Autoencoder-Based Hybrid Replay for Class-Incremental Learning

In class-incremental learning (CIL), effective incremental learning strategies are essential to mitigate task confusion and catastrophic forgetting, especially as the number of tasks $t$ increases. Current exemplar replay strategies impose $\mathcal{O}(t)$ memory/compute complexities. We propose an autoencoder-based hybrid replay (AHR) strategy that leverages our new hybrid autoencoder (HAE) to function as a compressor to alleviate the requirement for large memory, achieving $\mathcal{O}(0.1 t)$ at the worst case with the computing complexity of $\mathcal{O}(t)$ while accomplishing state-of-the-art performance. The decoder later recovers the exemplar data stored in the latent space, rather than in raw format. Additionally, HAE is designed for both discriminative and generative modeling, enabling classification and replay capabilities, respectively. HAE adopts the charged particle system energy minimization equations and repulsive force algorithm for the incremental embedding and distribution of new class centroids in its latent space. Our results demonstrate that AHR consistently outperforms recent baselines across multiple benchmarks while operating with the same memory/compute budgets. The source code is included in the supplementary material and will be open-sourced upon publication.

ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $α$-$β$-Divergence

Knowledge Distillation (KD) transfers knowledge from a large teacher model to a smaller student model by minimizing the divergence between their output distributions, typically using forward Kullback-Leibler divergence (FKLD) or reverse KLD (RKLD). It has become an effective training paradigm due to the broader supervision information provided by the teacher distribution compared to one-hot labels. We identify that the core challenge in KD lies in balancing two mode-concentration effects: the \textbf{\textit{Hardness-Concentration}} effect, which refers to focusing on modes with large errors, and the \textbf{\textit{Confidence-Concentration}} effect, which refers to focusing on modes with high student confidence. Through an analysis of how probabilities are reassigned during gradient updates, we observe that these two effects are entangled in FKLD and RKLD, but in extreme forms. Specifically, both are too weak in FKLD, causing the student to fail to concentrate on the target class. In contrast, both are too strong in RKLD, causing the student to overly emphasize the target class while ignoring the broader distributional information from the teacher. To address this imbalance, we propose ABKD, a generic framework with $\alpha$-$\beta$-divergence. Our theoretical results show that ABKD offers a smooth interpolation between FKLD and RKLD, achieving an effective trade-off between these effects. Extensive experiments on 17 language/vision datasets with 12 teacher-student settings confirm its efficacy. The code is available at https://github.com/ghwang-s/abkd.

VISUALCENT: Visual Human Analysis using Dynamic Centroid Representation

We introduce VISUALCENT, a unified human pose and instance segmentation framework to address generalizability and scalability limitations to multi person visual human analysis. VISUALCENT leverages centroid based bottom up keypoint detection paradigm and uses Keypoint Heatmap incorporating Disk Representation and KeyCentroid to identify the optimal keypoint coordinates. For the unified segmentation task, an explicit keypoint is defined as a dynamic centroid called MaskCentroid to swiftly cluster pixels to specific human instance during rapid changes in human body movement or significantly occluded environment. Experimental results on COCO and OCHuman datasets demonstrate VISUALCENTs accuracy and real time performance advantages, outperforming existing methods in mAP scores and execution frame rate per second. The implementation is available on the project page.

PF3Det: A Prompted Foundation Feature Assisted Visual LiDAR 3D Detector

3D object detection is crucial for autonomous driving, leveraging both LiDAR point clouds for precise depth information and camera images for rich semantic information. Therefore, the multi-modal methods that combine both modalities offer more robust detection results. However, efficiently fusing LiDAR points and images remains challenging due to the domain gaps. In addition, the performance of many models is limited by the amount of high quality labeled data, which is expensive to create. The recent advances in foundation models, which use large-scale pre-training on different modalities, enable better multi-modal fusion. Combining the prompt engineering techniques for efficient training, we propose the Prompted Foundational 3D Detector (PF3Det), which integrates foundation model encoders and soft prompts to enhance LiDAR-camera feature fusion. PF3Det achieves the state-of-the-art results under limited training data, improving NDS by 1.19% and mAP by 2.42% on the nuScenes dataset, demonstrating its efficiency in 3D detection.

Atten-Transformer: A Deep Learning Framework for User App Usage Prediction

Accurately predicting smartphone app usage patterns is crucial for user experience optimization and targeted marketing. However, existing methods struggle to capture intricate dependencies in user behavior, particularly in sparse or complex usage scenarios. To address these challenges, we introduce Atten-Transformer, a novel model that integrates temporal attention with a Transformer network to dynamically identify and leverage key app usage patterns. Unlike conventional methods that primarily consider app order and duration, our approach employs a multi-dimensional feature representation, incorporating both feature encoding and temporal encoding to enhance predictive accuracy. The proposed attention mechanism effectively assigns importance to critical app usage moments, improving both model interpretability and generalization. Extensive experiments on multiple smartphone usage datasets, including LSapp and Tsinghua App Usage datasets, demonstrate that Atten-Transformer consistently outperforms state-of-the-art models across different data splits. Specifically, our model achieves a 45.24\% improvement in HR@1 on the Tsinghua dataset (Time-based Split) and a 18.25\% improvement in HR@1 on the LSapp dataset (Cold Start Split), showcasing its robustness across diverse app usage scenarios. These findings highlight the potential of integrating adaptive attention mechanisms in mobile usage forecasting, paving the way for enhanced user engagement and resource allocation.

