Molecular evolution is the process of simulating the natural evolution of molecules in chemical space to explore potential molecular structures and properties. The relationships between similar molecules are often described through transformations such as adding, deleting, and modifying atoms and chemical bonds, reflecting specific evolutionary paths. Existing molecular representation methods mainly focus on mining data, such as atomic-level structures and chemical bonds directly from the molecules, often overlooking their evolutionary history. Consequently, we aim to explore the possibility of enhancing molecular representations by simulating the evolutionary process. We extract and analyze the changes in the evolutionary pathway and explore combining it with existing molecular representations. Therefore, this paper proposes the molecular evolutionary network (MEvoN) for molecular representations. First, we construct the MEvoN using molecules with a small number of atoms and generate evolutionary paths utilizing similarity calculations. Then, by modeling the atomic-level changes, MEvoN reveals their impact on molecular properties. Experimental results show that the MEvoN-based molecular property prediction method significantly improves the performance of traditional end-to-end algorithms by approximately 33% on both the QM7 and QM9 datasets.

The prediction of compound–protein interactions (CPIs) is crucial for drug discovery. Most existing CPI prediction models rely on protein sequence information as input. However, in early-stage drug development, particularly in phenotype-driven studies or compound-response analyses, proteins are often annotated only with functional labels, and their sequences remain undetermined. Consequently, current methods are inapplicable in such scenarios. Furthermore, our experiments find that even when large-scale perturbations were applied to protein sequences, the predictive performance of the existing models did not show a significant decline. It indicates that the high investment in sequencing may not bring corresponding returns. To address the above issues, we propose an inexpensive, protein-sequencing-free framework BioText-CPI, based on the Biomedical Textual description of protein for CPI prediction. Firstly, during the pre-training stage of the model, we use contrastive learning to align protein texts and sequence modalities. Subsequently, we add biological text descriptions of proteins to the existing public CPI dataset to construct a new CPI dataset. Finally, in the CPI prediction stage, the sequence and biomedical text descriptions of proteins can be used as the input for CPI prediction either separately or simultaneously to meet the application requirements of different scenarios. The experiments demonstrate that BioText-CPI achieves comparable effects to the traditional methods when only the biomedical description of protein is input. Moreover, when the two modalities of protein information are input simultaneously, BioText-CPI achieves state-of-the-art performance across multiple scenarios.

Xuxu Liu, Siyuan Liang, Mengya Han, Yong Luo, Aishan Liu, Xiantao Cai, Zheng He, Dacheng Tao. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Generating graph-structured molecular data involves understanding complex graph distributions. This is crucial for de novo drug molecule design, especially when incorporating drug-drug interactions (DDIs). Existing graph generative methods often struggle to capture the graphs' permutation invariance or fail to model the collaborative dependencies among various molecular components, including atom-, bond-, and textual-level DDI information. To address these limitations, we propose DDI-Diff, a knowledge-driven dual diffusion model for DDI-based drug design. DDI-Diff employs a continuous time framework and introduces a collaborative graph diffusion process, leveraging a stochastic differential equations (SDEs) system to jointly model node and edge distribution. During pretraining, we use a large-scale, unconditional dataset, followed by conditional training on DrugBank. This enhances the model's ability to generate molecular structures that align with DDI-aware knowledge, effectively capturing the collaborative effects among drugs. Then, we validated our model using DrugBank, demonstrating that DDI-Diff improves accuracy by 4.35% more than current state-of-the-art methods across all labels and highlighting its potential in collaborative drug design.

In the field of autonomous driving and intelligent transportation systems, 3D object detection plays a critical role in ensuring safe and efficient driving. Achieving reliable object detection relies on robust sensing technologies, where LiDAR provides accurate spatial perception, and radar offers extended detection range and speed information because of its longer wave-lengths. To capitalize on the strengths of both sensors, a novel RCS-based LiDAR-Radar fusion network, named RLRFusion, is proposed for 3D object detection in this paper. The network takes LiDAR and radar point clouds as inputs and processes them through dual bird's-eye view (BEV) feature extraction streams, followed by the BEV fusion and detection module to produce the detection results. In input-level fusion, a cross-modal pillar encoder is introduced to address the sparse radar data and its lack of height information. In feature-level fusion, an RCS-aware fusion encoder leverages the Radar Cross Section (RCS) distribution by mapping pillar features to their surroundings, enhancing object size estimation and mitigating the challenges faced by LiDAR in adverse weather conditions. Experimental results show that RLRFusion achieves competitive performance on the nuScenes dataset, with strong detection results even in rainy conditions. The source code of our method is available at: https://github.com/djZzgroupIRLRFusion.

