History-dependent policies induced by recurrent neural networks (RNNs) rely on latent hidden state dynamics, making verification in partially observable reinforcement learning (RL) challenging. Existing RNN verification tools typically rely on restrictive modeling assumptions or coarse over-approximations of the hidden state space, which can lead to overly conservative or inconclusive results. We propose RNN Probabilistic Verification (RNN-ProVe), a probabilistic framework that estimates the likelihood of undesired behaviors in RNN-based policies. RNN-ProVe uses policy-driven sampling to approximate the set of hidden states that are feasible under a trained policy, and derives statistical error bounds to produce bounded-error, high-confidence estimates of behavioral violations. Experiments on partially observable single-agent and cooperative multi-agent tasks show that RNN-ProVe yields more quantitative, feasibility-aware probabilistic guarantees than existing tools, while scaling to recurrent and multi-agent settings.
论文检索
输入标题、作者或关键词，从 4,015 篇学术成果中精准定位
Modeling inter-channel dependencies is important for multivariate time series forecasting (MTSF). However, in many cases, inter-channel dependencies are time-varying and subject to noise interference, making it difficult for models to find a balance between structural stability and temporal adaptivity. Existing methods either use a single global static structure, resulting in insufficient sensitivity to temporal changes, or use local statistical correlations to construct dependencies, but local correlations are prone to introducing noise, which may further amplify the impact of noise during propagation. To address these issues, we propose a Constraint-Guided Dynamic Graph Network (ConDyGNet), whose core idea is "global basis, dynamic weights". Specifically, ConDyGNet learns a low-rank global basis as a shared structural constraint and generates patch-wise basis mixing weights to construct dynamic propagation graphs. This maintains topological consistency while allowing local adaptation and reducing the influence of local noise. We conducted extensive experiments on eight public benchmark datasets and multiple forecasting horizons, demonstrating that ConDyGNet can learn more robust time-varying inter-channel dependencies and achieve state-of-the-art forecasting accuracy. The code is available at https://github.com/constli67/ConDyGNet.
Machine unlearning (MUL) aims to remove the influence of specific data from a trained model for data privacy and model adaptability. Existing MUL methods mostly assume the internal parameters and the training data of the target model are accessible. Nevertheless, in most practical scenarios, the model provider (MP) and the service operator (SO) are different entities with unequal model access privileges. The MP provides the model, while the SO can only access the model via APIs when handling unlearning requests. Under such an asymmetric access constraint, we propose One-Turn Knockout (OTK), a novel traceable and editable MUL framework based on a model-agnostic and editable proxy. Specifically, OTK first compresses the representation space of the target model into a discrete proxy based on codebook, with merely one pass post-training. Each data sample is recorded in the proxy space as a distribution over the codebook tokens, and its contribution to the model prediction can be cumulatively estimated via additive token statistics. Based on the traceable and editable proxy, the SO can instantly handle unlearning requests by (i) estimating the token distribution of the forgotten data, (ii) identifying the causal tokens, and (iii) erasing their contributions without the access to the model parameters and training data. Extensive experiments on multiple datasets and tasks show that OTK consistently outperforms state-of-the-art unlearning methods.
Prototype-based federated learning enables efficient knowledge sharing by exchanging class prototypes rather than full model parameters. However, heterogeneous client data and limited local samples increase prototype estimation variance, making many client prototypes unreliable. Existing methods usually treat prototypes as deterministic point estimates and cannot quantify their reliability, which may contaminate global prototypes and cause negative transfer. To address these challenges, we propose FedUP, an uncertainty-aware personalized federated learning framework that models prototypes as probability distributions. FedUP captures both aleatoric and epistemic uncertainty on a probabilistic simplex to guide local training and global aggregation. It further uses global probabilistic prototypes as class-conditional priors for feature augmentation, alleviating client-side data sparsity. Finally, FedUP aggregates prototype distributions through reliability-informed barycenters on the statistical manifold, suppressing unreliable contributions while preserving geometric structure. Experiments on natural and medical benchmarks demonstrate that FedUP consistently outperforms state-of-the-art methods.