Multi-Agent Performative Prediction Beyond the Insensitivity Assumption: A Case Study for Mortgage Competition

Performative prediction models account for feedback loops in decision-making processes where predictions influence future data distributions. While existing work largely assumes insensitivity of data distributions to small strategy changes, this assumption usually fails in real-world competitive (i.e. multi-agent) settings. For example, in Bertrand-type competitions, a small reduction in one firm's price can lead that firm to capture the entire demand, while all others sharply lose all of their customers. We study a representative setting of multi-agent performative prediction in which insensitivity assumptions do not hold, and investigate the convergence of natural dynamics. To do so, we focus on a specific game that we call the ''Bank Game'', where two lenders compete over interest rates and credit score thresholds. Consumers act similarly as to in a Bertrand Competition, with each consumer selecting the firm with the lowest interest rate that they are eligible for based on the firms' credit thresholds. Our analysis characterizes the equilibria of this game and demonstrates that when both firms use a common and natural no-regret learning dynamic -- exponential weights -- with proper initialization, the dynamics always converge to stable outcomes despite the general-sum structure. Notably, our setting admits multiple stable equilibria, with convergence dependent on initial conditions. We also provide theoretical convergence results in the stochastic case when the utility matrix is not fully known, but each learner can observe sufficiently many samples of consumers at each time step to estimate it, showing robustness to slight mis-specifications. Finally, we provide experimental results that validate our theoretical findings.

A Survey on Mamba Architecture for Vision Applications

Transformers have become foundational for visual tasks such as object detection, semantic segmentation, and video understanding, but their quadratic complexity in attention mechanisms presents scalability challenges. To address these limitations, the Mamba architecture utilizes state-space models (SSMs) for linear scalability, efficient processing, and improved contextual awareness. This paper investigates Mamba architecture for visual domain applications and its recent advancements, including Vision Mamba (ViM) and VideoMamba, which introduce bidirectional scanning, selective scanning mechanisms, and spatiotemporal processing to enhance image and video understanding. Architectural innovations like position embeddings, cross-scan modules, and hierarchical designs further optimize the Mamba framework for global and local feature extraction. These advancements position Mamba as a promising architecture in computer vision research and applications.

FgC2F-UDiff: Frequency-guided and Coarse-to-fine Unified Diffusion Model for Multi-modality Missing MRI Synthesis

Multi-modality magnetic resonance imaging (MRI) is essential for the diagnosis and treatment of brain tumors. However, missing modalities are commonly observed due to limitations in scan time, scan corruption, artifacts, motion, and contrast agent intolerance. Synthesis of missing MRI has been a means to address the limitations of modality insufficiency in clinical practice and research. However, there are still some challenges, such as poor generalization, inaccurate non-linear mapping, and slow processing speeds. To address the aforementioned issues, we propose a novel unified synthesis model, the Frequency-guided and Coarse-to-fine Unified Diffusion Model (FgC2F-UDiff), designed for multiple inputs and outputs. Specifically, the Coarse-to-fine Unified Network (CUN) fully exploits the iterative denoising properties of diffusion models, from global to detail, by dividing the denoising process into two stages, coarse and fine, to enhance the fidelity of synthesized images. Secondly, the Frequency-guided Collaborative Strategy (FCS) harnesses appropriate frequency information as prior knowledge to guide the learning of a unified, highly non-linear mapping. Thirdly, the Specific-acceleration Hybrid Mechanism (SHM) integrates specific mechanisms to accelerate the diffusion model and enhance the feasibility of many-to-many synthesis. Extensive experimental evaluations have demonstrated that our proposed FgC2F-UDiff model achieves superior performance on two datasets, validated through a comprehensive assessment that includes both qualitative observations and quantitative metrics, such as PSNR SSIM, LPIPS, and FID.

Improving Vision Transformers by Overlapping Heads in Multi-Head Self-Attention

Vision Transformers have made remarkable progress in recent years, achieving state-of-the-art performance in most vision tasks. A key component of this success is due to the introduction of the Multi-Head Self-Attention (MHSA) module, which enables each head to learn different representations by applying the attention mechanism independently. In this paper, we empirically demonstrate that Vision Transformers can be further enhanced by overlapping the heads in MHSA. We introduce Multi-Overlapped-Head Self-Attention (MOHSA), where heads are overlapped with their two adjacent heads for queries, keys, and values, while zero-padding is employed for the first and last heads, which have only one neighboring head. Various paradigms for overlapping ratios are proposed to fully investigate the optimal performance of our approach. The proposed approach is evaluated using five Transformer models on four benchmark datasets and yields a significant performance boost. The source code will be made publicly available upon publication.

KA-GNN: Kolmogorov-Arnold Graph Neural Networks for Molecular Property Prediction

Molecular property prediction is a crucial task in the process of Artificial Intelligence-Driven Drug Discovery (AIDD). The challenge of developing models that surpass traditional non-neural network methods continues to be a vibrant area of research. This paper presents a novel graph neural network model-the Kolmogorov-Arnold Network (KAN)-based Graph Neural Network (KA-GNN), which incorporates Fourier series, specifically designed for molecular property prediction. This model maintains the high interpretability characteristic of KAN methods while being extremely efficient in computational resource usage, making it an ideal choice for deployment in resource-constrained environments. Tested and validated on seven public datasets, KA-GNN has shown significant improvements in property predictions over the existing state-of-the-art (SOTA) benchmarks.