Embedding-based generalized zero-shot learning (GZSL) models often first forge robust latent semantic correlations between visual and attribute features so that knowledge can generalize to unseen categories. Despite leveraging attributes as priors and learning a shared embedding space, current methods exhibit two critical flaws. First, attributes with heterogeneous granularity are treated uniformly, leading to semantic ambiguity. Second, the source of class-level misclassification seldom aligns with attribute-level errors, preventing models from targeting the specific attributes responsible. To overcome these limitations, we introduce Structured Attribute-Guided Enhancement (SAGE), a unified framework for GZSL. Consensus-aware bidirectional attention first synchronizes visual–semantic focus regions via a mutual-distillation scheme. Next, we partition all attributes into pairwise-disjoint subsets—Global, Context, and Local—and couple them with visual features extracted at matching spatial scales. Finally, we design a cross-sample, subset-aware distillation mechanism—when a sample is misclassified, SAGE identifies the culpable attribute subset, retrieves high-confidence prototypes from a memory bank, and applies a Kullback–Leibler (KL) divergence constraint to the corresponding feature branch. Comprehensive experiments and ablations on the challenging AwA2, CUB, and SUN benchmarks demonstrate the contribution of each component, with SAGE achieving a new state-of-the-art throughout. These findings underscore SAGE’s robustness and versatility, marking a substantial advance in generalized zero-shot learning and paving the way for broader zero-resource recognition.
论文检索
输入标题、作者或关键词，从 100,903 篇学术成果中精准定位
Pseudo-Spiking Neurons: A Noise-Based Training Framework for Heterogeneous-Latency Spiking Neural Networks
PDF ↗Spiking Neural Networks (SNNs) promise significant energy efficiency by processing information via sparse, event-driven spikes. However, realizing this potential is hindered by the conventional use of a rigid, uniform timestep, T. This constraint imposes a challenging trade-off between accuracy and latency, while also incurring the prohibitive training costs of Backpropagation Through Time (BPTT). To overcome this limitation, we introduce the Pseudo-Spiking Neuron (PseudoSN), a novel training proxy that conceptualizes latency as an intrinsic, learnable parameter for each neuron. Building on the efficiency of rate-based methods, the PseudoSN models temporal dynamics in a single, BPTT-free pass. It employs a learnable probabilistic noise scheme to emulate the discretization effects of spike generation (e.g., clipping and quantization), making the neuron-specific timestep—and thus latency—directly optimizable via backpropagation. Integrated into a hardware-aware objective, our framework trains heterogeneous-latency SNNs that autonomously learn to optimize the trade-offs among accuracy, latency and energy, establishing a new state-of-the-art on major benchmarks.
Knowledge distillation from Artificial Neural Networks (ANNs) to Spiking Neural Networks (SNNs) is a prominent training paradigm. However, its efficacy is fundamentally limited by a spectral mismatch: SNNs, with their intrinsic low-pass filtering characteristics, struggle to learn high-frequency details from their ANN teachers, creating a bottleneck in knowledge transfer at both the feature and logit levels. To address this, we propose Bi-Spectrum Distillation (BSD), a novel framework that mitigates the mismatch from two complementary perspectives. First, at the feature level, our Spectral Residual Distillation (SRD) enhances the student SNN's features with a parameter-efficient, learnable filter that adaptively compensates for high-frequency information loss, which transforms the student's output to better match the teacher's rich spectral target. Second, at the logits level, our Spectral Semantic Distillation (SSD) enhances fine-grained classification by distilling high-frequency components from teacher-ordered logits. Extensive experiments on CIFAR-10/100, ImageNet, and CIFAR10-DVS demonstrate that BSD achieves new state-of-the-art performance across both CNN and Transformer-based SNNs, validating its effectiveness and broad applicability.
