Delay-Empowered Causal Hierarchical Reinforcement Learning

Many real-world tasks involve delayed effects, where the outcomes of actions emerge after varying time lags. Existing delay-aware reinforcement learning methods often rely on state augmentation, prior knowledge of delay distributions, or access to non-delayed data, limiting their generalization. Hierarchical reinforcement learning, by contrast, inherently offers advantages in handling delays due to its hierarchical structure, yet existing methods are restricted to fixed delays. To address these limitations, we propose Delay-Empowered Causal Hierarchical Reinforcement Learning (DECHRL). DECHRL explicitly models both the causal structure of state transitions and their associated stochastic delay distributions. These are then incorporated into a delay-aware empowerment objective that drives proactive exploration toward highly controllable states, thereby improving performance under temporal uncertainty. We evaluate DECHRL in modified 2D-Minecraft and MiniGrid environments featuring stochastic delays. Experimental results show that DECHRL effectively models temporal delays and significantly outperforms baselines in decision-making under temporal uncertainty.

Multi-View Synergistic Learning with Vision-Language Adaption for Low-Resource Biomedical Image Classification

Accurate biomedical image classification under low-resource conditions remains challenging due to limited annotations, subtle inter-class visual differences, and complex disease semantics. While vision--language models offer a promising foundation for mitigating data scarcity, their effective adaptation in biomedical settings is constrained by the need for parameter-efficient tuning alongside fine-grained and semantically consistent representation learning. In this work, we propose Multi-View Synergistic Learning (MVSL), a unified framework that addresses these challenges by jointly considering adaptation paradigms, representation granularity, and disease semantic relationships. MVSL decouples the adaptation of visual and textual encoders to respect their distinct representational characteristics, enabling more stable and effective parameter-efficient fine-tuning. It further introduces multi-granularity contrastive learning to explicitly model both global image semantics and localized lesion-level evidence, improving fine-grained discrimination for visually similar disease categories. In addition, MVSL preserves disease-level semantic structure by incorporating structured supervision derived from large language models, which constrains textual representations at the class level and indirectly regularizes visual embeddings through cross-modal alignment. Together, these components enable more stable cross-modal alignment and improved discrimination under limited supervision. Extensive experiments on $11$ public biomedical datasets spanning $9$ imaging modalities and $10$ anatomical regions demonstrate that MVSL consistently outperforms state-of-the-art methods in few-shot and zero-shot classification settings.

TRACE: An Experiential Framework for Coherent Multi-hop Knowledge Graph Question Answering

Multi-hop Knowledge Graph Question Answering (KGQA) requires coherent reasoning across relational paths, yet existing methods often treat each reasoning step independently and fail to effectively leverage experience from prior explorations, leading to fragmented reasoning and redundant exploration. To address these challenges, we propose Trajectoryaware Reasoning with Adaptive Context and Exploration priors (TRACE), an experiential framework that unifies LLM-driven contextual reasoning with exploration prior integration to enhance the coherence and robustness of multihop KGQA. Specifically, TRACE dynamically translates evolving reasoning paths into natural language narratives to maintain semantic continuity, while abstracting prior exploration trajectories into reusable experiential priors that capture recurring exploration patterns. A dualfeedback re-ranking mechanism further integrates contextual narratives with exploration priors to guide relation selection during reasoning. Extensive experiments on multiple KGQA benchmarks demonstrate that TRACE consistently outperforms state-of-the-art baselines.

DSBD: Dual-Aligned Structural Basis Distillation for Graph Domain Adaptation

Graph domain adaptation (GDA) aims to transfer knowledge from a labeled source graph to an unlabeled target graph under distribution shifts. However, existing methods are largely feature-centric and overlook structural discrepancies, which become particularly detrimental under significant topology shifts. Such discrepancies alter both geometric relationships and spectral properties, leading to unreliable transfer of graph neural networks (GNNs). To address this limitation, we propose Dual-Aligned Structural Basis Distillation (DSBD) for GDA, a novel framework that explicitly models and adapts cross-domain structural variation. DSBD constructs a differentiable structural basis by synthesizing continuous probabilistic prototype graphs, enabling gradient-based optimization over graph topology. The basis is learned under source-domain supervision to preserve semantic discriminability, while being explicitly aligned to the target domain through a dual-alignment objective. Specifically, geometric consistency is enforced via permutation-invariant topological moment matching, and spectral consistency is achieved through Dirichlet energy calibration, jointly capturing structural characteristics across domains. Furthermore, we introduce a decoupled inference paradigm that mitigates source-specific structural bias by training a new GNN on the distilled structural basis. Extensive experiments on graph and image benchmarks demonstrate that DSBD consistently outperforms state-of-the-art methods.

