Deep multi-view clustering draws plentiful attention in various domains, owing to remarkable performance in learning patterns from complementary information of multi-view data. However, previous methods encounter two challenges. They utilize a single pre-defined clustering strategy to perceive diverse structures from data in multiple views subject to heterogeneous distributions, failing to fully capture intricate complementary structures. They leverage either the feature fusion or the result fusion in clustering, which cannot fully integrate complementary information. Therefore, a decoupled multi-agent actor-critic (PRIME) is proposed via defining multi-view clustering as a partially observable Markov game, which establishes a dynamic trial-and-error assignment process of samples in a decentralized perception with centralized learning framework to adaptively learn the optimal clustering strategy. In PRIME, an actor leverages the policy gradient paradigm to independently implement a Markov decision process of data partition in a view, which fully explores data structures to tailor a clustering sub-policy for a view. Meanwhile, a critic utilizes the value function paradigm to centrally guide the Markov game among actors in different views, which constructs both feature and result fusion to progressively enhance complementary knowledge integration for robust clustering results. Extensive experiments on 6 benchmark datasets verify the superiority of PRIME against 10 methods.
论文检索
输入标题、作者或关键词，从 15,207 篇学术成果中精准定位
Reliable reasoning in Large Language Models (LLMs) is challenged by their propensity for hallucination. While augmenting LLMs with Knowledge Graphs (KGs) improves factual accuracy, existing KG-augmented methods fail to quantify epistemic uncertainty in both the retrieved evidence and LLMs' reasoning. To bridge this gap, we introduce DoublyCal, a framework built on a novel double‑calibration principle. DoublyCal employs a lightweight proxy model to first generate KG evidence alongside a calibrated evidence confidence. This calibrated supporting evidence then guides a black-box LLM, yielding final predictions that are not only more accurate but also well-calibrated, with confidence scores traceable to the uncertainty of the supporting evidence. Experiments on knowledge-intensive benchmarks show that DoublyCal significantly improves both the accuracy and confidence calibration of black-box LLMs while maintaining low token cost.
Reward specification plays a central role in reinforcement learning (RL), guiding the agent’s behavior. To express non-Markovian rewards, formalisms such as reward machines have been introduced to capture dependencies on histories. However, traditional reward machines lack the ability to model precise timing constraints, limiting their use in time-sensitive applications. In this paper, we propose timed reward machines (TRMs), which are an extension of reward machines that incorporate timing constraints into the reward structure. TRMs enable more expressive specifications with tunable reward logic, for example, imposing costs for delays and granting rewards for timely actions. We study model-free RL frameworks (i.e., tabular Q-learning) for learning optimal policies with TRMs under digital and real-time semantics. Our algorithms integrate the TRM into learning via abstractions of timed automata and employ counterfactual-imagining heuristics that exploit the TRM's structure to improve search. Experimentally, we demonstrate that our algorithm learns policies that achieve high rewards while satisfying the timing constraints specified by the TRM on popular RL benchmarks.
Multimodal Large Language Models (MLLMs) perform strongly in high-resource languages, yet often produce fluent but culturally "thin" descriptions in low-resource settings. We argue that this failure is not merely a linguistic limitation: culture-specific visual knowledge depends on native visual-textual alignments that translation-centric pipelines rarely provide. We present MELLA, a multimodal dataset across eight low-resource languages, designed to jointly support linguistic fluency and cultural groundedness. MELLA uses a dual-source strategy that combines native web image-alt-text pairs for culture-grounded supervision with generated-and-translated image descriptions for linguistically rich supervision, explicitly separating two learning signals often conflated in multilingual multimodal data. Through controlled diagnostic fine-tuning on multiple MLLM backbones, we show that MELLA mitigates cultural hallucination by helping models recognize and articulate culturally specific entities overlooked by translation-based adaptation. Our findings highlight data alignment, rather than model modification alone, as a key path toward culturally grounded multimodal understanding in low-resource languages.