The deployment of Vision-Language Models (VLMs) faces memory and computational bottlenecks because of the massive parameters and intensive computations. While Post-Training Quantization (PTQ) can reduce these costs, existing methods often overlook the heterogeneity of multimodal input when applied to VLMs, leading to quantization accuracy degradation. In this paper, we categorize the Transformer linear layers into Expansion Space (responsible for feature expansion) and Projection Space (responsible for feature aggregation) and reveal a cross-modal structural sensitivity asymmetry in VLMs: The Expansion Space is more sensitive to quantization accuracy than the Projection Space in both LLM and ViT encoders. Based on this, we propose SeGO, a unified structural sensitivity-aware sparse optimization framework. First, it constructs search interval for scaling factors using channel-wise statistics of LLM and ViT weights to exclude invalid solutions. Then it applies scaling protection only to the sensitive Expansion Space while directly quantizing the robust Projection Space. Moreover, SeGO uses a Golden-Section Solver to speedup the search of optimal scaling factors. Experiments show that SeGO achieves the balance among model parameter amount, quantization accuracy and scaling factors' search efficiency on InternVL2 and LLaVA series. Under the W3/W4A16 configuration, SeGO improves the accuracy of 7B-26B models by 3.8%-17.3% and enhances calibration efficiency by dozens of times.
Current mainstream research in multivariate time series (MTS) forecasting often assumes that all data are static. However, real-world MTS data typically arrives continuously in a streaming manner, which we refer to as streaming MTS. The statistical characteristics and spatiotemporal graph topology of these data evolve over time, presenting two key challenges: the model's ability to adapt to new data distributions and the enhancement of cross-domain generalization capabilities. In this paper, we propose a streaming MTS prediction framework. We begin by designing a lightweight spatiotemporal causal learning model that captures generalizable causal spatiotemporal features from a decoupling perspective. Next, we introduce a framework to enhance the model's streaming learning capability, leveraging the adaptability of continual learning while strengthening cross-domain representation abilities. Specifically, we reformulate continual learning as a multi-task learning problem and present a multi-task optimization algorithm that identifies a set of Pareto-optimal solutions to address the inherent stability-plasticity dilemma in continual learning. Finally, we propose a topology-aware feature propagation strategy that disseminates well-trained node embedding features to unseen graph structures, thereby improving the model's cross-domain generalization. Results on real-world datasets demonstrate that our model achieves superior forecasting performance while substantially improving computational efficiency and memory usage.
TD(λ) in value-based MARL algorithms or the Temporal Difference critic learning in Actor-Critic-based (AC-based) algorithms synergistically integrate elements from Monte-Carlo simulation and Q function bootstrapping via dynamic programming, which effectively addresses the inherent bias-variance trade-off in value estimation. Based on that, some recent works link the adaptive λ value to the policy distribution in the single-agent reinforcement learning area. However, because of the large joint action space from multiple agents and the limited transition data in Multi-agent Reinforcement Learning, the policy distribution is infeasible to calculate statistically. To solve the policy distribution calculation problem in MARL settings, we employ a parametric likelihood-free density ratio estimator with two replay buffers instead of calculating statistically. The two replay buffers of different sizes respectively store the historical trajectories that represent the data distribution of the past and current policies. Based on the estimator, we assign Adaptive TD(λ), ATD(λ), values to state-action pairs based on their likelihood under the stationary distribution of the current policy. We apply the proposed method on two competitive baseline methods, QMIX for value-based algorithms, and MAPPO for AC-based algorithms, over SMAC benchmarks and Gfootball academy scenarios, and demonstrate consistently competitive or superior performance compared to other baseline approaches with static λ values.
In the field of skeleton-based human action recognition, Graph Convolutional Networks (GCNs) have become a dominant framework. However, existing GCN-based approaches often treat the sequences of two-person interaction as separate entities, ignoring the inherent semantic dependencies and spatial correlations between interacting subjects. Furthermore, high-order skeleton representations naturally exhibit non-Euclidean structures, where Euclidean deep learning models are inherently limited in explicitly capturing and preserving such geometric information. As a countermeasure, we propose a Riemannian Graph Convolutional Network (RGCN) that operates on the Symmetric Positive Definite (SPD) manifolds. Specifically, we model high-order skeletal statistics via Gaussian embedding and propose a Riemannian network to capture inter-subject interactions and global correlations. The proposed RGCN is instantiated under three SPD geometries, and its effectiveness is validated through extensive experiments on three interaction benchmarks. Extensive experimental results show that RGCN provides a competitive and geometrically grounded alternative for skeleton-based interaction recognition.
