuralGLIP, which introduces an auxiliary branch to encode prompts into a latent knowledge bank layer-by-layer, enabling more context-aware and fine-grained alignment. Specifically, in each layer, we select highly similar features from both the image representation and the knowledge bank, forming structural representations that capture nuanced relationships between image patches and target descriptions. These features are then fused across modalities to further enhance detection performance. Extensive experiments demonstrate that StructuralGLIP achieves a +4.1\% AP improvement over prior state-of-the-art methods across seven zero-shot medical detection benchmarks, and consistently improves fine-tuned models by +3.2\% AP on endoscopy image datasets.

Shanyuan Liu, Dawei Leng, Yuhui Yin

Text-to-Image generation (TTI) technologies are advancing rapidly, especially in the English language communities. However, English-native TTI models inherently carry biases from English world centric training data, which creates a dilemma for development of other language-native TTI models. One common choice is fine-tuning the English-native TTI model with translated samples from non-English communities. It falls short of fully addressing the model bias problem. Alternatively, training non-English language native models from scratch can effectively resolve the English world bias, but diverges from the English TTI communities, thus not able to utilize the strides continuously gaining in the English TTI communities any more. To build non-English language native TTI model meanwhile keep compatability with the English TTI communities, we propose a novel model structure referred as "Bridge Diffusion Model" (BDM). The proposed BDM employs a backbone-branch network structure to learn the non-English language semantics while keep the latent space compatible with the English-native TTI backbone, in an end-to-end manner. The unique advantages of the proposed BDM are that it's not only adept at generating images that precisely depict non-English language semantics, but also compatible with various English-native TTI plugins, such as different checkpoints, LoRA, ControlNet, Dreambooth, and Textual Inversion, etc. Moreover, BDM can concurrently generate content seamlessly combining both non-English native and English-native semantics within a single image, fostering cultural interaction. We verify our method by applying BDM to build a Chinese-native TTI model, whereas the method is generic and applicable to any other language.

Jincheng Li, Chunyu Xie, Xiaoyu Wu et al.

Open-vocabulary detection (OVD) is a new object detection paradigm, aiming to localize and recognize unseen objects defined by an unbounded vocabulary. This is challenging since traditional detectors can only learn from pre-defined categories and thus fail to detect and localize objects out of pre-defined vocabulary. To handle the challenge, OVD leverages pre-trained cross-modal VLM, such as CLIP, ALIGN, etc. Previous works mainly focus on the open vocabulary classification part, with less attention on the localization part. We argue that for a good OVD detector, both classification and localization should be parallelly studied for the novel object categories. We show in this work that improving localization as well as cross-modal classification complement each other, and compose a good OVD detector jointly. We analyze three families of OVD methods with different design emphases. We first propose a vanilla method,i.e., cropping a bounding box obtained by a localizer and resizing it into the CLIP. We next introduce another approach, which combines a standard two-stage object detector with CLIP. A two-stage object detector includes a visual backbone, a region proposal network (RPN), and a region of interest (RoI) head. We decouple RPN and ROI head (DRR) and use RoIAlign to extract meaningful features. In this case, it avoids resizing objects. To further accelerate the training time and reduce the model parameters, we couple RPN and ROI head (CRR) as the third approach. We conduct extensive experiments on these three types of approaches in different settings. On the OVD-COCO benchmark, DRR obtains the best performance and achieves 35.8 Novel AP$_{50}$, an absolute 2.8 gain over the previous state-of-the-art (SOTA). For OVD-LVIS, DRR surpasses the previous SOTA by 1.9 AP$_{50}$ in rare categories. We also provide an object detection dataset called PID and provide a baseline on PID.

Yue Kang, Dawei Leng, Jinjiang Guo et al.

Antibody therapeutics has been extensively studied in drug discovery and development within the past decades. One increasingly popular focus in the antibody discovery pipeline is the optimization step for therapeutic leads. Both traditional methods and in silico approaches aim to generate candidates with high binding affinity against specific target antigens. Traditional in vitro approaches use hybridoma or phage display for candidate selection, and surface plasmon resonance (SPR) for evaluation, while in silico computational approaches aim to reduce the high cost and improve efficiency by incorporating mathematical algorithms and computational processing power in the design process. In the present study, we investigated different graph-based designs for depicting antibody-antigen interactions in terms of antibody affinity prediction using deep learning techniques. While other in silico computations require experimentally determined crystal structures, our study took interest in the capability of sequence-based models for in silico antibody maturation. Our preliminary studies achieved satisfying prediction accuracy on binding affinities comparing to conventional approaches and other deep learning approaches. To further study the antibody-antigen binding specificity, and to simulate the optimization process in real-world scenario, we introduced pairwise prediction strategy. We performed analysis based on both baseline and pairwise prediction results. The resulting prediction and efficiency prove the feasibility and computational efficiency of sequence-based method to be adapted as a scalable industry practice.