Bender Decomposition is a well-known solving technique in Operation Research that decomposes a problem into a master and a subproblem, which interact via “cuts". This technique has been extended to Logic-Based Bender Decomposition (LBBD), solving problems specified by logic-based languages and enabling a wider applicability. However, while Bender Decomposition guarantees optimality, LBBD does not: this property is problem-specific and depends on the defined decomposition and cuts. In this paper, we present a theoretical analysis of the conditions under which LBBD, including cuts, can preserve optimality in the context of Answer Set Programming (ASP), a prominent logic-based language in the field of Artificial Intelligence. We also introduce a general-purpose algorithm that employs both minimal unsatisfiable subsets and minimal correction subsets to define cuts in a fully automated, problem-independent way. The algorithm preserves the optimality guarantees of Bender Decomposition. An empirical evaluation on real-world scheduling instances shows that our approach can find significantly more solutions, and more optimal ones, compared to a standard direct ASP encoding, while also consistently reducing the execution time.
Existential rules are a prominent formalism to enrich a database with knowledge from the domain of interest, but make even basic reasoning tasks on the resulting knowledge base undecidable. To circumvent this, several classes of rules offering various useful properties have been identified. One such class, for instance, contains all sets of rules on which the chase algorithm always terminates, which guarantees the existence of a finite universal model. However, these classes are often abstract rather than concrete: it may be undecidable to check whether a given set of rules belongs to them. Given that the most studied classes of existential rules are designed for reasoning on databases, thus ensuring decidable conjunctive query entailment, we ask: Within a class that supports decidable query entailment, do the usual abstract classes become concrete? We answer in the negative for classes based upon the termination of all classical chase variants and for the bts class.
Knowledge concept tagging aims to assign specific concept or topic labels to educational content, which is essential for both educators and learners in traditional and online teaching practices. Recent work has explored large language models (LLMs) for this task, achieving promising performance. However, LLMs still struggle to select the correct concept from a large-scale candidate set due to the high dimensionality of the decision space. In this paper, we propose a novel three-stage Select-Reason-Judge (SRJudge) framework, which empowers LLMs with selective reasoning capability for fine-grained knowledge concept tagging. Specifically, the Selector in Stage 1 first narrows the candidate concepts to a top-K shortlist by fine-tuning a small language model (SLM), e.g., BERT, since the top-K predictions hit the correct concept in most cases, thereby reducing the decision space of correct candidates. Next, the Stage 2 Reasoner employs a lightweight LLM for refined reasoning over the shortlisted candidates. It further integrates an improved reinforcement learning strategy with a dynamic task-specific reward function and a pruning mechanism to better align with human reasoning preferences. Finally, a larger LLM acts as a judger that evaluates the overall rationality of the reasoning process and its explanations to determine the final output. In addition, we construct two high-quality datasets for further validation, i.e., the biology dataset S_Bio and the physics dataset S_Phy. Experimental results demonstrate that our method consistently outperforms state-of-the-art baselines across benchmark datasets, verifying its effectiveness and superiority. Resources are available at: https://github.com/Nicozwy/SRJudge.
Progression, the task of updating a knowledge base to reflect action effects, generally requires second-order logic. Identifying first-order special cases, by restricting either the knowledge base or action effects, has long been a central topic in reasoning about actions. It is known that local-effect, normal, and acyclic actions, three increasingly expressive classes, admit first-order progression. However, a systematic analysis of the size of such progressions, crucial for practical applications, has been missing. In this paper, using the framework of Situation Calculus, we show that under reasonable assumptions, first-order progression for these action classes grows only polynomially. Moreover, we show that when the KB belongs to decidable fragments such as two-variable first-order logic or universal theories with constants, the progression remains within the same fragment, ensuring decidability and practical applicability.