Parameter-efficient transfer learning (PETL) has emerged as a pivotal paradigm for adapting pre-trained foundation models to downstream tasks, significantly reducing trainable parameters yet suffering from substantial memory overhead caused by gradient backpropagation during fine-tuning. While memory-efficient transfer learning (METL) circumvents this challenge by bypassing backbone gradient computation via lightweight small side networks, its stringent memory constraint severely limits learning capacity of side networks, thereby significantly compromising performance. To address these limitations, we propose a novel Mixed-Precision Interactive Side Mixture-of-Experts framework (MP-ISMoE). Specifically, we first propose an Gaussian Noise Perturbed Iterative Quantization (GNP-IQ) scheme to quantize weights into lower-bits while effectively decreasing quantization errors. By leveraging memory conserved from GNP-IQ, we subsequently employ Interactive Side Mixture-of-Experts (ISMoE) to scale up side networks without sacrificing overall memory efficiency. Different from conventional mixture-of-experts, ISMoE learns to select optimal experts by interacting with salient features from frozen backbones, thus suppressing knowledge forgetting and boosting performance. Extensive experiments across diverse vision-language and language-only tasks demonstrate that MP-ISMoE remarkably promotes accuracy compared to state-of-the-art METL approaches, while maintaining comparable parameter and memory efficiency.
Model-heterogeneous federated tuning (MHFT) enables the privacy-preserving fine-tuning of foundation models in heterogeneous systems by allowing clients and the server to adopt different model architectures. Depth partial training—where each client updates only a subset of the model's layers—alleviates system heterogeneity but exacerbates client drift, which stems from clients optimizing different objectives and therefore degrades overall performance. Beyond the well-known statistical bias—where non-IID data leads to client drift—we identify a structural bias arising from clients deploying only partial layers of the global model, which serves as an important cause of drift. We further provide a theoretical analysis showing that the possible range of structural bias expands linearly with the number of missing layers. To counter this effect, we introduce FedBRICK (Federated Bias Recovery via Inserted Calibrative Kernels), which inserts tiny BRICKs into each client’s subnetwork. We employ a dual-end layer-wise distillation scheme to train these blocks using both client-side local data and a small public proxy set on the server. This design effectively mitigates the structural bias caused by layer dropping, reduces client drift, and remains practical for storage-constrained devices. Extensive experiments on federated learning benchmarks confirm that FedBRICK delivers up to a 5% average accuracy gain while requiring no more than 1.44% extra storage per client.
Mamba-Driven Multi-View Discriminative Clustering via Global-Local Cross-View Sequence Modeling
PDF ↗Multi-view clustering (MVC) has recently garnered increasing attention for its ability to partition unlabeled samples into distinct clusters by leveraging complementary and consistent information from different views. Existing MVC methods primarily combine deep neural networks with contrastive learning for cross-view representation learning, yet often overlook the inherent global-local structural relationships among samples. While GNN-based methods capture local structures, they struggle to model global dependencies, leading to inferior inter-cluster separability. In contrast, Transformer-based methods excel at global aggregation but suffer from quadratic complexity, and their attention smoothing effect weakens fine-grained local structures, resulting in suboptimal intra-cluster compactness. To address these limitations, we propose a novel end-to-end MVC framework called Mamba-Driven Multi-View Discriminative Clustering via Global-Local Cross-View Sequence Modeling (MGLC). By flexibly constructing multi-view sequences, MGLC fully exploits the efficient sequence modeling capabilities of Mamba to jointly model cross-view dependencies and global-local structural relationships among samples. Furthermore, MGLC introduces a Cross-Mamba Fusion module to dynamically integrate cross-view and global-local structural representations. Additionally, MGLC incorporates a Dual Calibration Contrastive Learning module, guided by high-confidence pseudo-labels, that adaptively refines both feature and semantic representations while mitigating false negatives among semantically similar samples. Extensive comparative experiments and ablation studies demonstrate the effectiveness of MGLC.
