Nowadays, recommendation systems have become crucial to online platforms, shaping user exposure by accurate preference modeling. However, such an exposure strategy can also reinforce users’ existing preferences, leading to a notorious phenomenon named filter bubbles. Given its negative effects, such as group polarization, increasing attention has been paid to exploring reasonable measures to filter bubbles. However, most existing evaluation metrics simply measure the diversity of user exposure, failing to distinguish between algorithmic preference modeling and actual information confinement. In view of this, we introduce Bubble Escape Potential (BEP), a behavior-aware measure that quantifies how easily users can escape from filter bubbles. Specifically, BEP leverages a contrastive simulation framework that assigns different behavioral tendencies (e.g., positive vs. negative) to synthetic users and compares the induced exposure patterns. This design enables decoupling the effect of filter bubbles and preference modeling, allowing for more precise diagnosis of bubble severity. We conduct extensive experiments across multiple recommendation models to examine the relationship between predictive accuracy and bubble escape potential across different groups. To the best of our knowledge, our empirical results are the first to quantitatively validate the dilemma between preferences modeling and filter bubbles. What's more, we observe a counter-intuitive phenomenon that mild random recommendations are ineffective in alleviating filter bubbles, which can offer a principled foundation for further work in this direction.

Efficiently fine-tuning pre-trained models for downstream tasks is a key challenge in the era of foundation models. Parameter-efficient fine-tuning (PEFT) presents a promising solution, achieving performance comparable to full fine-tuning by updating only a small number of adaptation weights per layer. Traditional PEFT methods typically rely on a single expert, where the adaptation weight is a low-rank matrix. However, for complex tasks, the data's inherent diversity poses a significant challenge for such models, as a single adaptation weight cannot adequately capture the features of all samples. To address this limitation, we explore how to integrate multiple small adaptation experts into a compact structure to defeat a large adapter. Specifically, we propose Tucker Adaptation (TuckA), a method with four key properties: (i) We use Tucker decomposition to create a compact 3D tensor where each slice naturally serves as an expert. The low-rank nature of this decomposition ensures that the number of parameters scales efficiently as more experts are added. (ii) We introduce a hierarchical strategy that organizes these experts into groups at different granularities, allowing the model to capture both local and global data patterns. (iii) We develop an efficient batch-level routing mechanism, which reduces the router's parameter size by a factor of L compared to routing at every adapted layer (where L is the number of adapted layers) (iv) We propose data-aware initialization to achieve loss-free expert load balancing based on theoretical analysis. Extensive experiments on benchmarks in natural language understanding, image classification, and mathematical reasoning speak to the efficacy of TuckA, offering a new and effective solution to the PEFT problem.

Early diagnosis of Alzheimer's disease (AD) is crucial for its prevention, and hippocampal atrophy is a significant lesion for early diagnosis. The current DL-based AD diagnosis methods only focus on either AD classification or hippocampus segmentation independently, neglecting the correlation between the two tasks and lacking pathological interpretability. To address this issue, we propose a Reliable Hippo-guided Learning model for Alzheimer's Disease diagnosis (RLAD), which employs multi-task learning for AD classification as a main task supplemented by hippocampus segmentation. More specifically, our model consists of 1) a hybrid shared features encoder that encodes local and global information in MRI to enhance the model's ability to learn discriminative features; 2) Task Specific Decoders to accomplish AD classification and hippocampus segmentation; and 3) Task Coordination module to correlate the two tasks and guide the classification task to focus on the hippocampus area. Our proposed RLAD model is evaluated on MRI scans of 1631 subjects from three independent datasets, including ADNI-1, ADNI-2, and HarP. Our extensive experimental results demonstrate that the proposed model significantly improves the performance of AD classification and hippocampus segmentation with strong generalization capabilities.

Recent advances in deep learning have led to increasingly complex models with deeper layers and more parameters, reducing interpretability and making their decisions harder to understand. While many methods explain black-box reasoning, most lack effective interventions or only operate at sample-level without modifying the model itself. To address this, we propose the Concept Bottleneck Model for Enhancing Human-Neural Network Mutual Understanding (CBM-HNMU). CBM-HNMU leverages the Concept Bottleneck Model (CBM) as an interpretable framework to approximate black-box reasoning and communicate conceptual understanding. Detrimental concepts are automatically identified and refined (removed/replaced) based on global gradient contributions. The modified CBM then distills corrected knowledge back into the black-box model, enhancing both interpretability and accuracy. We evaluate CBM-HNMU on various CNN and transformer-based models across Flower-102, CIFAR-10, CIFAR-100, FGVC-Aircraft, and CUB-200, achieving a maximum accuracy improvement of 2.64% and a maximum increase in average accuracy across 1.03%. Source code is available at: https://github.com/XiGuaBo/CBM-HNMU.