Join ordering is the NP-hard problem of selecting the most efficient order in which to evaluate joins (conjunctive, binary operators) in a database query. Because query execution performance critically depends on this choice, join ordering lies at the core of query optimization. Traditional approaches cast this problem as a discrete combinatorial search over binary trees guided by a cost model, but they have trade-offs between effectiveness and efficiency. We show that when the cost model is differentiable, query plans can be continuously relaxed into a soft adjacency matrix that represents a superposition of plans. This continuous relaxation, combined with differentiable constraints that enforce plan validity, enables a gradient-based search for low-cost plans within this relaxed space. Using a Graph Neural Network as the cost model, we demonstrate that this gradient-based approach can find comparable and even lower-cost plans compared to traditional discrete search methods on two different graph datasets. Furthermore, we empirically show that the runtime of this approach scales better than discrete search algorithms. We believe this first step towards gradient-based join ordering can lead to more effective and efficient query optimizers in the future.
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.
Inductive knowledge graph reasoning (IKGR) requires generalization to entities and relation types not seen during training. We introduce Knowledge Graph Wave Networks (KGWN), an IKGR approach that learns adaptive per-relation wave operators to control relation-dependent propagation, along with velocity normalization ensuring stability at any propagation depth. Experiments demonstrate state-of-the-art results on inductive benchmarks and competitive transductive performance.
Infrared and visible image fusion (IVF) encounters two challenges: 1) image unregistered, where parallax leads to blurred fusion results, and 2) adverse imaging conditions, which introduces outlier data (such as haze) that significantly degrade image registered and fusion performance. Existing IVF methods fail to account for the joint impact of unregistered and haze factor, often neglecting these challenges or addressing them in isolation. However, unregistered and haze are intrinsically coupled in fusion task. For example, haze can obscure structural details, leading to inaccurate registration and ultimately degrading fusion performance. To address the intrinsic coupling between unregistered and haze, we propose a progressive task-cooperative processing pipeline—dehazing, registration, and fusion—to achieve robust fusion of unregistered images under hazy conditions. To mitigate the challenges posed by architectural complexity and excessive parameter overhead in task progressive learning, we propose a lightweight model approximation paradigm through hierarchical knowledge distillation. The framework employs a stage-wise distillation optimization strategy that synergistically integrates: 1) primary task-specific distillation for modality-aware feature extraction, and 2) progressive task-cooperative distillation for fusion-oriented representation learning, which can improve fusion robustness for unregistered multi-modal inputs in hazy conditions. Extensive experiments demonstrate that our method achieves significantly superior performance compared to the State-Of-The-Art (SOTA) methods.
Empowering Precise Embodied Agents with Executable Analytic Concepts as Semantic-Physical Blueprints
A core challenge for embodied agents is the ``semantic-to-physical gap"—the difficulty of mapping symbolic reasoning to precise execution. While Vision-Language Models (VLMs) enhance agent task planning, they often fail in problem classes requiring accurate alignment between functional geometry and physical constraints, such as articulated object manipulation or precision assembly. To address these challenges, we propose GRACE, an agent framework that adopts Executable Analytic Concepts (EAC) as a core knowledge annotation paradigm for object understanding. Under this paradigm, the agent does not merely perceive objects as unstructured visual data; instead, it interprets and annotates them as ``Semantic-Physical Blueprints", which provide a structured cognitive representation that encodes geometric primitives, mechanical affordances, and manipulation constraints. Central to our framework is a policy scaffolding mechanism, which allows the agent to dynamically ground VLM-based insights into these instantiated blueprints. This enables the agent to model and resolve complex decision-making tasks involving parameterized object descriptions and constrained motion planning. Experimental results demonstrate that agents utilizing this paradigm achieve high robustness in complex manipulation tasks. Furthermore, we demonstrate that GRACE supports automated concept discovery, offering a scalable and modular solution for high-precision embodied intelligence.