Test-Time Adaptation (TTA) aims to adapt pretrained models to unseen test data, which is crucial for resource-constrained edge devices that must handle distribution shifts on the fly without human supervision. However, conventional TTA methods often fail in realistic scenarios characterized by continuous shifts and severe class imbalances while incurring prohibitive memory overheads. To enable continuous adaptation to test data on edge devices under a realistic TTA setting, we propose a Bias-Resistant Online Statistical Alignment (BOSA) method. BOSA facilitates unbiased adaptation via a discrepancy-aware statistical alignment mechanism integrated with a class-balanced memory bank. To ensure memory efficiency, we further design a saliency-guided activation sparsification and gradient reconstruction scheme, which drastically reduces memory overhead without sacrificing gradient integrity. Extensive evaluations demonstrate that BOSA achieves superior accuracy with a compact memory consumption compared to state-of-the-art methods under realistic TTA settings.
Predicting responses to genetic perturbation is pivotal for elucidating gene regulatory machinery. However, existing methods often rely on statistical perspectives to model differential expression, overlooking the constraints of the underlying molecular interactome, which renders predictions susceptible to spurious correlations. Based on the fact that a genetic perturbation is a molecular stimulus acting through functional connectivity to reconfigure cellular expression profiles, we propose PertDCR, a framework for context-aware Perturbation response prediction via Distance-Constrained Refinement. Specifically, PertDCR addresses the heterogeneity of perturbation effects by contextualizing the perturbation source with relevant gene programs inferred from the protein-protein interaction network as well as cell representation. To activate biologically valid responses, PertDCR predicts the distance between the perturbation source and highly responsive genes within the PPI network, and dynamically modulates the response intensity based on distance, thereby facilitating accurate perturbation prediction. Extensive experiments demonstrate that PertDCR achieves state-of-the-art performance across diverse unseen genetic perturbations, and the predictions are consistent with underlying biological mechanisms.
Federated Learning (FL) enables distributed learning across multiple clients without sharing raw data. When statistical heterogeneity across clients is severe, Clustered Federated Learning (CFL) can improve performance by grouping similar clients and training cluster-wise models. However, most CFL approaches rely on multiple communication rounds for cluster estimation and model updates, which limits their practicality under tight constraints on communication rounds. We propose Data Collaboration-based Clustered Federated Learning (DC-CFL), a single-round framework that completes both client clustering and cluster-wise learning, using only the information shared in DC analysis. DC-CFL quantifies inter-client similarity via total variation distance between label distributions, estimates clusters using hierarchical clustering, and performs cluster-wise learning via DC analysis. Experiments on multiple open datasets under representative non-IID conditions show that DC-CFL achieves accuracy comparable to multi-round baselines while requiring only one communication round. These results indicate that DC-CFL is a practical alternative for collaborative AI model development when multiple communication rounds are impractical. Our source code is publicly available at https://github.com/soutasuga/DC-CFL.
With the rising demand for trustworthy AI in clinical practice, strong interpretability is now a critical requirement as well as accuracy. However, the modality gap for medical visual question answering is quite severe when continuous visual signals are forcibly projected into discrete text space for reasoning, and the loss of necessary diagnostic information leads to low precision and black-box opacity. To address this problem, we propose MedVCoT, which incorporates latent visual reasoning into the medical visual question answering(VQA) domain. Rather than merely integrating modules, MedVCoT utilizes the specialized expertise of MedSAM to train a large vision-language model so that it can autonomously generate consistent and continuous latent visual tokens within Visual Chain-of-Thought. This mechanism forces the model to explicitly "see" the lesion in the latent space before formulating a textual diagnosis, ensuring answers are causally rooted in verifiable visual evidence rather than statistical hallucination. We achieve this through a progressive 3-stage training procedure: medical feature alignment, visual reasoning learning by utilizing latent tokens generated, and instruction tuning for complex clinical scenarios. Extensive experiments show that MedVCoT can achieve state-of-the-art performance on multiple benchmarks, outperforming other methods by large margins. Meanwhile, it provides pixel-level segmentation masks to validate its diagnostic reasoning. Our demo is available at https://zhuqh19.github.io/MedVCoT.