Prompt tuning adapts Vision-Language Models like CLIP to open-world tasks with minimal training costs. In this direction, one typical paradigm evaluates model performance separately on known classes (i.e., base domain) and unseen classes (i.e., new domain). However, real-world scenarios require models to handle inputs without prior domain knowledge. This practical challenge has spurred the development of open-world prompt tuning, which demands a unified evaluation of two stages: 1) detecting whether an input belongs to the base or new domain (P1), and 2) classifying the sample into its correct class (P2). What’s more, as domain distributions are generally unknown, a proper metric should be insensitive to varying base/new sample ratios (P3). However, we find that current metrics, including HM, overall accuracy, and AUROC, fail to satisfy these three properties simultaneously. To bridge this gap, we propose $\mathsf{OpenworldAUC}$, a unified metric that jointly assesses detection and classification through pairwise instance comparisons. To optimize $\mathsf{OpenworldAUC}$ effectively, we introduce Gated Mixture-of-Prompts (GMoP), which employs domain-specific prompts and a gating mechanism to dynamically balance detection and classification. Theoretical guarantees ensure generalization of GMoP under practical conditions. Experiments on 15 benchmarks in open-world scenarios show GMoP achieves SOTA performance on $\mathsf{OpenworldAUC}$ and other metrics.

Three-dimensional in-domain retrieval has recently achieved significant success, but 3-D cross-modal retrieval still faces problems and challenges. Existing methods only rely on a simple global feature (GF), which overlooks the local information of complex 3-D objects and the connections between similar local features across complex multimodal instances. To tackle this issue, we propose a hierarchical set-to-set representation (HSR) and a corresponding hierarchical similarity that incorporates global-to-global and local-to-local similarity metrics. Specifically, we employ feature extractors for each modality to learn both GFs and local feature sets. We then project these features into their respective common space and use bilinear pooling to generate compact-set features that maintain the invariant for set-to-set similarity measurement. To facilitate effective hierarchical similarity measurement, we design an operation to combine the GF and the compact-set feature to generate the hierarchical representation for 3-D cross-modal retrieval, which preserves hierarchical similarity measurement. To optimize the framework, we adopt the joint loss functions, including cross-modal center loss (CMCL), mean square loss, and cross-entropy loss, to reduce the cross-modal discrepancy for each instance and minimize the distances between the instances in the same category. Experimental results demonstrate that our method outperforms the state-of-the-art methods on the 3-D cross-modal retrieval task on both ModelNet10 and ModelNet40 datasets.

This paper explores a novel multi-modal alternating learning paradigm pursuing a reconciliation between the exploitation of uni-modal features and the exploration of cross-modal interactions. This is motivated by the fact that current paradigms of multi-modal learning tend to explore multi-modal features simultaneously. The resulting gradient prohibits further exploitation of the features in the weak modality, leading to modality competition, where the dominant modality overpowers the learning process. To address this issue, we study the modality-alternating learning paradigm to achieve reconcilement. Specifically, we propose a new method called ReconBoost to update a fixed modality each time. Herein, the learning objective is dynamically adjusted with a reconcilement regularization against competition with the historical models. By choosing a KL-based reconcilement, we show that the proposed method resembles Friedman’s Gradient-Boosting (GB) algorithm, where the updated learner can correct errors made by others and help enhance the overall performance. The major difference with the classic GB is that we only preserve the newest model for each modality to avoid overfitting caused by ensembling strong learners. Furthermore, we propose a memory consolidation scheme and a global rectification scheme to make this strategy more effective. Experiments over six multi-modal benchmarks speak to the efficacy of the proposed method.

The key of Human-Object Interaction(HOI) recognition is to infer the relationship between human and objects. Recently, the image's Human-Object Interaction(HOI) detection has made significant progress. However, there is still room for improvement in video HOI detection performance. Existing one-stage methods use well-designed end-to-end networks to detect a video segment and directly predict an interaction. A side effect of these approaches is that we have no way of knowing the human-object pair of the interaction or the keyframes in which the interaction took place. It makes the model learning and further optimization of the network more complex. This paper introduces the Spatial Parsing and Dynamic Temporal Pooling (SPDTP) network, which takes the entire video as a spatio-temporal graph with human and object nodes as input. Unlike existing methods, our proposed network predicts the difference between interactive and non-interactive pairs through explicit spatial parsing, and then performs interaction recognition. Moreover, we propose a learnable and differentiable Dynamic Temporal Module(DTM) to emphasize the keyframes of the video and suppress the redundant frame. Furthermore, the experimental results show that SPDTP can pay more attention to active human-object pairs and valid keyframes. Overall, we achieve state-of-the-art performance on CAD-120 dataset and Something- Else dataset.

For a given video-based Human-Object Interaction scene, modeling the spatio-temporal relationship between humans and objects is the important cue to understand the contextual information presented in the video. With the efficient spatio-temporal relationship modeling, it is possible not only to uncover contextual information in each frame, but to directly capture inter-frame dependencies as well. Capturing the position changes of human and objects over the spatio-temporal dimension is more critical when significant changes in the appearance features may not occur over time. When utilizing appearance features, the spatial location and the semantic information are also the key to improve the video-based Human-Object Interaction recognition performance. In this paper, Spatio-Temporal Interaction Graph Parsing Networks (STIGPN) are constructed, which encode the videos with a graph composed of human and object nodes. These nodes are connected by two types of relations: (i) intra-frame relations: modeling the interactions between human and the interacted objects within each frame. (ii) inter-frame relations: capturing the long range dependencies between human and the interacted objects across frame. With the graph, STIGPN learn spatio-temporal features directly from the whole video-based Human-Object Interaction scenes. Multi-modal features and a multi-stream fusion strategy are used to enhance the reasoning capability of STIGPN. Two Human-Object Interaction video datasets, including CAD-120 and Something-Else, are used to evaluate the proposed architectures, and the state-of-the-art performance demonstrates the superiority of STIGPN. Code for STIGPN is available at https://github.com/GuangmingZhu/STIGPN.