The inherent challenge of image fusion lies in capturing the correlation of multi-source images and comprehensively integrating effective information from different sources. Most existing techniques fail to perform dynamic image fusion while notably lacking theoretical guarantees, leading to potential deployment risks in this field. Is it possible to conduct dynamic image fusion with a clear theoretical justification? In this paper, we give our solution from a generalization perspective. We proceed to reveal the generalized form of image fusion and derive a new test-time dynamic image fusion paradigm. It provably reduces the upper bound of generalization error.

Multimodal learning systems often struggle in non-stationary environments due to concept drift, where changing data distributions can degrade performance. Modality-specific drifts and the lack of mechanisms for continuous, stable adaptation compound this challenge. This paper introduces LS-OGD, a novel adaptive control framework for robust multimodal learning in the presence of concept drift. LS-OGD uses an online controller that dynamically adjusts the model's learning rate and the fusion weights between different data modalities in response to detected drift and evolving prediction errors. We prove that under bounded drift conditions, the LS-OGD system's prediction error is uniformly ultimately bounded and converges to zero if the drift ceases. Additionally, we demonstrate that the adaptive fusion strategy effectively isolates and mitigates the impact of severe modality-specific drift, thereby ensuring system resilience and fault tolerance. These theoretical guarantees establish a principled foundation for developing reliable and continuously adapting multimodal learning systems.

Balancing multiple objectives is critical for user satisfaction in modern recommender and search systems, yet current Multi-Task Fusion (MTF) methods rely on static, manually-tuned weights that fail to capture individual user intent. While Reinforcement Learning (RL) offers a path to personalization, traditional approaches often falter due to training instability and the sparse rewards inherent in these large-scale systems. To address these limitations, we propose Group-relative Reinforcement learning with Adaptive Dirichlet Exploration (GRADE), a novel and robust framework for personalized multi-task fusion. GRADE leverages a critic-free, Group Relative Policy Optimization (GRPO) paradigm, enabling stable and efficient policy learning by evaluating the relative performance of candidate weight groups. Its core innovations include employing the Dirichlet distribution for principled and structured exploration of the weight space, and a composite reward function that combines sparse user feedback with dense model priors and rule-based constraints to guide the search effectively. Deployed in the in-app marketplace of an application with over hundreds of millions daily active users, GRADE significantly outperforms established baselines, achieving substantial gains in rigorous large-scale A/B tests: +0.595\% in CTR, +1.193\% in CVR, +1.788\% in OPM, and +1.568\% in total order volume. Following its strong performance, GRADE has been fully deployed in the marketplace search scenario of Kuaishou, serving hundreds of millions of users.

Federated learning (FL) has emerged as a promising paradigm for distributed machine learning, enabling collaborative training of a global model across multiple local devices without requiring them to share raw data. Despite its advancements, FL is limited by factors such as: (i) privacy risks arising from the unprotected transmission of local model updates to the fusion center (FC) and (ii) decreased learning utility caused by heterogeneity in model quantization resolution across participating devices. Prior work typically addresses only one of these challenges because maintaining learning utility under both privacy risks and quantization heterogeneity is a non-trivial task. In this paper, our aim is therefore to improve the learning utility of a privacy-preserving FL that allows clusters of devices with different quantization resolutions to participate in each FL round. Specifically, we introduce a novel stochastic quantizer (SQ) that is designed to simultaneously achieve differential privacy (DP) and minimum quantization error. Notably, the proposed SQ guarantees bounded distortion, unlike other DP approaches. To address quantization heterogeneity, we introduce a cluster size optimization technique combined with a linear fusion approach to enhance model aggregation accuracy. Numerical simulations validate the benefits of our approach in terms of privacy protection and learning utility compared to the conventional LaplaceSQ-FL algorithm.