Driven by privacy regulations, federated unlearning (FU) aims to remove the influence of specific clients or samples from a trained federated model, approximating the behavior of retraining from scratch without the target data. However, existing FU methods are largely reactive: retraining-based solutions are accurate but prohibitively expensive, while parameter-based approaches are more efficient yet may cause irreversible knowledge damage and catastrophic forgetting. We introduce PFU-SKLA, a proactive FU framework that endows models with built-in forgettability. During pretraining, we perform Orthogonality-guided Representation Disentanglement (ORD) to learn a robust, disentangled feature space that reduces cross-client/class interference. Additionally, we use Dynamic Sensitivity-based Key Layer Identification (DS-KLI) to identify sensitive layers that hold target knowledge. During unlearning, we propose a sparse, lightweight adaptation strategy that precisely erases target knowledge by inserting sparse adapters into the identified critical layers while preserving non-target knowledge by freezing the backbone. Extensive experiments across multiple datasets and three standard unlearning settings show that PFU-SKLA consistently approaches retraining-from-scratch performance, while substantially reducing communication and computation costs compared to state-of-the-art (SOTA) FU methods.
Process Reward Models (PRMs) supervise intermediate reasoning steps in large language models (LLMs), but existing PRMs are mainly trained on general-domain data and struggle with the structured, symbolic, and fact-sensitive nature of financial reasoning. Financial tasks require not only correct final answers but also verifiable intermediate steps grounded in domain knowledge. In this paper, we propose Fin-PRM, a domain-specialized, trajectory-aware PRM for financial reasoning that jointly models step-level correctness and trajectory-level coherence, producing binary supervision signals for both local and global reasoning quality. To support reliable supervision, we construct a high-quality financial reasoning dataset of 3K trajectories, where step- and trajectory-level labels are automatically derived from multi-source reward signals, including Monte Carlo rollouts, LLM-based evaluation, and explicit financial knowledge verification. Fin-PRM defines a unified ranking score that integrates step- and trajectory-level rewards, enabling consistent use across multiple settings. We evaluate Fin-PRM in three scenarios: (1) offline trajectory selection for supervised fine-tuning, (2) reward-guided Best-of-N inference for test-time scaling, and (3) process-aware reward shaping for reinforcement learning. Experiments on financial reasoning benchmarks, including CFLUE and FinQA, show that Fin-PRM consistently outperforms general-purpose PRMs and strong baselines. Our project resources will be available at https://github.com/aliyun/qwen-dianjin.
Fair dynamic graph embedding is crucial for real-world systems, such as recommendation and social networks. Prior studies impose a single-axis fairness formulation, treating attribute and structural bias as separable artifacts. This overlooks their coupling relationship, under which debiasing along one axis can induce cross-axis amplification. This coupling further introduces opposing gradient constraints under joint optimization, leading to optimization conflicts. Furthermore, the evolution of dynamic graphs causes shifts in bias distribution, leading to unstable optimization and exacerbating these conflicts. To address these issues, we propose FairTCD, a Fair Dual-Teacher Temporal Contrastive Distillation framework. FairTCD employs two adversarial fairness teachers to decouple attribute and structural fairness representations. To reconcile dynamic conflicts between two fairness objectives, we introduce a temporal contrastive distillation to induce consistency between attribute and structural fairness representations across time while retaining temporal semantics. A unified student model distills complementary knowledge from both teachers to achieve twofold fairness. Experiments on three real-world benchmarks demonstrate that FairTCD preserves performance while improving twofold fairness metrics by at least 4.53%.