Text-to-motion has widespread applications in VR/AR, games, filmmaking, and robotics. In real-world scenarios, humans frequently initiate interactions with the surrounding environment using specific body parts. In this work, we introduce BOCO, a novel method for fine-grained BOdy part COntrol in text-driven human motion synthesis with interactive intention. BOCO employs a decoupled strategy to extract body part movements and leverages large language models to capture corresponding part-level semantics described in text. Additionally, BOCO introduces a spatial coherence module based on a part-based graph structure to ensure semantic accuracy and spatial consistency. We developed a specialized dataset from HUMANML3D for training and evaluation. Experiments demonstrate that BOCO significantly enhances nuanced, accurate, and adaptable text-to-motion generation. By focusing on human-centric interactive intentions, BOCO is better suited for general and flexible interaction scenarios, paving the way for broader interaction applications as object inference and simulation technologies advance.

Due to their excellent drug-like and pharmacokinetic properties, small molecule drugs are widely used to treat various diseases, making them a critical component of drug discovery. In recent years, with the rapid development of deep learning (DL) techniques, DL-based small molecule drug discovery methods have achieved excellent performance in prediction accuracy, speed, and complex molecular relationship modeling compared to traditional machine learning approaches. These advancements enhance drug screening efficiency, streamline optimization, and provide more precise and effective solutions for drug discovery. Contributing to this field's development, this paper aims to systematically summarize and generalize the recent key tasks and representative techniques in graph-structured small molecule drug discovery. Specifically, we provide an overview of the major tasks in small-molecule drug discovery and their interrelationships. Next, we analyze the six core tasks, summarizing the related methods, commonly used datasets, and technological development trends. Finally, we discuss key challenges, such as interpretability and out-of-distribution generalization, and offer our insights into future research directions for small molecule drug discovery.

Antibody design remains a critical challenge in therapeutic and diagnostic development, particularly for complex antigens with diverse binding interfaces. Current computational methods face two main limitations: (1) capturing geometric features while preserving symmetries, and (2) generalizing novel antigen interfaces. Despite recent advancements, these methods often fail to accurately capture molecular interactions and maintain structural integrity. To address these challenges, we propose AbMEGD, an end-to-end framework integrating Multi-scale Equivariant Graph Diffusion for antibody sequence and structure co-design. Leveraging advanced geometric deep learning, AbMEGD combines atomic-level geometric features with residue-level embeddings, capturing local atomic details and global sequence-structure interactions. Its E(3)-equivariant diffusion method ensures geometric precision, computational efficiency, and robust generalizability for complex antigens. Furthermore, experiments using the SAbDab database demonstrate a 10.13% increase in amino acid recovery, 3.32% rise in improvement percentage, and a 0.062 Å reduction in root mean square deviation within the critical CDR-H3 region compared to DiffAb, a leading antibody design model. These results highlight AbMEGD's ability to balance structural integrity with improved functionality, establishing a new benchmark for sequence-structure co-design and affinity optimization. The code is available at: https://github.com/Patrick221215/AbMEGD.

We proposes a novel visual tokenizer by combining high-level semantic tokens and low-level pixel tokens to represent images, aiming to address the challenges of image-to-sequence conversion for Large Language Models (LLMs). Existing visual tokenizers, such as VQ-VAE and diffusion-based models, either struggle with token explosion as image resolution increases or fail to capture detailed structural information. Our method introduces a dual-token system: high-level semantic tokens capture the main content of the image, while low-level pixel tokens preserve structural details. By integrating these tokens in a hybrid architecture, we leverage a VQ-VAE branch to generate low-resolution guidance and a diffusion process to reconstruct high-resolution images with both semantic coherence and structural accuracy. This approach significantly reduces the number of required tokens and enhances image reconstruction quality, offering an efficient solution for tasks like image generation and understanding based on LLMs.