USBD: Universal Structural Basis Distillation for Source-Free Graph Domain Adaptation

SF-GDA is pivotal for privacy-preserving knowledge transfer across graph datasets. Although recent works incorporate structural information, they implicitly condition adaptation on the smoothness priors of sourcetrained GNNs, thereby limiting their generalization to structurally distinct targets. This dependency becomes a critical bottleneck under significant topological shifts, where the source model misinterprets distinct topological patterns unseen in the source domain as noise, rendering pseudo-label-based adaptation unreliable. To overcome this limitation, we propose the Universal Structural Basis Distillation, a framework that shifts the paradigm from adapting a biased model to learning a universal structural basis for SF-GDA. Instead of adapting a biased source model to a specific target, our core idea is to construct a structure-agnostic basis that proactively covers the full spectrum of potential topological patterns. Specifically, USBD employs a bi-level optimization framework to distill the source dataset into a compact structural basis. By enforcing the prototypes to span the full Dirichlet energy spectrum, the learned basis explicitly captures diverse topological motifs, ranging from low-frequency clusters to high-frequency chains, beyond those present in the source. This ensures that the learned basis creates a comprehensive structural covering capable of handling targets with disparate structures. For inference, we introduce a spectral-aware ensemble mechanism that dynamically activates the optimal prototype combination based on the spectral fingerprint of the target graph. Extensive experiments on benchmarks demonstrate that USBD significantly outperforms state-of-the-art methods, particularly in scenarios with severe structural shifts, while achieving superior computational efficiency by decoupling the adaptation cost from the target data scale.

Riemannian Flow Matching for Disentangled Graph Domain Adaptation

Graph Domain Adaptation (GDA) typically uses adversarial learning to align graph embeddings in Euclidean space. However, this paradigm suffers from two critical challenges: Structural Degeneration, where hierarchical and semantic representations are entangled, and Optimization Instability, which arises from oscillatory dynamics of minimax adversarial training. To tackle these issues, we propose DisRFM, a geometry-aware GDA framework that unifies Riemannian embedding and flow-based transport. First, to overcome structural degeneration, we embed graphs into a Riemannian manifold. By adopting polar coordinates, we explicitly disentangle structure (radius) from semantics (angle). Then, we enforce topology preservation through radial Wasserstein alignment and semantic discrimination via angular clustering, thereby preventing feature entanglement and collapse. Second, we address the instability of adversarial alignment by using Riemannian flow matching. This method learns a smooth vector field to guide source features toward the target along geodesic paths, guaranteeing stable convergence. The geometric constraints further guide the flow to maintain the disentangled structure during transport. Theoretically, we prove the asymptotic stability of the flow matching and derive a tighter bound for the target risk. Extensive experiments demonstrate that DisRFM consistently outperforms state-of-the-art methods.

Understanding Model Merging: A Unified Generalization Framework for Heterogeneous Experts

Model merging efficiently aggregates capabilities from multiple fine-tuned models into a single one, operating purely in parameter space without original data or expensive re-computation. Despite empirical successes, a unified theory for its effectiveness under heterogeneous finetuning hyperparameters (e.g., varying learning rates, batch sizes) remains missing. Moreover, the lack of hyperparameter transparency in open-source fine-tuned models makes it difficult to predict merged-model performance, leaving practitioners without guidance on how to fine-tune merge-friendly experts. To address those two challenges, we employ $L_2$-Stability theory under heterogeneous hyperparameter environments to analyze the generalization of the merged model $\boldsymbol{x}_{avg}$. This pioneering analysis yields two key contributions: (i) \textit{A unified theoretical framework} is provided to explain existing merging algorithms, revealing how they optimize specific terms in our bound, thus offering a strong theoretical foundation for empirical observations. (ii) \textit{Actionable recommendations} are proposed for practitioners to strategically fine-tune expert models, enabling the construction of merge-friendly models within the pretraining-to-finetuning pipeline. Extensive experiments on the ResNet/Vit family across 20/8 visual classification tasks, involving thousands of finetuning models, robustly confirm the impact of different hyperparameters on the generalization of $\boldsymbol{x}_{avg}$ predicted by our theoretical results.