Rethinking Multi-Instance Learning Through Graph-Driven Fusion: A Dual-Path Approach to Adaptive Representation
PDF ↗Multi-instance learning (MIL) has become a powerful paradigm for weakly supervised learning tasks, where each sample is a bag of unlabeled instances with only the bag-level label. While graph-based MIL methods enhance bag topological structure modeling, they often suffer from high computation costs and limited representation due to rigid graph construction and insufficient integration of intra-bag semantics. To address these challenges, we propose GDF-MIL, a novel graph-driven MIL framework, which introduces a dual-path feature fusion mechanism to adaptively balance topological structure modeling and semantic feature preservation. First, the adaptive bag mapping module (ABMM) performs soft clustering to extract compact and informative representations. Subsequently, a dynamic graph structure learning (DGSL) component efficiently learns sparse topological structures via weighted connectivity, aggregating them into a comprehensive graph-level representation. Finally, to balance fast graph construction and bag-level knowledge, dual-path feature fusion (DPFF) employs a dual-path gating mechanism to integrate both types of features, which are then passed to the classifier for bag label prediction. Extensive experiments on twenty-four datasets across four domains show that GDF-MIL significantly outperforms eighteen state-of-the-art methods on the majority of datasets.
Efficient Tensorized Multi-View Anchor Graph Clustering with Affinity Propagation for Remote Sensing Data
PDF ↗Multi-view clustering of remote sensing data presents significant challenges, as it integrates diverse data representations to improve Earth observation. Although existing anchor graph-based methods have yielded promising results, they generally exhibit two key limitations: (1) the time-consuming process of directly exploring pixel clustering structures, and (2) insufficient modeling of high-order correlations among different views. To address these issues, we propose an Efficient Tensorized multi-view anchor graph clustering method with Affinity Propagation (ETAP) for remote sensing data. Based on superpixel preprocessing, anchor graphs are learned from view-specific pixels and anchors, while compressed anchor graphs are simultaneously learned from the view-specific anchors. An adaptive weighting scheme is introduced to facilitate the learning of these anchor graphs. To capture high-order correlations, tensor Schatten p-norm regularization is applied to the compressed anchor graphs. A connectivity constraint is introduced to uncover the clustering structures of anchors. Finally, pixel clustering structures are then efficiently revealed from the pseudo-labeled anchors through affinity propagation without requiring additional clustering steps. To solve the proposed formulation, we develop an alternating optimization algorithm. Extensive experiments on three public datasets demonstrate the efficacy and efficiency of the proposed method over state-of-the-art methods.
We demonstrate for the first time that a medical image segmentation model can achieve near fully supervised performance using only a single annotated image and abundant unlabeled data. We present MedSMILE, a novel framework that synergistically integrates transductive and inductive learning for this extreme one-label semi-supervised setting. Its core novelty lies in an iterative loop where a foundation model both bootstraps and refines pseudo-labels for an inductive segmentation model. This process begins with the foundation model performing transductive inference to generate an initial set of pseudo-labels for the unlabeled data pool. This bootstraps an iterative self-training process where the segmentation model is trained and used to generate progressively better labels, with an inter-round refinement step that re-leverages the foundation model to correct errors in uncertain predictions. Experiments on seven datasets across four modalities show MedSMILE recovers 90%–95% of the fully supervised Dice score while decisively outperforming existing semi-supervised techniques that require substantially more annotation. MedSMILE sets a new standard for label-efficient learning in medical image segmentation.
Fairness concerns are increasingly critical as machine learning models are deployed in high-stakes applications. While existing fairness-aware methods typically intervene at the model level, they often suffer from high computational costs, limited scalability, and poor generalization. To address these challenges, we propose a Bayesian data selection framework that ensures fairness by aligning group-specific posterior distributions of model parameters and sample weights with a shared central distribution. Our framework supports flexible alignment via various distributional discrepancy measures, including Wasserstein distance, maximum mean discrepancy, and f-divergence, allowing geometry-aware control without imposing explicit fairness constraints. This data-centric approach mitigates group-specific biases in training data and improves fairness in downstream tasks, with theoretical guarantees. Experiments on benchmark datasets show that our method consistently outperforms existing data selection and model-based fairness methods in both fairness and accuracy.
