Training vision-language models (VLMs) typically requires large-scale, high-quality image-text pairs, but collecting or synthesizing such data is costly. In contrast, text data is abundant and inexpensive, prompting the question: can high-quality multimodal training data be synthesized purely from text? To tackle this, we propose a cross-integrated three-stage multimodal data synthesis framework, which generates two datasets: Unicorn-1.2M and Unicorn-471K-Instruction. In Stage 1: Diverse Caption Data Synthesis, we construct 1.2M semantically diverse high-quality captions by expanding sparse caption seeds using large language models (LLMs). In Stage 2: Instruction-Tuning Data Generation, we further process 471K captions into multi-turn instruction-tuning tasks to support complex reasoning. Finally, in Stage 3: Modality Representation Transfer, these textual captions representations are transformed into visual representations, resulting in diverse synthetic image representations. This three-stage process enables us to construct Unicorn-1.2M for pretraining and Unicorn-471K-Instruction for instruction-tuning, without relying on real images. By eliminating the dependency on real images while maintaining data quality and diversity, our framework offers a cost-effective and scalable solution for VLMs training. Code is available at https://github.com/Yu-xm/Unicorn.git.

The Graph Edit Distance (GED) problem, which aims to compute the minimum number of edit operations required to transform one graph into another, is a fundamental challenge in graph analysis with wide-ranging applications. However, due to its NP-hard nature, traditional A* approaches often suffer from scalability issue, making them computationally intractable for large graphs. Many recent deep learning frameworks address GED by formulating it as a regression task, which, while efficient, fails to recover the edit path -- a central interest in GED. Furthermore, recent hybrid approaches that combine deep learning with traditional methods to recover the edit path often yield poor solution quality. These methods also struggle to generate candidate solutions in parallel, resulting in increased running times.In this paper, we present a novel approach, DiffGED, that leverages generative diffusion model to solve GED and recover the corresponding edit path. Specifically, we first generate multiple diverse node matching matrices in parallel through a diffusion-based graph matching model. Next, node mappings are extracted from each generated matching matrices in parallel, and each extracted node mapping can be simply transformed into an edit path. Benefiting from the generative diversity provided by the diffusion model, DiffGED is less likely to fall into local sub-optimal solutions, thereby achieving superior overall solution quality close to the exact solution. Experimental results on real-world datasets demonstrate that DiffGED can generate multiple diverse edit paths with exceptionally high accuracy comparable to exact solutions while maintaining a running time shorter than most of hybrid approaches.

Cardinality estimation is a fundamental functionality in database systems. Most existing cardinality estimators focus on handling predicates over numeric or categorical data. They have largely omitted an important data type, set-valued data, which frequently occur in contemporary applications such as information retrieval and recommender systems. The few existing estimators for such data either favor high-frequency elements or rely on a partial independence assumption, which limits their practical applicability. We propose ACE, an Attention-based Cardinality Estimator for estimating the cardinality of queries over set-valued data. We first design a distillation-based data encoder to condense the dataset into a compact matrix. We then design an attention-based query analyzer to capture correlations among query elements. To handle variable-sized queries, a pooling module is introduced, followed by a regression model (MLP) to generate final cardinality estimates. We evaluate ACE on three datasets with varying query element distributions, demonstrating that ACE outperforms the state-of-the-art competitors in terms of both accuracy and efficiency.

Accurate segmentation is essential for effective treatment planning and disease monitoring. Existing medical image segmentation methods predominantly rely on uni-modal visual inputs, such as images or videos, requiring labor-intensive manual annotations. Additionally, medical imaging techniques capture multiple intertwined organs within a single scan, further complicating segmentation accuracy. To address these challenges, MedSAM, a large-scale medical segmentation model based on the Segment Anything Model (SAM), was developed to enhance segmentation accuracy by integrating image features with user-provided prompts. While MedSAM has demonstrated strong performance across various medical segmentation tasks, it primarily relies on geometric prompts (e.g., points and bounding boxes) and lacks support for text-based prompts, which could help specify subtle or ambiguous anatomical structures. To overcome these limitations, we propose the Organ-aware Multi-scale Text-guided Medical Image Segmentation Model (OMT-SAM) for multi-organ segmentation. Our approach introduces CLIP encoders as a novel image-text prompt encoder, operating with the geometric prompt encoder to provide informative contextual guidance. We pair descriptive textual prompts with corresponding images, processing them through pre-trained CLIP encoders and a cross-attention mechanism to generate fused image-text embeddings. Additionally, we extract multi-scale visual features from MedSAM, capturing fine-grained anatomical details at different levels of granularity. We evaluate OMT-SAM on the FLARE 2021 dataset, benchmarking its performance against existing segmentation methods. Empirical results demonstrate that OMT-SAM achieves a mean Dice Similarity Coefficient of 0.937, outperforming MedSAM (0.893) and other segmentation models, highlighting its superior capability in handling complex medical image segmentation tasks.