Yutong Jin, Jie Li, Xinyu Wang et al.

The novel coronavirus (SARS-CoV-2) which causes COVID-19 is an ongoing pandemic. There are ongoing studies with up to hundreds of publications uploaded to databases daily. We are exploring the use-case of artificial intelligence and natural language processing in order to efficiently sort through these publications. We demonstrate that clinical trial information, preclinical studies, and a general topic model can be used as text mining data intelligence tools for scientists all over the world to use as a resource for their own research. To evaluate our method, several metrics are used to measure the information extraction and clustering results. In addition, we demonstrate that our workflow not only have a use-case for COVID-19, but for other disease areas as well. Overall, our system aims to allow scientists to more efficiently research coronavirus. Our automatically updating modules are available on our information portal at https://ghddi-ailab.github.io/Targeting2019-nCoV/ for public viewing.

Dawei Leng, Jinjiang Guo, Lurong Pan et al.

Graph neural networks are emerging as continuation of deep learning success w.r.t. graph data. Tens of different graph neural network variants have been proposed, most following a neighborhood aggregation scheme, where the node features are updated via aggregating features of its neighboring nodes from layer to layer. Though related research surges, the power of GNNs are still not on-par-with their counterpart CNNs in computer vision and RNNs in natural language processing. We rethink this problem from the perspective of information propagation, and propose to enhance information propagation among GNN layers by combining heterogeneous aggregations. We argue that as richer information are propagated from shallow to deep layers, the discriminative capability of features formulated by GNN can benefit from it. As our first attempt in this direction, a new generic GNN layer formulation and upon this a new GNN variant referred as HAG-Net is proposed. We empirically validate the effectiveness of HAG-Net on a number of graph classification benchmarks, and elaborate all the design options and criterions along with.

Junfeng Wu, Dawei Leng, Lurong Pan

Structure-based virtual screening (SBVS) is a promising in silico technique that integrates computational methods into drug design. An extensively used method in SBVS is molecular docking. However, the docking process can hardly be computationally efficient and accurate simultaneously because classic mechanics scoring function is used to approximate, but hardly reach, the quantum mechanics precision in this method. In order to reduce the computational cost of the protein-ligand scoring process and use data driven approach to boost the scoring function accuracy, we introduce a docking-based SBVS method and, furthermore, a deep learning non-docking-based method that is able to avoid the computational cost of the docking process. Then, we try to integrate these two methods into an easy-to-use framework, ParaVS, that provides both choices for researchers. Graph neural network (GNN) is employed in ParaVS, and we explained how our in-house GNN works and how to model ligands and molecular targets. To verify our approaches, cross validation experiments are done on two datasets, an open dataset Directory of Useful Decoys: Enhanced (DUD.E) and an in-house proprietary dataset without computational generated artificial decoys (NoDecoy). On DUD.E we achieved a state-of-the-art AUC of 0.981 and a state-of-the-art enrichment factor at 2% of 36.2; on NoDecoy we achieved an AUC of 0.974. We further finish inference of an open database, Enamine REAL Database (RDB), that comprises over 1.36 billion molecules in 4050 core-hours using our ParaVS non-docking method (ParaVS-ND). The inference speed of ParaVS-ND is about 3.6e5 molecule / core-hour, while this number of a conventional docking-based method is around 20, which is about 16000 times faster. The experiments indicate that ParaVS is accurate, computationally efficient and can be generalized to different molecular.

Jinjiang Guo, Jie Li, Dawei Leng et al.

Multi-scale biomedical knowledge networks are expanding with emerging experimental technologies that generates multi-scale biomedical big data. Link prediction is increasingly used especially in bipartite biomedical networks to identify hidden biological interactions and relationshipts between key entities such as compounds, targets, gene and diseases. We propose a Graph Neural Networks (GNN) method, namely Graph Pair based Link Prediction model (GPLP), for predicting biomedical network links simply based on their topological interaction information. In GPLP, 1-hop subgraphs extracted from known network interaction matrix is learnt to predict missing links. To evaluate our method, three heterogeneous biomedical networks were used, i.e. Drug-Target Interaction network (DTI), Compound-Protein Interaction network (CPI) from NIH Tox21, and Compound-Virus Inhibition network (CVI). Our proposed GPLP method significantly outperforms over the state-of-the-art baselines. In addition, different network incompleteness is analysed with our devised protocol, and we also design an effective approach to improve the model robustness towards incomplete networks. Our method demonstrates the potential applications in other biomedical networks.