Graph self-supervised learning (SSL) typically relies on large-scale unlabeled datasets, heavily inflating computational costs. However, empirical evidence suggests that these datasets contain substantial redundancy—our analysis reveals that uniformly subsampling 50% of graphs retains over 96% of downstream performance. To exploit this redundancy, we introduce GraphSculptor for pre-training coreset construction. Unlike methods dependent on additional training-time signals or limited solely to topological statistics, GraphSculptor provides a label-free solution that constructs coresets via two complementary perspectives: intrinsic structure and contextual semantics. Concretely, structural diversity is quantified using intrinsic graph statistics, yielding a structural feature vector for each graph, while semantic diversity is captured by utilizing a pre-trained language model to encode descriptions generated via graph-to-text. GraphSculptor integrates these signals into a unified metric space and performs cluster-aware selection to preserve joint structural--semantic diversity. We further derive a theoretical bound on the loss gap between coreset and full-data pre-training, offering theoretical motivation for our selection formulation. Extensive experiments demonstrate that GraphSculptor effectively "sculpts" the dataset: a 10% coreset achieves 99.6% of full-data performance while reducing pre-training time by nearly 90%, offering a scalable solution for data-efficient graph pre-training.
Clustering is fundamental to scRNA-seq analysis, serving as a cornerstone for identifying cell populations and resolving tissue heterogeneity. However, existing methods focus on mining numerical statistical patterns, suffering from semantic agnosticism by neglecting the intrinsic biological functions encoded by genes. While Large Language Models (LLMs) offer promising semantic capabilities, their direct adaptation to cell clustering is hindered by the structural mismatch between generative pre-training objectives and discriminative downstream tasks. To bridge this gap, we propose scLLM-DSC, a novel LLM-Knowledge Enhanced Cross-Modal Deep Structural Clustering framework. Diverging from data-driven paradigms, scLLM-DSC establishes a semantically-grounded representation by synergizing two views: a Knowledge-Driven Semantic View derived from NCBI gene priors and contextualized Cell2Sentence embeddings, and a Structure-Aware Topological View extracted via a graph-guided encoder. Crucially, we introduce a cross-modal contrastive alignment mechanism to enforce consistency between biological semantics and transcriptomic features within a unified latent space. Extensive benchmarks demonstrate that scLLM-DSC significantly outperforms eleven state-of-the-art baselines in clustering accuracy.
Inductive Logic Programming (ILP) learns interpretable logical rules from data. Existing methods are transductive: their learned parameters are bound to specific predicates and require retraining for each new task. We introduce Neural Rule Inducer (NRI), a pretrained model for zero-shot rule induction. Rather than encoding literal identities, NRI represents literals using domain-agnostic statistical properties such as class-conditional rates, entropy, and co-occurrence, which generalize across variable identities and counts without retraining. The model consists of a statistical encoder and a parallel slot-based decoder. Parallel decoding preserves the permutation invariance of logical disjunction; an autoregressive decoder would instead impose an arbitrary clause order. Product T-norm relaxation makes rule execution differentiable, allowing end-to-end training on prediction accuracy alone. We evaluate NRI on rule recovery, robustness to label noise and spurious correlations, and zero-shot transfer to real-world benchmarks, and we believe this work opens up the possibility of foundation models for symbolic reasoning. Code and the reference checkpoint are available at https://github.com/phuayj/neural-rule-inducer. An extended version with full appendices is available at https://arxiv.org/abs/2605.04916.
Federated learning (FL) enables privacy-preserving video human activity recognition without centralizing data. Despite its potential, FL remains fundamentally constrained by the high communication overhead incurred during training. Existing methods, such as model quantization, gradient sparsification and low-rank approximation, aim to mitigate this overhead but often at the cost of model expressivity, leading to reduced classification accuracy. In this work, we take a representation-centric perspective and show that for video-base activity recognition using pretrained embeddings, class-discriminative information lies in a very low-dimensional subspace, that preserves linear seperability between activity classes. Motivated by this observation, we propose Federated discriminative subspace discovery, a framework that collaboratively identify and operate within such a subspace. Instead of communicating full classifier updates, each client first projects its local video embeddings using a shared random projection matrix. It then computes the covariance of the projected embeddings and transmits this statistic to the server for aggregation. The server reconstructs a global covariance matrix, performs singular value decomposition, and selects the top-k eigenvectors that define the global class-discriminative subspace. Subsequent communication occurs only in this compact subspace. Extensive experiments on UCF101, HMDB51, and Toyota-SmartHome demonstrate that, learning and sharing the classifier in the discovered subspace, reduces communication costs by up to 61%, with a moderate drop in activity recognition accuracy compared to the full model.