In this work, we address the new challenge of open-vocabulary fine-grained hand action detection, which aims to recognize hand actions from both known and novel categories using textual descriptions. Traditional hand action detection methods are limited to closed-set detection, making it difficult for them to generalize to new, unseen hand action categories. While current open-vocabulary detection (OVD) methods are effective at detecting novel objects, they face challenges with fine-grained action recognition, particularly when data is limited and heterogeneous. This often leads to poor generalization and performance bias between base and novel categories. To address these issues, we propose a novel approach, Open-FGHA (Open-vocabulary Fine-Grained Hand Action), which learns to distinguish fine-grained features across multiple modalities from limited heterogeneous data. It then identifies optimal matching relationships among these features, enabling accurate open-vocabulary fine-grained hand action detection. Specifically, we introduce three key components: Hierarchical Heterogeneous Low-Rank Adaptation, Bidirectional Selection and Fusion Mechanism, and Cross-Modality Query Generator. These components work in unison to enhance the alignment and fusion of multimodal fine-grained features. Extensive experiments demonstrate that Open-FGHA outperforms existing OVD methods, showing its strong potential for open-vocabulary hand action detection. The source code is available at OV-FGHAD.

Chain-of-thought (CoT) reasoning has exhibited impressive performance in language models for solving complex tasks and answering questions. However, many real-world questions require multi-modal information, such as text and images. Previous research on multi-modal CoT has primarily focused on extracting fixed image features from off-the-shelf vision models and then fusing them with text using attention mechanisms. This approach has limitations because these vision models were not designed for complex reasoning tasks and do not align well with language thoughts. To overcome this limitation, we introduce a novel approach for multi-modal CoT reasoning that utilizes latent space learning via diffusion processes to generate effective image features that align with language thoughts. Our method fuses image features and text representations at a deep level and improves the complex reasoning ability of multi-modal CoT. We demonstrate the efficacy of our proposed method on multi-modal ScienceQA and machine translation benchmarks, achieving state-of-the-art performance on ScienceQA. Overall, our approach offers a more robust and effective solution for multi-modal reasoning in language models, enhancing their ability to tackle complex real-world problems.

In recent years, the use of multi-modal pre-trained Transformers has led to significant advancements in visually-rich document understanding. However, existing models have mainly focused on features such as text and vision while neglecting the importance of layout relationship between text nodes. In this paper, we propose GraphLayoutLM, a novel document understanding model that leverages the modeling of layout structure graph to inject document layout knowledge into the model. GraphLayoutLM utilizes a graph reordering algorithm to adjust the text sequence based on the graph structure. Additionally, our model uses a layout-aware multi-head self-attention layer to learn document layout knowledge. The proposed model enables the understanding of the spatial arrangement of text elements, improving document comprehension. We evaluate our model on various benchmarks, including FUNSD, XFUND and CORD and it achieves state-of-the-art results among these datasets. Our experiment results demonstrate that our proposed method provides a significant improvement over existing approaches and showcases the importance of incorporating layout information into document understanding models. We also conduct an ablation study to investigate the contribution of each component of our model. The results show that both the graph reordering algorithm and the layout-aware multi-head self-attention layer play a crucial role in achieving the best performance.

U-Net[1] framework which containing an encoder- decoder architecture is still a comment choice for semantic segmentation in medical area. However, due to the intrinsic locality of convolution operations, the U-Net framework is not capable of capturing long-range dependency. Transformer[2] which can model long-range dependency because of the insider self-attention mechanism, first proposed in natural language processing domain and got a great success, is introduced to computer vision and has achieved promising results in the downstream tasks such as image classification and segmentation. In this paper, we propose UTransNet to explore a way to fuse transformer into U-Net to take both advantage of the characteristics of convolution layer and transformer to segment medical images. We test our end-to-end network on ATLAS datasets and the results demonstrate that the performance of our method is superior than previous U-Net based methods but with the least parameters.

The point cloud we obtained from LiDAR or depth camera may usually have some kind of missing part due to the obstacles and the insufficient of resolution. Finding a way to complete these missing parts comes to be essential for the understanding of point cloud. The previous methods tend to have a strict limitation on the input size or output size of point cloud, which leads to some kind of sparsification of the points and can not actually be applied to various scenarios. In this paper, we provide a self-adaptive method where both the input size and output size can be flexible and don’t have any hard limitations on them. We apply the AABB box to convert the problem into 2D image plane and take use of hierarchically depth image painting to complete the task. The experiment shows that our method has a self-adaptive ability to give various output without strict limitations while maintaining the local detail of the point cloud.