Reward models (RMs) play a pivotal role in aligning large language models (LLMs) with human preferences. Due to the difficulty of obtaining high-quality human preference annotations, distilling preferences from generative LLMs has emerged as a standard practice. However, existing approaches predominantly treat teacher models as simple binary annotators, failing to fully exploit the rich knowledge and capabilities for RM distillation. To address this, we propose RM-Distiller, a framework designed to systematically exploit the multifaceted capabilities of teacher LLMs: (1) Refinement capability, which synthesizes highly correlated response pairs to create fine-grained and contrastive signals. (2) Scoring capability, which guides the RM in capturing precise preference strength via a margin-aware optimization objective. (3) Generation capability, which incorporates the teacher's generative distribution to regularize the RM to preserve its fundamental linguistic knowledge. Extensive experiments demonstrate that RM-Distiller significantly outperforms traditional distillation methods both on RM benchmarks and reinforcement learning-based alignment, proving that exploiting multifaceted teacher capabilities is critical for effective reward modeling. To the best of our knowledge, this is the first systematic research on RM distillation from generative LLMs.
Recent personalized federated learning research focuses on heterogeneous models across clients. However, existing methods often rely on external data, model decoupling, and partial learning, which makes them sensitive to settings. In contrast, we revisit hypernetworks and leverage their strong generalization ability to propose the first practical method for personalized federated learning. We first propose a model heterogeneous personalized federated learning framework based on hypernetworks, MH-pFedHN, which quantifies clients with different architectures using customized embedding vectors and then generates client-specific model parameters through a server-side hypernetwork. Besides the shared feature extractor, our hypernetwork consists of multiple heads, where clients with similar numbers of parameters are assigned the same number of customized embedding vectors and consequently share the same head. This design enables knowledge sharing across different architectures and reduces the computation of parameter generation. To further enhance the hypernetwork’s learning and generalization, we propose MH-pFedHNGD, which introduces a lightweight yet effective plug-in global model. Our framework requires no external data and does not disclose client model architectures, thereby effectively ensuring security and demonstrating great potential. Experiments across various models and tasks demonstrate that our approach outperforms standard baselines and exhibits strong generalization performance. Our code is available at https://github.com/DangDang1895/MH-pFL
Learning universal representations for time series is fundamental for diverse downstream tasks. However, current approaches largely rely on handcrafted data augmentations, which may distort intrinsic temporal dynamics and structural regularities. In addition, most static representation learning frameworks struggle to cope with the non-stationary nature of real-world time series. To address these issues, we propose Heterogeneous Hypergraph Structure-aware Contrastive Adaptive Network (H²SCAN), a novel augmentation-free framework that derives contrastive supervision directly from graph topology. Specifically, H²SCAN constructs a heterogeneous hypergraph with three node types to capture multi-scale temporal characteristics. Building upon this representation, a meta-adaptation network is introduced to dynamically reweight heterogeneous hyperedges, enabling the model to adapt to distribution shifts in real-time. Finally, a structure-aware contrastive learning objective is employed to align latent representation similarity with the intrinsic hypergraph topology. Experiments on multiple benchmarks and cloud Kafka cluster datasets demonstrate that H²SCAN outperforms existing methods by modeling high-order multi-domain dependencies and preserving the semantic integrity of time series data.
Evaluating LLM forecasting capabilities is constrained by a fundamental tension: prospective evaluation offers methodological rigor but prohibitive latency, while retrospective forecasting (RF)—evaluating on already-resolved events—faces rapidly shrinking clean evaluation data as SOTA models possess increasingly recent knowledge cutoffs. Simulated Ignorance (SI), prompting models to suppress pre-cutoff knowledge, has emerged as a potential solution. We provide the first systematic test of whether SI can approximate True Ignorance (TI). Across 470 competition-level questions and 9 models, we find that SI fails systematically: (1) cutoff instructions leave a 52% performance gap between SI and TI; (2) chain-of-thought reasoning fails to suppress prior knowledge, even when reasoning traces contain no explicit post-cutoff references; (3) reasoning-optimized models exhibit worse SI fidelity despite superior reasoning trace quality. These findings demonstrate that prompts cannot reliably "rewind" model knowledge. We conclude that RF on pre-cutoff events is methodologically flawed; we recommend against using SI-based retrospective setups to benchmark forecasting capabilities.