Dynamic Text-Attributed Graphs (DyTAGs) are a novel graph paradigm that captures evolving temporal edges alongside rich textual attributes. A prior approach to representing DyTAGs leverages pre-trained language models to encode text attributes and subsequently integrates them into dynamic graph models. However, it follows edge-centric modeling, as in dynamic graph learning, which is limited in local structures and fails to exploit the unique characteristics of DyTAGs, leading to suboptimal performance. We observe that DyTAGs inherently comprise three distinct modalities-temporal, textual, and structural-often exhibiting dispersed or even orthogonal distributions, with the first two largely overlooked in existing research. Building on this insight, we propose MoMent, a model-agnostic multi-modal framework that can seamlessly integrate with dynamic graph models for structural modality learning. The core idea is to shift from edge-centric to node-centric modeling, fully leveraging three modalities for node representation. Specifically, MoMent presents non-shared node-centric encoders based on the attention mechanism to capture global temporal and semantic contexts from temporal and textual modalities, together with local structure learning, thus generating modality-specific tokens. To prevent disjoint latent space, we propose a symmetric alignment loss, an auxiliary objective that aligns temporal and textual tokens, ensuring global temporal-semantic consistency with a theoretical guarantee. Last, we design a lightweight adaptor to fuse these tokens, generating comprehensive and cohesive node representations. We theoretically demonstrate that MoMent enhances discriminative power over exclusive edge-centric modeling. Extensive experiments across seven datasets and two downstream tasks show that MoMent achieves up to 33.62% improvement against the baseline using four dynamic graph models.

--Dynamic graphs, which capture time-evolving edges between nodes, are formulated in continuous-time or discrete-time dynamic graphs. They differ in temporal granularity: Continuous-Time Dynamic Graphs (CTDGs) exhibit rapid, localized changes, while Discrete-Time Dynamic Graphs (DTDGs) show gradual, global updates. This difference leads to isolated developments in representation learning for each type. T o advance dynamic graph representation learning, recent research attempts to design a unified model capable of handling both CTDGs and DTDGs, achieving promising results. However, it typically focuses on local dynamic propagation for temporal structure learning in the time domain, failing to accurately capture the underlying structural evolution associated with each temporal granularity and thus compromising model effectiveness. In addition, existing works-whether specific or unified-often overlook the issue of temporal noise, compromising the model's robustness. T o better model both types of dynamic graphs, we propose UniDyG, a unified and effective representation learning approach, which can scale to large dynamic graphs. Specifically, we first propose a novel Fourier Graph Attention (FGA T) mechanism that can model local and global structural correlations based on recent neighbors and complex-number selective aggregation, while theoretically ensuring consistent representations of dynamic graphs over time. Based on approximation theory, we demonstrate that FGA T is well-suited to capture the underlying structures in both CTDGs and DTDGs. We further enhance FGA T to resist temporal noise by designing an energy-gated unit, which adaptively filters out high-frequency noise according to the energy. Last, we leverage our proposed FGA T mechanisms for temporal structure learning and employ the frequency-enhanced linear function for node-level dynamic updates, facilitating the generation of high-quality temporal embeddings. Extensive experiments show that our UniDyG achieves an average improvement of 14. 4% over sixteen baselines across nine dynamic graphs while exhibiting superior robustness in noisy scenarios. YNAMIC graphs serve as a crucial data modality for representing time-evolving relationships (edges) between entities (nodes). Y uanyuan Xu and Wenjie Zhang are with the School of Computer Science and Engineering, The University of New South Wales, Sydney, NSW 2052, Australia (e-mail: yuanyuan.xu@unsw.edu.au; Xuemin Lin is with Antai College of Economics and Management, Shanghai Jiao Tong University, Shanghai 200052, china (e-mail: xuemin.lin@gmail.com). Ying Zhang is with the School of Statistics and Mathematics, School of Computer Science, Zhejiang Gongshang University, Hangzhou, Zhejiang 310018, China (e-mail: ying.zhang@zjgsu.edu.cn).

