Rebuttal acknowledged, thank you for the additional clarifications. Indeed, given a flat prior for x_{t 1} (i.e., Gaussian with "infinite" variance), we have two independent observations: - the influence of the past (prediction term) - the influence of the current measurement (filtering term) both have Gaussian likelihood. So the posterior density of x_{t 1} is proportional to a product of three Gaussian-shaped terms. The two different ways in which these terms can be folded into each other (using standard Gaussian conjugacy rules) lead to Thm 1. I believe that the linear-algebraic formulation the authors use just hides the fact that we are multiplying Gaussian PDFs in different ways.

The results of this paper could be of interest to NeurIPS. However, the author(s) should try and address most of the concerns raised by the reviewers, specially a review of existing work on Kalman filtering with infinite variance.

Summary This paper discusses the importance and the method for deep fusion model with single-source noise with experiments on 3D/BEV object detection. It first proposes a novel loss called MAXSSN, as a loss used in the whole paper for single-source robustness. It then shows the limitation of standard robust fusion model -- if we do not consider every single loss separately -- adding all of them to the input at once, we would get a worse model. Two algorithms are proposed for minimizing the MAXSSN loss. The basic idea is to alternatively train on clean data and data with noise.

This is a borderline paper that discusses the problem of robustness with two sources. The reviewers thought the approach was novel; however, there is a lack of theoretical analysis and question about the method's generalization to more complex scenarios.

Multi-task model merging offers an efficient solution for integrating knowledge from multiple fine-tuned models, mitigating the significant computational and storage demands associated with multi-task training. Despite the promising performance of TA, conflicts can arise among the task vectors, particularly when different tasks require distinct model adaptations. In this paper, we formally define this issue as knowledge conflicts, characterized by the performance degradation of one task after merging with a model fine-tuned for another task. Restricting parameter merging within this trust region, TATR can effectively alleviate knowledge conflicts. Moreover, TATR serves as both an independent approach and a plug-and-play module compatible with a wide range of TAbased methods. Extensive empirical evaluations on eight distinct datasets robustly demonstrate that TATR improves the multi-task performance of several TA-based model merging methods by an observable margin. The growing adoption of large foundation models is accompanied by significant practical challenges in terms of computational and storage demands (Kaplan et al., 2020). To address these challenges, multi-task model merging (Matena & Raffel, 2022) has emerged as a promising solution. Here task vectors are the difference in model parameters between the pre-trained foundation model and its fine-tuned version on a specific task. This approach builds a high-performance multi-task model by simple arithmetic operations in the model parameter space, thereby reducing computational overheads associated with fine-tuning on multiple tasks. Despite their successes, task arithmetic and its variants (Yadav et al., 2023; Wang et al., 2024; Yang et al., 2024b;a) still suffer from conflicts between task vectors.

Contextual Partitioning introduces an innovative approach to enhancing the architectural design of large-scale computational models through the dynamic segmentation of parameters into context-aware regions. This methodology emphasizes the importance of task-specific specialization, achieved through adaptive parameter allocation mechanisms that align with the linguistic features of input data. Experimental evaluations demonstrated substantial improvements in accuracy, perplexity, and contextual coherence across a variety of linguistic tasks, highlighting the adaptability and scalability of the proposed framework. By reducing redundancy and enhancing computational efficiency, Contextual Partitioning not only streamlines model operations but also expands the scope of applications for advanced language processing systems. The approach operates autonomously, requiring no external fine-tuning, thereby addressing a significant limitation in conventional parameter optimization techniques. Empirical results demonstrate the effectiveness of gradient-driven segmentation, enabling models to dynamically recalibrate and specialize in response to task-specific demands. Furthermore, resource utilization metrics reveal notable reductions in memory usage and training times, confirming the efficiency of the approach. Observations from qualitative analyses illustrate improved contextual coherence and logical flow in generated outputs, reinforcing the practical value of this technique. The findings collectively demonstrate the potential for Contextual Partitioning to redefine the scalability and adaptability of computational language architectures in diverse and complex domains.

Accurate classification of histological subtypes of non-small cell lung cancer (NSCLC) is essential in the era of precision medicine, yet current invasive techniques are not always feasible and may lead to clinical complications. This study presents a multi-stage intermediate fusion approach to classify NSCLC subtypes from CT and PET images. Our method integrates the two modalities at different stages of feature extraction, using voxel-wise fusion to exploit complementary information across varying abstraction levels while preserving spatial correlations. We compare our method against unimodal approaches using only CT or PET images to demonstrate the benefits of modality fusion, and further benchmark it against early and late fusion techniques to highlight the advantages of intermediate fusion during feature extraction. Additionally, we compare our model with the only existing intermediate fusion method for histological subtype classification using PET/CT images. Our results demonstrate that the proposed method outperforms all alternatives across key metrics, with an accuracy and AUC equal to 0.724 and 0.681, respectively. This non-invasive approach has the potential to significantly improve diagnostic accuracy, facilitate more informed treatment decisions, and advance personalized care in lung cancer management.

In the past years, YOLO-series models have emerged as the leading approaches in the area of real-time object detection. Many studies pushed up the baseline to a higher level by modifying the architecture, augmenting data and designing new losses. However, we find previous models still suffer from information fusion problem, although Feature Pyramid Network (FPN) and Path Aggregation Network (PANet) have alleviated this. Therefore, this study provides an advanced Gatherand-Distribute mechanism (GD) mechanism, which is realized with convolution and self-attention operations. This new designed model named as Gold-YOLO, which boosts the multi-scale feature fusion capabilities and achieves an ideal balance between latency and accuracy across all model scales.

Researchers often face data fusion problems, where multiple data sources are available, each capturing a distinct subset of variables. While problem formulations typically take the data as given, in practice, data acquisition can be an ongoing process. In this paper, we introduce the problem of deciding, at each time, which data source to sample from. Our goal is to estimate a given functional of the parameters of a probabilistic model as efficiently as possible. We propose online moment selection (OMS), a framework in which structural assumptions are encoded as moment conditions.

Deep neural networks provide reliable solutions for many classification and regression tasks; however, their application in real-time wireless systems with simple sensor networks is limited due to high energy consumption and significant bandwidth needs. This study proposes a multi-sensor wireless inference system with memristor-based analog computing. Given the sensors' limited computational capabilities, the features from the network's front end are transmitted to a central device where an $L_p$-norm inspired approximation of the maximum operation is employed to achieve transformation-invariant features, enabling efficient over-the-air transmission. We also introduce a trainable over-the-air sensor fusion method based on $L_p$-norm inspired combining function that customizes sensor fusion to match the network and sensor distribution characteristics, enhancing adaptability. To address the energy constraints of sensors, we utilize memristors, known for their energy-efficient in-memory computing, enabling analog-domain computations that reduce energy use and computational overhead in edge computing. This dual approach of memristors and $L_p$-norm inspired sensor fusion fosters energy-efficient computational and transmission paradigms and serves as a practical energy-efficient solution with minimal performance loss.