Knowledge plays a very important role in the dialogue systems. Inspired by how humans use unstructured background knowledge in the conversations, this paper proposes a dialogue generation model based on multi-task learning. The model divides the conversation generation task into two tasks, a knowledge selection task and a response prediction task, which are regard as a reading comprehension task and a text generation task separately. Specifically, in the task of knowledge selection, a language pre-training model Bidirectional Encoder Representations from Transformers (BERT) is applied to solve the problem of selecting the knowledge from the background knowledge documents in the current context. And in the task of response prediction, a transformer version of pointer-generator network, being composed of an encoder using the shared BERT mentioned in knowledge selection and a decoder using the left-context-only transformer, is applied to copy tokens from the background knowledge via pointing and produce tokens in the vocabulary through a generator. Our experiments on the HOLL-E dataset show that our model achieves better results than the strong baseline models and the related recent work.

6G-Enabled Internet of Things (IoT) is about to open a new era of Internet of Everything (IoE). It creates favorable conditions for new application services. The human-machine dialogue system, one of the most important forms of human–machine interaction, is expected to replace mobile applications in the future. This article proposes a dialogue generation scheme named background knowledge-aware dialogue generation model with pretrained encoders (BKADGPE). Dialogue generation, which takes the context as input and response as output, is a sequence-to-sequence (Seq2Seq) task. Instead of only generating the response based on the previous sequence of utterances, background knowledge-aware dialogue generation is also relying on background knowledge documents. This is because people often communicate based on their background knowledge. This article divides it into two tasks: 1) a knowledge selection task and 2) a response generation task. One of the latest language pretraining models, a lite bidirectional encoder representations from transformers (ALBERT), is applied as the encoder. In the knowledge selection task, ALBERT adds the linear layer and softmax layer to predict the content-related knowledge span. In the response generation task, the ALBERT after fine-tuning through the knowledge selection task adds the left-context-only transformer with a copy mechanism to incorporate background knowledge span into the generated response. Empirical studies on the HOLL-E dataset show that the result of BKADGPE is better than the related works.

In the context of collaborative design, it is a challenge to effectively protect some IP(Intellectual Property) information while the model needs to be shared to another designer for co-design activities. In biology, genes determine the essential biological attributes of species and should be well kept. For collaborative design, the IP information of a CAD model is analogous to biological genes and can be therefore defined as Design Genes (DGs) to be protected during collaboration. Based on this concept, this paper presents a novel approach of DG based secure sharing of CAD models to support collaborative design. The approach consists of the following steps. Firstly, an innovative concept of DGs in a collaborative CAD model is defined used for representing protected knowledge in the model during collaboration. Secondly, a filter is introduced to identify the DGs of the model flexibly. An encryption algorithm is then described to encrypt the identified DGs of the model as encrypted DGs, while the other parts of the model are still geometrically valid and sharable to support collaborative design. Finally, case studies are used to validate the above steps. The innovation of the approach is the introduction of the innovative concept of DGs, development of related filter and encryption algorithm to ensure the security of critical information during collaborative design. The complexity of case studies can prove that the approach is applicable to realworld application scenarios.

An innovative Big Data enabled Intelligent Immune System (12S) has been developed to address manufacturing dynamics over life cycles to achieve sustainable manufacturing. The 12S is a novel inter-disciplinary integrated system of the artificial immune mechanism, the Wireless Sensor Network (WSN)-based Cyber Physical System (CPS), Artificial Neural Networks (ANNs) and sustainable manufacturing scheduling optimization algorithm. Abnormal energy consumption patterns of manufactured components from monitored Big Data are identified using ANNs. An intelligent immune mechanism is devised to adapt to the pattern/condition changes of machine tool systems and process dynamics. A rescheduling algorithm is triggered if abnormal manufacturing conditions are detected thereby achieving adaptive multiobjective optimization of energy consumption and manufacturing performance. Computer Numerical Controlled (CNC) machining processes have been used for system validation via industrial deployment into multiple machine lines in manufacturing factories. Around 30% in energy saving and over 50% in productivity improvement have been achieved by adopting 12S.