Continual instruction tuning aims to incrementally adapt large language models to new tasks without forgetting previously acquired knowledge. Existing approaches often struggle to balance plasticity and stability. Replay-based methods retrain on historical data, which raises privacy concerns. Architecture-based methods allocate task-specific components, resulting in significant parameter growth. To address this, we consider a structure-sharing strategy that enables parameter reuse across similar tasks and expands only when necessary, avoiding any data replay. Specifically, we introduce Grow-on-Demand (GoD-MoE), a parameter-efficient framework that is based on sparse and adaptive expert module expansion for continual instruction tuning. GoD-MoE inserts multiple LoRA-based experts into attention layers and dynamically activates a small subset of experts for each task. To avoid redundant parameter growth, we develop an Expert Demand Detector that determines whether new experts are added, facilitating adaptive structural sharing and minimizing parameter overhead. We conduct comprehensive experiments on the TRACE benchmark, demonstrating that GoD-MoE achieves state-of-the-art performance. Furthermore, it effectively mitigates catastrophic forgetting and even outperforms several advanced replay-based baselines.
Enhancing Exploration and Exploitation in Hierarchical Reinforcement Learning with Subgoal Graph Learning
PDF ↗Goal-conditioned hierarchical reinforcement learning has demonstrated effectiveness in addressing complicated decision-making tasks by providing ''temporal extraction'', which decomposes tasks into smaller and more manageable ''subgoals''. This enables agents to plan over a longer time scale. However, achieving optimal exploration and exploitation still remains a challenge, especially for long-horizon or sparse-reward scenarios. In this paper, we introduce Active exploraion and hierarchical Self-Imitation (ASI), an effective scheme to enhance exploration and exploitation based on subgoal representation learning. The key point of ASI is to utilize temporal adjacency information in the representation space. We construct and dynamically update an adjacency graph that captures the relationships between subgoals. Based on the adjacency information provided by the graph, we design two mechanisms: active ``frontier-reaching'' exploration that faster expands the explored area by targeting boundary regions, and hierarchical self-imitation learning that leverages historical experience to facilitate both frontier reaching and policy training. Experimental results show that our method accelerates exploration and outperforms existing baselines in challenging long-horizon continuous control tasks.
Learning to Compress: Unlocking the Potential of Large Language Models for Text Representation
PDF ↗Text representation plays a critical role in tasks like clustering, retrieval, and other downstream applications. With the emergence of large language models (LLMs), there is increasing interest in harnessing their capabilities for this purpose. However, most of the LLMs are inherently causal and optimized for next-token prediction, making them suboptimal for producing holistic representations. To address this, recent studies introduced pretext tasks to adapt LLMs for text representation. Most of these tasks, however, rely on token-level prediction objectives, such as the masked next-token prediction (MNTP) used in LLM2Vec. In this work, we explore the untapped potential of context compression as a pretext task for unsupervised adaptation of LLMs. During compression pre-training, the model learns to generate compact memory tokens, which substitute the whole context for downstream sequence prediction. Experiments demonstrate that a well-designed compression objective can significantly enhance LLM-based text representations, outperforming models trained with token-level pretext tasks. Further improvements through contrastive learning produce a strong representation model (LLM2Comp) that outperforms contemporary LLM-based text encoders on a wide range of tasks while being more sample-efficient, requiring significantly less training data.