Batch selection is crucial for improving both training efficiency and predictive performance in deep multi-label classification (MLC). Existing batch selection methods typically rely on a single metric to assess instance importance and use static label weights to distinguish label significance, neglecting the dynamic evolution of metric utility and label significance during training. In addition, the method that explicitly exploits label correlations is largely affected by abundant irrelevant labels and insensitive to local label distributions. To address these issues, we propose D2ACE, a novel multi-label batch selection method guided by Dual Dynamics and Adaptive Correlation Enhancement. D2ACE explicitly captures metric and label-level training dynamics by combining stage-wise Bernoulli mixture sampling, which balances uncertainty and noise-resistant hardness, with dynamic label weighting to recalibrate label priorities at each epoch based on current metric statistics. Furthermore, D2ACE introduces a local context-aware correlation enhancement to focus on relevant labels with instance-adaptive dependencies. Extensive experiments on tabular and image benchmarks demonstrate that D2ACE outperforms existing batch selection approaches across various deep MLC models, achieving stronger predictive performance and more efficient correlation modeling.
Few-shot learning aims to recognize novel categories from limited labeled samples, where prototypes estimated from 1--5 supports per class are often unreliable. Semantic-based approaches alleviate this by introducing class-level priors, but they often ignore instance-level cues and rarely optimize queries under the inductive protocol. We propose PMCE, a Probabilistic framework that leverages Multi-granularity semantics with Caption-guided Enhancement for few-shot classification. On base classes, we build a knowledge bank with class-wise visual statistics and class-name embeddings. At test time, the semantic embedding of a novel class retrieves a few similar base classes whose visual priors are aggregated into a class-specific prior and combined with the support-based prototype via MAP estimation. Simultaneously, we train a lightweight enhancer on base classes that fuses frozen BLIP captions with visual features, and apply it to both supports and queries without using query-set statistics or novel labels. A simple caption-consistency regularizer further improves robustness to noisy captions. Experiments on four standard benchmarks with ResNet-12 and Swin-T backbones show that PMCE outperforms state-of-the-art few-shot baselines, achieving up to 7.71% gains over the strongest competitor on MiniImageNet in the challenging 1-shot setting. Our code is available at https://github.com/channa419/PMCE.
Language models are powerful artifacts, yet their factual knowledge is still poorly understood, and inaccessible to ad-hoc browsing and scalable statistical analysis. This demonstration introduces GPTKB v1.5, a densely interlinked 100-million-triple knowledge base (KB) built for $14,000 from GPT-4.1, using the GPTKB methodology for massive-recursive LLM knowledge materialization. This demo focuses on three use cases: (1) link-traversal-based LLM knowledge exploration, (2) SPARQL-based structured LLM knowledge querying, (3) comparative exploration of the strengths and weaknesses of LLM knowledge. Massive-recursive LLM knowledge materialization is a groundbreaking opportunity both for the systematic analysis of LLM knowledge, as well as for automated KB construction.
Spatiotemporal Transformers with Multiple Instance Learning for Label-Efficient Behavioral Analysis in Autism (Student Abstract)
PDF ↗The identification of unique traits and behavior is essential to providing personalized intervention in individuals with Autism Spectrum Disorder. However, the limited personalized quantitative data with experts' annotations in autism research pose a fundamental challenge to train AI models for unique behavioral patten discovery. Multiple Instance Learning (MIL) has demonstrated promising results in medical domains, where annotations are only needed at the group level (i.e., a whole sequence) instead of individual data instances. It provides a cost-effective way to train statistical models with limited labeled data. Additionally, the rise of pretrained models have shown great success in improving the performance in few-shot learning scenarios. In this proof-of-concept study, we propose a novel framework that integrates a transformer encoder pre-trained on large-scale spatiotemporal data with MIL, for unique behavioral pattern detection from autistic individuals. Our results demonstrated the discrimination of individual-level autistic behavioral differences and the accurate classification of behaviors across distinct groups: typically developing (TD) and autistic (ASD). Beyond aggregate performance metrics, we highlight visual insights from temporal instance scores, revealing interpretable differences between individuals in their respective groups. These results show promising progress towards tools that can be used for personalized intervention for autistic individuals, and more interpretable AI diagnostics.