Missing data imputation, which aims to impute the missing values in the raw datasets to achieve the completeness of datasets, is crucial for modern data-driven models like large language models (LLMs) and has attracted increasing interest over the past decades. Despite its importance, existing solutions for missing data imputation either 1) only support numerical and categorical data or 2) show an unsatisfactory performance due to their design prioritizing text data and the lack of key properties for tabular data imputation. In this paper, we propose UnIMP, a Unified IMPutation framework that leverages LLM and high-order message passing to enhance the imputation of mixed-type data including numerical, categorical, and text data. Specifically, we first introduce a cell-oriented hypergraph to model the table. We then propose BiHMP, an efficient Bidirectional High-order Message-Passing network to aggregate global-local information and high-order relationships on the constructed hypergraph while capturing the inter-column heterogeneity and intra-column homogeneity. To effectively and efficiently align the capacity of the LLM with the information aggregated by BiHMP, we introduce Xfusion, which, together with BiHMP, acts as adapters for the LLM. We follow a pre-training and fine-tuning pipeline to train UnIMP, integrating two optimizations: chunking technique, which divides tables into smaller chunks to enhance efficiency; and progressive masking technique, which gradually adapts the model to learn more complex data patterns. Both theoretical proofs and empirical experiments on 10 real world datasets highlight the superiority of UnIMP over existing techniques.

This paper addresses the inherent inference latency challenges associated with deploying multimodal large language models (MLLM) in quadruped vision-language-action (QUAR-VLA) tasks. Our investigation reveals that conventional parameter reduction techniques ultimately impair the performance of the language foundation model during the action instruction tuning phase, making them unsuitable for this purpose. We introduce a novel latency-free quadruped MLLM model, dubbed QUART-Online, designed to enhance inference efficiency without degrading the performance of the language foundation model. By incorporating Action Chunk Discretization (ACD), we compress the original action representation space, mapping continuous action values onto a smaller set of discrete representative vectors while preserving critical information. Subsequently, we fine-tune the MLLM to integrate vision, language, and compressed actions into a unified semantic space. Experimental results demonstrate that QUART-Online operates in tandem with the existing MLLM system, achieving real-time inference in sync with the underlying controller frequency, significantly boosting the success rate across various tasks by 65%. Our project page is https://quart-online.github.io.

Materials discovery and design aim to find components and structures with desirable properties over highly complex and diverse search spaces. Traditional solutions, such as high-throughput simulations and machine learning (ML), often rely on complex descriptors, which hinder generalizability and transferability across tasks. Moreover, these descriptors may deviate from experimental data due to inevitable defects and purity issues in the real world, which may reduce their effectiveness in practical applications. To address these challenges, we propose Darwin 1.5, an open-source large language model (LLM) tailored for materials science. By leveraging natural language as input, Darwin eliminates the need for task-specific descriptors and enables a flexible, unified approach to material property prediction and discovery. We employ a two-stage training strategy combining question-answering (QA) fine-tuning with multi-task learning (MTL) to inject domain-specific knowledge in various modalities and facilitate cross-task knowledge transfer. Through our strategic approach, we achieved a significant enhancement in the prediction accuracy of LLMs, with a maximum improvement of 60\% compared to LLaMA-7B base models. It further outperforms traditional machine learning models on various tasks in material science, showcasing the potential of LLMs to provide a more versatile and scalable foundation model for materials discovery and design.

Signed Graph Neural Networks (SGNNs) are powerful tools for signed graph representation learning but struggle with limited generalization and heavy dependence on labeled data. While recent advancements in "graph pre-training and prompt tuning" have reduced label dependence in Graph Neural Networks (GNNs) and improved their generalization abilities by leveraging pre-training knowledge, these efforts have focused exclusively on unsigned graphs. The scarcity of publicly available signed graph datasets makes it essential to transfer knowledge from unsigned graphs to signed graph tasks. However, this transfer introduces significant challenges due to the graph-level and task-level divergences between the pre-training and downstream phases. To address these challenges, we propose Signed Graph Prompt Tuning (SGPT) in this paper. Specifically, SGPT employs a graph template and a semantic prompt to segregate mixed link semantics in the signed graph and then adaptively integrate the distinctive semantic information according to the needs of downstream tasks, thereby unifying the pre-training and downstream graphs. Additionally, SGPT utilizes a task template and a feature prompt to reformulate the downstream signed graph tasks, aligning them with pre-training tasks to ensure a unified optimization objective and consistent feature space across tasks. Finally, extensive experiments are conducted on popular signed graph datasets, demonstrating the superiority of SGPT over state-of-the-art methods.