In a Cloud-enabled collaborative environment, how to ensure that the shared sensitive information of CAD models is effectively protected is one of the key challenges. In this paper, a parametric encryption method for CAD models in a Cloud manufacturing environment is presented. The method contains a Self-adaptive Encryption Algorithm and an Entire Encryption Algorithm. Based on the Self-adaptive Encryption Algorithm, the sensitive part of a CAD model is encrypted parametrically and adaptively, guaranteeing the security and validity of accessing the different parts of the CAD model when it being shared by its co-designer. Based on the Entire Encryption Algorithm, the whole CAD model is encrypted entirely in a large scale to prevent potential information leakage to unauthorized users when the model is uploaded to the Cloud.

As the popularization of 3D print technology, in the future cloud manufacturing environment, it makes the customization of personalized product with low cost to be possible. The design in the customization of personalized product is particularly important. And the key issues are the expression and understanding of design intentions from designers with different backgrounds in collaborative CAD which is main design tool for industrial products. An operation-effects merging for collaborative design method of personalized product is presented, which treats the operation effects reflecting the design intention as the research object, and merges the operation effects based on the geometric semantics to support the real-time collaborative product design freely. The advantage of the proposed method is that, the design intentions are expressed without any delay in the design which can improve the design efficiency and product quality.

Product data exchange is one of most important key issues in Collaborative Product Development. Since feature-based parametric CAD systems have been dominated by industrial applications, Feature-Based Data Exchange (FBDE) is getting real growth. However the main feature-based method still lacks the ability to exchange complex shape among the heterogeneous CAD Systems. This paper attacks the problem by exchanging the parametric curve (such as Spline) which is sketched in 2D and will be used to prepare complex 3D shapes by various extrusion features. Therefore the data exchange of complex shape is divided into two layers: 3D extrusion layer and 2D sketch layer. The exchange of spline proceed in the 2D sketch layer between different CAD systems. We innovatively convert the problem of spline exchange into the problem of spline fitting, and employ the Genetic Algorithm (GA) to solve the problem. A new coding strategy in stage of initialization population is presented to improve the GA so it works well with the spline fitting among the heterogeneous CAD systems. Finally, a Hausdorff Distance (HD) is adopted to calculate the fitness. Experimental results demonstrate the effectiveness of our method.

Model security for collaborative product design in a networked environment (or called networked manufacture, grid manufacture, and cloud manufacture) is an important and also challenging research issue. In order to support collaborative product design in a secure and flexible means, a multi-granularity partial encryption method has been proposed in this paper. Base on the above method, parts of a Computer Aided Design (CAD) model can be selected flexibly by users for encrypting with multi-granularity, according to different users' requirements. The secret keys for the different parts of the CAD model can be customized to meet the requirements of users. Case studies have been developed to demonstrate the effectiveness of the proposed method.

The environmental impact of manufacturing processes is closely associated with energy consumption. Decreasing energy consumption of manufacturing processes can significantly improve the environmental performance of manufacturing to obtain sustainability. However, in most manufacturing process planning and scheduling methods, little attention has been paid to the energy consumption. In this paper, an energy consumption model and a honey-bee mating optimization (HBMO) approach have been developed to take the energy consumption into account as an objective to facilitate sustainable manufacturing process planning and scheduling. In the approach, a honey-bee mating process is simulated to achieve the optimization process where makespan and energy consumption are used as the performance criteria. A case study of process planning and scheduling is given. The experimental results are promising and compare well with the final results of the genetic algorithm based optimization approach.

In 3D collaborative modeling systems, users need a convenient mechanism to repeatedly modify the models they are operating on. In this paper, we contribute a selective undo/redo solution for users to select arbitrary operation to undo. With the consistency maintainence mechanism we proposed, operations need to be re-arranged on each site for after their arriving. Both history buffer and model state stream are adopted to present the arriving sequence of operations and their actual execution sequence. In case of concurrent undo/redo, undo state vector is proposed to make sure that an operation can only be undone once and redone by the designer who undoes it. Based on all the precautions we have made, an undo/redo algorithm is proposed. The algorithm has been verified in the prototype we implemented.

Consistency maintenance is one of the most important problems in collaborative CAD systems. However, existing consistency maintenance mechanisms limit multi-user interaction. This paper presents a consistency maintenance method to gain a less-constrained multi-user interaction. First, the causal relation between modeling operations is preserved using the state vector. Then, the concurrent deletion operations are checked to decide if the current operation is masked. If not, the solution for topological entities' matching is adopted to deal with the operations that use topological entities. Then, for those operations which do not use topological entities, the corresponding mechanism is adopted according to their types. By these mechanisms, the commutative, masked and conflicted relations between the concurrent operations, are explored and the conflicts are solved. The experiments prove that our method can support less-constrained multi-user interaction.