Enabling neural networks to learn complex logical constraints and fulfill symbolic reasoning is a critical challenge. Bridging this gap often requires guiding the neural network’s output distribution to move closer to the symbolic constraints. While diffusion models have shown remarkable generative capability across various domains, we employ the powerful architecture to perform neuro-symbolic learning and solve logical puzzles. Our diffusion-based pipeline adopts a two-stage training strategy: the first stage focuses on cultivating basic reasoning abilities, while the second emphasizes systematic learning of logical constraints. To impose hard constraints on neural outputs in the second stage, we formulate the diffusion reasoner as a Markov decision process and innovatively fine-tune it with an improved proximal policy optimization algorithm. We utilize a rule-based reward signal derived from the logical consistency of neural outputs and adopt a flexible strategy to optimize the diffusion reasoner's policy. We evaluate our methodology on some classical symbolic reasoning benchmarks, including Sudoku, Maze, pathfinding and preference learning. Experimental results demonstrate that our approach achieves outstanding accuracy and logical consistency among neural networks.
Image clustering is a fundamental task in unsupervised visual learning. While recent self-supervised methods have explored various pretext tasks to generate supervision signals for clustering, they typically depend exclusively on raw images, resulting in insufficient supervision signals that are inherently constrained by limited visual semantics. In this paper, we propose a novel Semantic-Augmented image Clustering (SAC) method, which transcends the inherent limitations of purely visual representations through the integration of external knowledge. Specifically, SAC utilizes Vision-Language pre-trained Models (VLMs) to flexibly generate textual descriptions for each image, providing external semantic cues to supplement the visual information. By integrating both visual and textual information, SAC achieves image clustering through a multi-modal learning framework. To mitigate the negative impact of inaccurate textual information, SAC designs an uncertainty-driven adaptive weighting mechanism that explores both intra-modal and inter-modal neighborhood structures, and incorporates the adaptive weights into intra-modal and inter-modal contrastive learning, which improves the robustness against noisy image-text correspondences. Experiments on several popular datasets demonstrate the superiority of SAC compared to state-of-the-art methods.
Unifying Channel Independence and Mixing: Multi-Scale Patch Recursion for Global–Local Representation Synergy in Multivariate Time Series Forecasting
PDF ↗Multivariate time series forecasting underpins applications in finance, meteorology, and industrial operations. Yet two persistent hurdles remain: (i) models typically choose between Channel–Independent (CI) and Channel–Mixed (CM) formulations—each with distinct strengths—leading to large performance variance across datasets; and (ii) short-term dynamics and long-term trends are hard to model jointly, making it difficult to capture both transient bursts and periodic patterns. We propose FusionTimePatch (FTP), a purely MLP-driven, lightweight framework composed of three modules: (1) Dual-View Global–Local Fusion (Dual-GLF), which runs CI and CM views in parallel and employs multi-scale patch recursion to adaptively adjust the look-back window, thereby coupling global tendencies with local details; (2) Channel Enhancement (CE), which adaptively identifies and amplifies salient channel signals and diffuses them to others, improving sensitivity to abrupt events and latent drivers; and (3) a Linear Fusion layer, which unifies Dual-GLF and CE outputs to strengthen cross-view interactions and enhance robustness. Extensive experiments on multiple public benchmarks show FTP consistently surpasses state-of-the-art counterparts in both accuracy and efficiency, offering a scalable new paradigm for multichannel forecasting. Code and datasets are publicly available at https://github.com/Zhveh7/FTP.
Recent advances in vision-language models (VLMs) have enabled broad progress in the general medical field. However, pathology still remains a more challenging sub-domain, with current pathology-specific VLMs exhibiting limitations in both diagnostic accuracy and reasoning plausibility. Such shortcomings are largely attributable to the nature of current pathology datasets, which are primarily composed of image–description pairs that lack the depth and structured diagnostic paradigms employed by real-world pathologists. In this study, we leverage pathology textbooks and real-world pathology experts to construct high-quality, reasoning-oriented datasets. Building on this, we introduce Patho-R1, a multimodal RL-based pathology Reasoner, trained through a three-stage pipeline: (1) continued pretraining on 3.5 million image-text pairs for knowledge infusion; (2) supervised fine-tuning on 500k high-quality Chain-of-Thought samples for reasoning incentivizing; (3) reinforcement learning using Group Relative Policy Optimization and Decoupled Clip and Dynamic sAmpling Policy Optimization strategies for multimodal reasoning quality refinement. To further assess the alignment quality of our dataset, we propose Patho-CLIP, trained on the same figure-caption corpus used for continued pretraining. Comprehensive experimental results demonstrate that both Patho-CLIP and Patho-R1 achieve robust performance across a wide range of pathology-related tasks, including zero-shot classification, cross-modal retrieval, Visual Question Answering, and Multiple Choice Question.