The inherent challenge of image fusion lies in capturing the correlation of multi-source images and comprehensively integrating effective information from different sources. Most existing techniques fail to perform dynamic image fusion while notably lacking theoretical guarantees, leading to potential deployment risks in this field. Is it possible to conduct dynamic image fusion with a clear theoretical justification? In this paper, we give our solution from a generalization perspective. We proceed to reveal the generalized form of image fusion and derive a new test-time dynamic image fusion paradigm.

The challenge of data scarcity hinders the application of deep learning in industrial surface defect classification (SDC), as it's difficult to collect and centralize sufficient training data from various entities in Industrial Internet of Things (IIoT) due to privacy concerns. Federated learning (FL) provides a solution by enabling collaborative global model training across clients while maintaining privacy. However, performance may suffer due to data heterogeneity-discrepancies in data distributions among clients. In this paper, we propose a novel personalized FL (PFL) approach, named Adversarial Federated Consensus Learning (AFedCL), for the challenge of data heterogeneity across different clients in SDC. First, we develop a dynamic consensus construction strategy to mitigate the performance degradation caused by data heterogeneity. Through adversarial training, local models from different clients utilize the global model as a bridge to achieve distribution alignment, alleviating the problem of global knowledge forgetting. Complementing this strategy, we propose a consensus-aware aggregation mechanism. It assigns aggregation weights to different clients based on their efficacy in global knowledge learning, thereby enhancing the global model's generalization capabilities. Finally, we design an adaptive feature fusion module to further enhance global knowledge utilization efficiency. Personalized fusion weights are gradually adjusted for each client to optimally balance global and local features. Compared with state-of-the-art FL methods like FedALA, the proposed AFedCL method achieves an accuracy increase of up to 5.67% on three SDC datasets.

In this paper, we study the collaborative state fusion problem in a multi-agent environment, where mobile agents collaborate to track movable targets. Due to the limited sensing range and potential errors of on-board sensors, it is necessary to aggregate individual observations to provide target state fusion for better target state estimation. Existing schemes do not perform well due to (1) impractical assumption of the fully known prior target state-space model and (2) observation outliers from individual sensors. To address the issues, we propose a two-stage collaborative fusion framework, namely \underline{L}earnable Weighted R\underline{o}bust \underline{F}usion (\textsf{LoF}). \textsf{LoF} combines a local state estimator (e.g., Kalman Filter) with a learnable weight generator to address the mismatch between the prior state-space model and underlying patterns of moving targets. Moreover, given observation outliers, we develop a time-series soft medoid(TSM) scheme to perform robust fusion. We evaluate \textsf{LoF} in a collaborative detection simulation environment with promising results. In an example setting with 4 agents and 2 targets, \textsf{LoF} leads to a 9.1\% higher fusion gain compared to the state-of-the-art.

As the last key stage of Recommender Systems (RSs), Multi-Task Fusion (MTF) is in charge of combining multiple scores predicted by Multi-Task Learning (MTL) into a final score to maximize user satisfaction, which decides the ultimate recommendation results. In recent years, to maximize long-term user satisfaction within a recommendation session, Reinforcement Learning (RL) is widely used for MTF in large-scale RSs. However, limited by their modeling pattern, all the current RL-MTF methods can only utilize user features as the state to generate actions for each user, but unable to make use of item features and other valuable features, which leads to suboptimal results. Addressing this problem is a challenge that requires breaking through the current modeling pattern of RL-MTF. To solve this problem, we propose a novel method called Enhanced-State RL for MTF in RSs. Unlike the existing methods mentioned above, our method first defines user features, item features, and other valuable features collectively as the enhanced state; then proposes a novel actor and critic learning process to utilize the enhanced state to make much better action for each user-item pair. To the best of our knowledge, this novel modeling pattern is being proposed for the first time in the field of RL-MTF. We conduct extensive offline and online experiments in a large-scale RS. The results demonstrate that our model outperforms other models significantly. Enhanced-State RL has been fully deployed in our RS more than half a year, improving +3.84% user valid consumption and +0.58% user duration time compared to baseline.