In this paper, we introduce a novel 2D-3D hybrid video stabilization method which combines virtues of 2D and 3D video stabilization methods in one routine. It attempts to achieve high-quality camera motions and to retain full frame coherence in each frame, at while, ensure that local regions undergo a similarity transformation. We solve the stabilization problem by integrating 3D and 2D video stabilization methods into one routine. It smooths camera motions and explicitly employs local motion information which constraints video frames to be temporal coherent, and achieves high-quality video stabilization. Experiments show that our method not only can achieve high-quality camera motion on good 3D reconstructed scene, but also can deal with complicated videos containing near, large moving objects.

This paper introduces an approach to performance animation that uses window-based principal component analysis (WLPCA). Our key idea is to construct a series of local models from a prerecorded motion database and utilize them to construct full-body human motion in a maximum a posteriori frame work. We have demonstrated the effectiveness of our approach by synthesizing a variety of human actions. Given an appropriate motion capture database, the results are comparable in quality to the ground truth data. We have also evaluated the performance of our approach by leave-one-out experiments and by comparing to two baseline algorithms.

In the feature modeling procedure, one-dimensional topological entities (edges) are always used as references or operational objects. Hence, to realize the integration of heterogeneous CAD systems, the corresponding one-dimensional topological entities must be found in the target CAD system to match the source ones. This paper presents a method to gain one-dimensional topological entity matching. The method is based on two algorithms, i.e. combining algorithm and matching algorithm. The combining algorithm is adopted to combine the edges retrieved in a source CAD system. Then, for each combined edge, the matching edges are found by using the matching algorithm in a target CAD system. The experiments prove that our method is valid for both offline and online integrations.

Heterogeneous CAD data exchange is very important in collaborative product development and also extremely difficult. Feature-based data exchange has many advantages than traditional geometry-based data exchange. According to the framework of procedure recovery in feature-based data exchange, this paper discusses the key issues of feature extraction and reconstruction, including the extraction of first-order feature information, extraction of second-order feature information and the reconstruction of feature model. The proposed methods have been tested in experiments. The result shows that propsed approach has efficiently improved the former researches, such as ISO/STEP method, Macro command method and UPR method.

How to name the topological entities is the footstone of collaborative modeling systems. This paper presents a method to correspond topological entities in non-quiescent context of replicated collaborative CAD system. The proposed method adopts an automatic undo/do/redo mechanism to restore the definition context of CAD command to achieve a consistent naming mechanism in non-quiescent context.

Data exchange is one of key issues in collaborative design. The purpose of feature-based data exchange is that the target model is editable after being exchanged. This is the reason why nowadays feature-based data exchanges become the research focus beyond the traditional geometry-based data exchange. This paper presents a two-stage mechanism to recover a complete modeling process of a parametric CAD mode in source systems. Therefore, what we exchange is the procedure of modeling steps. In target systems, we use the exchanged procedure to simulate a real human to reconstruct the parametric CAD mode in any heterogeneous CAD systems. The proposed method has been tested with case studies among typical CAD systems, such as SolidWorks, UG, Pro/E and Catia.

From CSCW view, the name issues in replicated collaborative solid modeling involve several fundamental challenges, such as consistency maintenance, multi-user interaction and undo/redo mechanism. Therefore, a consistency and awareness naming approach will contribute to all of above three challenges, either directly or potentially. The paper begins with the multi-user interaction framework in replicated collaborative solid modeling. And then a collaborative name structure is constructed to consistently name merged faces. Finally an awareness method is presented to distinguish which type of operation to create the merged faces. The proposed methods are illustrated with case studies in replicated collaborative solid modeling.

At first, graphics media are abstracted into high level and low level representation. The high level representation includes the design history and feature description. The low level includes topology, geometry and attribution. Secondly, the consistency conditions for different abstracted levels are established. The consistency conditions can be described as strong consistency or weak consistency. They also can be described as strong no-consistency or weak no-consistency. Thirdly, according to layered consistency conditions, different abstracted levels of graphics media are associated with suitable concurrent control methods respectively, which can be strict or relaxed. Fourthly, the strategy how to apply hierarchical consistency model into flexible collaboration transparent infrastructure are analyzed. Finally, we applied the model and methods in our test-bed for collaborative design of engineering graphics.