As an ordered extension of evidence theory, Random permutation set (RPS) theory has received increasing attention due to its advantage in dealing with order-structured uncertain information. However, a significant research gap remains in the current literature concerning the construction of RPS. Building on the interpretation of RPS as a layer-2 belief structure, this paper proposes a data-driven hierarchical method for generating RPS, called DDHRPS. Specifically, DDHRPS first generates BPA from statistical features of data on the layer-1 belief structure, and then refines them with propensity information derived from distance analysis between samples to single classes, ultimately forming RPS on the layer-2 belief structure. Moreover, a DDHRPS-based classification algorithm (DDHRPSCA) is presented. Experimental comparisons involving two kinds of classifiers, namely, two uncertainty-based classifiers and seven machine learning classifiers validate the effectiveness and superiority of DDHRPSCA in handling uncertain information in classification tasks.

Similar to Language or Image LLMs, VideoLLMs are also plagued by hallucination issues. Hallucinations in videos not only manifest in the spatial dimension regarding the perception of the existence of visual objects (static) but also the temporal dimension influencing the perception of actions and events (dynamic). This paper introduces the concept of Motion Hallucination for the first time, exploring the hallucination phenomena caused by insufficient motion perception capabilities in VideoLMMs, as well as how to detect, evaluate, and mitigate the hallucination. To this end, we propose the first benchmark for assessing motion hallucination MHBench, which consists of 1,200 videos of 20 different action categories. By constructing a collection of adversarial triplet types of videos (original/antonym/incomplete), we achieve a comprehensive evaluation of motion hallucination. Furthermore, we present a Motion Contrastive Decoding (MotionCD) method, which employs bidirectional motion elimination between the original video and its reverse playback to construct an amateur model that removes the influence of motion while preserving visual information, thereby effectively suppressing motion hallucination. Extensive experiments on MHBench reveal that current state-of-the-art VideoLLMs significantly suffer from motion hallucination, while the introduction of MotionCD can effectively mitigate this issue, achieving up to a 15.1% performance improvement. We hope this work will guide future efforts in avoiding and mitigating hallucinations in VideoLLMs.

Recent advancements in Large Vision-Language Models (LVLMs) highlight their ability to integrate and process multi-modal information. However, hallucinations—where generated content is inconsistent with input vision and instructions—remain a challenge. In this paper, we analyze LVLMs' layer-wise decoding and identify that hallucinations can arise during the reasoning and factual information injection process. Additionally, as the number of generated tokens increases, the forgetting of the original prompt may also lead to hallucinations.To address this, we propose a training-free decoding method called Mixture of Layer Experts (MoLE). MoLE leverages a heuristic gating mechanism to dynamically select multiple layers of LVLMs as expert layers: the Final Expert, the Second Opinion expert, and the Prompt Retention Expert. By the cooperation of each expert, MoLE enhances the robustness and faithfulness of the generation process. Our extensive experiments demonstrate that MoLE significantly reduces hallucinations, outperforming the current state-of-the-art decoding techniques across three mainstream LVLMs and two established hallucination benchmarks. Moreover, our method reveals the potential of LVLMs to independently produce more reliable and accurate outputs.

Recent advancements in language models pre-trained on large-scale corpora have significantly propelled developments in the NLP domain and advanced progress in multimodal tasks. In this paper, we propose a Parameter-Efficient multimodal language model learning strategy, named QaP (Querying as Prompt). Its core innovation is a novel modality-bridging method that allows a set of modality-specific queries to be input as soft prompts into a frozen pre-trained language model. Specifically, we introduce an efficient Text-Conditioned Resampler that is easy to incorporate into the language models, which enables adaptive injection of text-related multimodal information at different levels of the model through query learning. This approach effectively bridges multimodal information to the language models while fully leveraging its token fusion and representation potential. We validated our method across four datasets in three distinct multimodal tasks. The results demonstrate that our QaP multimodal language model achieves state-of-the-art performance in various tasks with training only 4.6% parameters. Code is available at https://github.com/RainltIQaP.

The accuracy and robustness of 3D human pose estimation (HPE) are limited by 2D pose detection errors and 2D to 3D ill-posed challenges, which have drawn great attention to Multi-Hypothesis HPE research. Most existing MH-HPE methods are based on generative models, which are computationally expensive and difficult to train. In this study, we propose a Probabilistic Restoration 3D Human Pose Estimation framework (PRPose) that can be integrated with any lightweight single-hypothesis model. Specifically, PRPose employs a weakly supervised approach to fit the hidden probability distribution of the 2D-to-3D lifting process in the Single-Hypothesis HPE model and then reverse-map the distribution to the 2D pose input through an adaptive noise sampling strategy to generate reasonable multi-hypothesis samples effectively. Extensive experiments on 3D HPE benchmarks (Human3.6M and MPI-INF-3DHP) highlight the effectiveness and efficiency of PRPose. Code is available at: https://github.com/xzhouzeng/PRPose.

This paper presents an analysis of how Linux's performance has evolved over the past seven years. Unlike recent works that focus on OS performance in terms of scalability or service of a particular workload, this study goes back to basics: the latency of core kernel operations (e.g., system calls, context switching, etc.). To our surprise, the study shows that the performance of many core operations has worsened or fluctuated significantly over the years. For example, the select system call is 100% slower than it was just two years ago. An in-depth analysis shows that over the past seven years, core kernel subsystems have been forced to accommodate an increasing number of security enhancements and new features. These additions steadily add overhead to core kernel operations but also frequently introduce extreme slowdowns of more than 100%. In addition, simple misconfigurations have also severely impacted kernel performance. Overall, we find most of the slowdowns can be attributed to 11 changes.