FOUND: Fourier-based von Mises Distribution for Robust Single Domain Generalization in Object Detection

Single Domain Generalization (SDG) for object detection aims to train a model on a single source domain that can generalize effectively to unseen target domains. While recent methods like CLIP-based semantic augmentation have shown promise, they often overlook the underlying structure of feature distributions and frequency-domain characteristics that are critical for robustness. In this paper, we propose a novel framework that enhances SDG object detection by integrating the von Mises-Fisher (vMF) distribution and Fourier transformation into a CLIP-guided pipeline. Specifically, we model the directional features of object representations using vMF to better capture domain-invariant semantic structures in the embedding space. Additionally, we introduce a Fourier-based augmentation strategy that perturbs amplitude and phase components to simulate domain shifts in the frequency domain, further improving feature robustness. Our method not only preserves the semantic alignment benefits of CLIP but also enriches feature diversity and structural consistency across domains. Extensive experiments on the diverse weather-driving benchmark demonstrate that our approach outperforms the existing state-of-the-art method.

Separation and Collaboration: Two-Level Routing Grouped Mixture-of-Experts for Multi-Domain Continual Learning

Multi-Domain Continual Learning (MDCL) acquires knowledge from sequential tasks with shifting class sets and distribution. Despite the Parameter-Efficient Fine-Tuning (PEFT) methods can adapt for this dual heterogeneity, they still suffer from catastrophic forgetting and forward forgetting. To address these challenges, we propose a Two-Level Routing Grouped Mixture-of-Experts (TRGE) method. Firstly, TRGE dynamically expands the pre-trained CLIP model, assigning specific expert group for each task to mitigate catastrophic forgetting. With the number of experts continually grows in this process, TRGE maintains the static experts count within the group and introduces the intra-group router to alleviate routing overfitting caused by the increasing routing complexity. Meanwhile, we design an inter-group routing policy based on task identifiers and task prototype distance, which dynamically selects relevant expert groups and combines their outputs to enhance inter-task collaboration. Secondly, to get the correct task identifiers, we leverage Multimodal Large Language Models (MLLMs) which own powerful multimodal comprehension capabilities to generate semantic task descriptions and recognize the correct task identifier. Finally, to mitigate forward forgetting, we dynamically fuse outputs for unseen samples from the frozen CLIP model and TRGE adapter based on training progress, leveraging both pre-trained and learned knowledge. Through extensive experiments across various settings, our method outperforms other advanced methods with fewer trainable parameters.

Nested Graph Pseudo-Label Refinement for Noisy Label Domain Adaptation Learning

Graph Domain Adaptation (GDA) facilitates knowledge transfer from labeled source graphs to unlabeled target graphs by learning domain-invariant representations, which is essential in applications such as molecular property prediction and social network analysis. However, most existing GDA methods rely on the assumption of clean source labels, which rarely holds in real-world scenarios where annotation noise is pervasive. This label noise severely impairs feature alignment and degrades adaptation performance under domain shifts. To address this challenge, we propose Nested Graph Pseudo-Label Refinement (NeGPR), a novel framework tailored for graph-level domain adaptation with noisy labels. NeGPR first pretrains dual branches, i.e., semantic and topology branches, by enforcing neighborhood consistency in the feature space, thereby reducing the influence of noisy supervision. To bridge domain gaps, NeGPR employs a nested refinement mechanism in which one branch selects high-confidence target samples to guide the adaptation of the other, enabling progressive cross-domain learning. Furthermore, since pseudo-labels may still contain noise and the pre-trained branches are already overfitted to the noisy labels in the source domain, NeGPR incorporates a noise-aware regularization strategy. This regularization is theoretically proven to mitigate the adverse effects of pseudo-label noise, even under the presence of source overfitting, thus enhancing the robustness of the adaptation process. Extensive experiments on benchmark datasets demonstrate that NeGPR consistently outperforms state-of-the-art methods under severe label noise, achieving gains of up to 12.7% in accuracy.