Graph Neural Networks (GNNs) perform well on in-distribution data but often fail under out-of-distribution (OOD) shifts due to reliance on spurious patterns. To address this, we propose CauVQ, a causal vector quantization framework that improves OOD generalization by identifying and leveraging invariant substructures that are causally predictive. To construct stable and symbolic graph representations, CauVQ decomposes each input into local substructures and maps them to a discrete codebook of prototypical motifs. This enables consistent and interpretable encoding across diverse graph domains. To isolate the causal substructures, we maximize their mutual information with graph labels and refine their representations using a learnable interaction matrix and a causal attention mechanism. Furthermore, we introduce a counterfactual regularization strategy to enforce prediction stability under substructure perturbations, encouraging the model to focus on truly causal patterns rather than superficial shortcuts. Extensive experiments across standard and OOD benchmarks demonstrate that CauVQ consistently outperforms state-of-the-art baselines in robustness and interpretability. Our framework offers a promising step toward reliable, explainable, and distribution-aware graph learning.
One crucial factor behind the success of deep learning lies in the implicit bias induced by noise inherent in gradient-based training algorithms. Motivated by empirical observations that training with noisy labels improves model generalization, we delve into the underlying mechanisms behind stochastic gradient descent (SGD) with label noise. Focusing on a two-layer over-parameterized linear network, we analyze the learning dynamics of label noise SGD, unveiling a two-phase learning behavior. In Phase I, the magnitudes of model weights progressively diminish, and the model escapes the lazy regime; enters the rich regime. In Phase II, the alignment between model weights and the ground-truth interpolator increases, and the model eventually converges. Our analysis highlights the critical role of label noise in driving the transition from the lazy to the rich regime and minimally explains its empirical success. Furthermore, we extend these insights to Sharpness-Aware Minimization (SAM), showing that the principles governing label noise SGD also apply to broader optimization algorithms. Extensive experiments, conducted under both synthetic and real-world setups, strongly support our theory.
The ability to perform multi-modal multi-hop reasoning by iteratively integrating information across various modalities and external knowledge is critical for addressing complex real-world challenges. However, existing Multi-modal Large Language Models (MLLMs) are predominantly limited to single-step reasoning, as existing benchmarks lack the complexity needed to evaluate and drive multi-hop abilities. To bridge this gap, we introduce MMhops, a novel, large-scale benchmark designed to systematically evaluate and foster multi-modal multi-hop reasoning. MMhops dataset comprises two challenging task formats, Bridging and Comparison, which necessitate that models dynamically construct complex reasoning chains by integrating external knowledge. To tackle the challenges posed by MMhops, we propose MMhops-R1, a novel multi-modal Retrieval-Augmented Generation (mRAG) framework for dynamic reasoning. Our framework utilizes reinforcement learning to optimize the model for autonomously planning reasoning paths, formulating targeted queries, and synthesizing multi-level information. Comprehensive experiments demonstrate that MMhops-R1 significantly outperforms strong baselines on MMhops, highlighting that dynamic planning and multi-modal knowledge integration are crucial for complex reasoning. Moreover, MMhops-R1 demonstrates strong generalization to tasks requiring fixed-hop reasoning, underscoring the robustness of our dynamic planning approach.