Large language models (LLMs) show promising performance on small-scale graph reasoning tasks but fail when handling real-world graphs with complex queries. This phenomenon arises from LLMs' working memory constraints, which result in their inability to retain long-range graph topology over extended contexts while sustaining coherent multi-step reasoning. However, real-world graphs are often structurally complex, such as Web, Transportation, Social, and Citation networks. To address these limitations, we propose GraphCogent, a collaborative agent framework inspired by human Working Memory Model that decomposes graph reasoning into specialized cognitive processes: sense, buffer, and execute. The framework consists of three modules: Sensory Module standardizes diverse graph text representations via subgraph sampling, Buffer Module integrates and indexes graph data across multiple formats, and Execution Module combines tool calling and tool creation for efficient reasoning. We also introduce Graph4real, a comprehensive benchmark that contains four domains of real-world graphs (Web, Transportation, Social, and Citation) to evaluate LLMs' graph reasoning capabilities. Our Graph4real covers 21 different graph reasoning tasks, categorized into three types (Structural Querying, Algorithmic Reasoning, and Predictive Modeling tasks), with graph scales up to 10 times larger than existing benchmarks. Experiments show that Llama3.1-8B based GraphCogent achieves a 50% improvement over massive-scale LLMs like DeepSeek-R1 (671B). Compared to state-of-the-art code-based baseline, our framework outperforms by 20% in accuracy while reducing token usage by 80% for in-toolset tasks and 30% for out-toolset tasks.

Dataset distillation (DD) has demonstrated the promise of synthesizing smaller datasets that enable competitive performance. While most of DD methods operate in pixel space, they often suffer from poor scalability on high-resolution datasets. Recent works have thus shifted towards parameterizing synthetic data using deep generative priors. However, these approaches apply latent updates to all generator layers, leading to substantial computational overhead. To address this limitation, we propose Generative Lightweight Distillation (GLiD), a unified framework that jointly compresses the generator and accelerates latent optimization for efficient distillation. GLiD introduces two key components: (1) We introduce a Classification-Diversity Sensitivity Pruning mechanism that quantifies both discriminative utility and semantic diversity of each output channel to guide structural pruning and selective layer-wise optimization. (2) We also present a Layer-Adaptive Scheduling strategy that dynamically allocates latent update steps across generator stages based on convergence behavior. Extensive experiments on CIFAR-10 and ImageNet-1K and its subsets demonstrate that our GLiD achieves up to 10× acceleration across different datasets, while maintaining performance competitive with state-of-the-art methods.

Modern industrial environments generate massive streams of discrete textual logs that record device status, error codes, and operational events. Deploying models on resource-constrained edge devices demands extreme data compression and fast inference, yet existing dataset distillation (DD) methods are designed for images and capture only short-term training dynamics via single-step gradient or distribution matching. To address these limitations, we propose textual trajectory matching (TTM), a novel textual DD framework that aligns student trajectories with expert trajectories derived from industrial data training. We introduce a Mask-and-Fill initialization to enhance trajectory diversity, expanding semantic representations. We further propose a manifold distribution-based initialization to preserve original semantic features through low-dimensional manifold analysis. To address model computational costs, we design a subset matching strategy to reducing by aligning critical structural components. Evaluated on SST-2, MNLI-m, AGNews, and BlueGene/L (BGL) with$\text{BERT}_{\text{BASE}}$,$\text{RoBERTa}_{\text{BASE}}$,$\text{XLNet}_{\text{BASE}}$, and LLaMA 3, TTM achieves 3.6% higher accuracy than state-of-the-art methods, enabling efficient industrial dataset and model deployment in smart factories.

Contemporary deep learning, characterized by the training of cumbersome neural networks on massive datasets, confronts substantial computational hurdles. To alleviate heavy data storage burdens on limited hardware resources, numerous dataset compression methods such as dataset distillation (DD) and coreset selection have emerged to obtain a compact but informative dataset through synthesis or selection for efficient training. However, DD involves an expensive optimization procedure and exhibits limited generalization across unseen architectures, while coreset selection is limited by its low data keep ratio and reliance on heuristics, hindering its practicality and feasibility. To address these limitations, we introduce a newly versatile framework for dataset compression, namely Adaptive Dataset Quantization (ADQ). Specifically, we first identify the sub-optimal performance of naive Dataset Quantization (DQ), which relies on uniform sampling and overlooks the varying importance of each generated bin. Subsequently, we propose a novel adaptive sampling strategy through the evaluation of generated bins' representativeness score, diversity score and importance score, where the former two scores are quantified by the texture level and contrastive learning-based techniques, respectively. Extensive experiments demonstrate that our method not only exhibits superior generalization capability across different architectures, but also attains state-of-the-art results.

The growing demand for efficient deep learning has positioned dataset distillation as a pivotal technique for compressing training dataset while preserving model performance. However, existing inner-loop optimization methods for dataset distillation typically rely on random truncation strategies, which lack flexibility and often yield suboptimal results. In this work, we observe that neural networks exhibit distinct learning dynamics across different training stages—early, middle, and late—making random truncation ineffective. To address this limitation, we propose Automatic Truncated Backpropagation Through Time (AT-BPTT), a novel framework that dynamically adapts both truncation positions and window sizes according to intrinsic gradient behavior. AT-BPTT introduces three key components: (1) a probabilistic mechanism for stage-aware timestep selection, (2) an adaptive window sizing strategy based on gradient variation, and (3) a low-rank Hessian approximation to reduce computational overhead. Extensive experiments on CIFAR-10, CIFAR-100, Tiny-ImageNet, and ImageNet-1K show that AT-BPTT achieves state-of-the-art performance, improving accuracy by an average of 6.16\% over baseline methods. Moreover, our approach accelerates inner-loop optimization by 3.9 × while saving 63\% memory cost.

Data-free knowledge distillation (DFKD) has emerged as a pivotal technique in the domain of model compression, substantially reducing the dependency on the original training data. Nonetheless, conventional DFKD methods that employ synthesized training data are prone to the limitations of inadequate diversity and discrepancies in distribution between the synthesized and original datasets. To address these challenges, this paper introduces an innovative approach to DFKD through diverse diffusion augmentation (DDA). Specifically, we revise the paradigm of common data synthesis in DFKD to a composite process through leveraging diffusion models subsequent to data synthesis for self-supervised augmentation, which generates a spectrum of data samples with similar distributions while retaining controlled variations. Furthermore, to mitigate excessive deviation in the embedding space, we introduce an image filtering technique grounded in cosine similarity to maintain fidelity during the knowledge distillation process. Comprehensive experiments conducted on CIFAR-10, CIFAR-100, and Tiny-ImageNet datasets showcase the superior performance of our method across various teacher-student network configurations, outperforming the contemporary state-of-the-art DFKD methods. Code will be available at: https://github.com/SLGSP/DDA.