Deep model merging represents an emerging research direction that combines multiple fine-tuned models to harness their specialized capabilities across different tasks and domains. Current model merging techniques focus on merging all available models simultaneously, with weight interpolation-based methods being the predominant approaches. However, these conventional approaches are not well-suited for scenarios where models become available sequentially, and they often suffer from high memory requirements and potential interference between tasks. In this study, we propose a training-free projection-based continual merging method that processes models sequentially through orthogonal projections of weight matrices and adaptive scaling mechanisms. Our method operates by projecting new parameter updates onto subspaces orthogonal to existing merged parameter updates while using an adaptive scaling mechanism to maintain stable parameter distances, enabling efficient sequential integration of task-specific knowledge. Our approach maintains constant memory complexity to the number of models, minimizes interference between tasks through orthogonal projections, and retains the performance of previously merged models through adaptive task vector scaling. Extensive experiments on CLIP-ViT models demonstrate that our method achieves a 5-8% average accuracy improvement while maintaining robust performance in different task orderings.

The vast majority of Reinforcement Learning methods is largely impacted by the computation effort and data requirements needed to obtain effective estimates of action-value functions, which in turn determine the quality of the overall performance and the sample-efficiency of the learning procedure. Typically, action-value functions are estimated through an iterative scheme that alternates the application of an empirical approximation of the Bellman operator and a subsequent projection step onto a considered function space. It has been observed that this scheme can be potentially generalized to carry out multiple iterations of the Bellman operator at once, benefiting the underlying learning algorithm. However, till now, it has been challenging to effectively implement this idea, especially in high-dimensional problems. In this paper, we introduce iterated $Q$-Network (iQN), a novel principled approach that enables multiple consecutive Bellman updates by learning a tailored sequence of action-value functions where each serves as the target for the next. We show that iQN is theoretically grounded and that it can be seamlessly used in value-based and actor-critic methods. We empirically demonstrate the advantages of iQN in Atari $2600$ games and MuJoCo continuous control problems.

Artificial intelligence generated content (AIGC) has emerged as a promising technology to improve the efficiency, quality, diversity and flexibility of the content creation process by adopting a variety of generative AI models. Deploying AIGC services in wireless networks has been expected to enhance the user experience. However, the existing AIGC service provision suffers from several limitations, e.g., the centralized training in the pre-training, fine-tuning and inference processes, especially their implementations in wireless networks with privacy preservation. Federated learning (FL), as a collaborative learning framework where the model training is distributed to cooperative data owners without the need for data sharing, can be leveraged to simultaneously improve learning efficiency and achieve privacy protection for AIGC. To this end, we present FL-based techniques for empowering AIGC, and aim to enable users to generate diverse, personalized, and high-quality content. Furthermore, we conduct a case study of FL-aided AIGC fine-tuning by using the state-of-the-art AIGC model, i.e., stable diffusion model. Numerical results show that our scheme achieves advantages in effectively reducing the communication cost and training latency and privacy protection. Finally, we highlight several major research directions and open issues for the convergence of FL and AIGC.

Differential replication through copying refers to the process of replicating the decision behavior of a machine learning model using another model that possesses enhanced features and attributes. This process is relevant when external constraints limit the performance of an industrial predictive system. Under such circumstances, copying enables the retention of original prediction capabilities while adapting to new demands. Previous research has focused on the single-pass implementation for copying. This paper introduces a novel sequential approach that significantly reduces the amount of computational resources needed to train or maintain a copy, leading to reduced maintenance costs for companies using machine learning models in production. The effectiveness of the sequential approach is demonstrated through experiments with synthetic and real-world datasets, showing significant reductions in time and resources, while maintaining or improving accuracy. Keywords: Sustainable AI, transfer learning, environmental adaptation, optimization, and model enhancement.

To remind you with a visual, here, in figure 1, is the whole pipeline. I've circled the part of the system we'll address in this article. You may ask, what exactly is a pipeline and why do we use one, whether for ML production or any programmatic production operation which is managed by orchestration? You typically use pipelines when the job, such as training or other operation handled by orchestration, has multiple steps that occur in sequential order: do step A, do step B, and like this. Putting the steps into a ML production pipeline has multiple benefits.

Detecting and predicting the behavior of pedestrians is extremely crucial for self-driving vehicles to plan and interact with them safely. Although there have been several research works in this area, it is important to have fast and memory efficient models such that it can operate in embedded hardware in these autonomous machines. In this work, we propose a novel architecture using spatial-temporal multi-tasking to do camera based pedestrian detection and intention prediction. Our approach significantly reduces the latency by being able to detect and predict all pedestrians' intention in a single shot manner while also being able to attain better accuracy by sharing features with relevant object level information and interactions.

Robotic mobile fulfillment systems (RMFSs) are a new type of warehousing system, which has received more attention recently, due to increasing growth in the e-commerce sector. Instead of sending pickers to the inventory area to search for and pick the ordered items, robots carry shelves (called "pods") including ordered items from the inventory area to picking stations. In the picking stations, human pickers put ordered items into totes; then these items are transported by a conveyor to the packing stations. This type of warehousing system relieves the human pickers and improves the picking process. In this paper, we concentrate on decisions about the assignment of pods to stations and orders to stations to fulfill picking for each incoming customer's order. In previous research for an RMFS with multiple picking stations, these decisions are made sequentially. Instead, we present a new integrated model. To improve the system performance even more, we extend our model by splitting orders. This means parts of an order are allowed to be picked at different stations. To the best of the authors' knowledge, this is the first publication on split orders in an RMFS. We analyze different performance metrics, such as pile-on, pod-station visits, robot moving distance and order turn-over time. We compare the results of our models in different instances with the sequential method in our open-source simulation framework RAWSim-O.

We propose a new architecture and training methodology for generative adversarial networks. Current approaches attempt to learn the transformation from a noise sample to a generated data sample in one shot. Our proposed generator architecture, called $\textit{ChainGAN}$, uses a two-step process. It first attempts to transform a noise vector into a crude sample, similar to a traditional generator. Next, a chain of networks, called $\textit{editors}$, attempt to sequentially enhance this sample. We train each of these units independently, instead of with end-to-end backpropagation on the entire chain. Our model is robust, efficient, and flexible as we can apply it to various network architectures. We provide rationale for our choices and experimentally evaluate our model, achieving competitive results on several datasets.

An econometric or statistical model may undergo a marginal gain when a new variable is admitted, and a marginal loss if an existing variable is removed. The value of a variable to the model is quantified by its expected marginal gain and marginal loss. Assuming the equality of opportunity, we derive a few formulas which evaluate the overall performance in potential modeling scenarios. However, the value is not symmetric to marginal gain and marginal loss; thus, we introduce an unbiased solution. Simulation studies show that our new approaches significantly outperform a few practice-used variable selection methods.

Correspondence algorithms typically struggle with shapes that display part-based variation. We present a probabilistic approach that matches shapes using independent parttransformations, where the parts themselves are learnt during matching. Ideas from semi-supervised learning are used to bias the algorithm towards finding'perceptuallyvalid' part structures. Shapes are represented by unlabeled point sets of arbitrary size and a background component is used to handle occlusion, local dissimilarity and clutter. Thus, unlike many shape matching techniques, our approach can be applied to shapes extracted from real images. Model parameters areestimated using an EM algorithm that alternates between finding a soft correspondence and computing the optimal part transformations using Procrustes analysis.