Search

We establish a new criterion for exponential mixing of random dynamical systems. Our criterion is applicable to a wide range of systems, including in particular dispersive equations. Its verification is in nature related to several topics, i.e., asymptotic compactness in dynamical systems, global stability of evolution equations, and localized control problems. As an initial application, we exploit the exponential mixing of random nonlinear wave equations with degenerate damping, critical nonlinearity, and physically localized noise. The essential challenge lies in the fact that the weak dissipation and randomness interact in the evolution.

The universality of deep neural networks across different modalities and their generalization capabilities to unseen domains play an essential role in medical image segmentation. The recent Segment Anything Model (SAM) has demonstrated its potential in both settings. However, the huge computational costs, demand for manual annotations as prompts and conflict-prone decoding process of SAM degrade its generalizability and applicability in clinical scenarios. To address these issues, we propose an efficient self-prompting SAM for universal domain-generalized medical image segmentation, named ESP-MedSAM. Specifically, we first devise the Multi-Modal Decoupled Knowledge Distillation (MMDKD) strategy to construct a lightweight semi-parameter sharing image encoder that produces discriminative visual features for diverse modalities. Further, we introduce the Self-Patch Prompt Generator (SPPG) to automatically generate high-quality dense prompt embeddings for guiding segmentation decoding. Finally, we design the Query-Decoupled Modality Decoder (QDMD) that leverages a one-to-one strategy to provide an independent decoding channel for every modality. Extensive experiments indicate that ESP-MedSAM outperforms state-of-the-arts in diverse medical imaging segmentation tasks, displaying superior modality universality and generalization capabilities. Especially, ESP-MedSAM uses only 4.5\% parameters compared to SAM-H. The source code is available at https://github.com/xq141839/ESP-MedSAM., Comment: Under Review

Self-supervised contrastive learning has become a key technique in deep learning, particularly in time series analysis, due to its ability to learn meaningful representations without explicit supervision. Augmentation is a critical component in contrastive learning, where different augmentations can dramatically impact performance, sometimes influencing accuracy by over 30%. However, the selection of augmentations is predominantly empirical which can be suboptimal, or grid searching that is time-consuming. In this paper, we establish a principled framework for selecting augmentations based on dataset characteristics such as trend and seasonality. Specifically, we construct 12 synthetic datasets incorporating trend, seasonality, and integration weights. We then evaluate the effectiveness of 8 different augmentations across these synthetic datasets, thereby inducing generalizable associations between time series characteristics and augmentation efficiency. Additionally, we evaluated the induced associations across 6 real-world datasets encompassing domains such as activity recognition, disease diagnosis, traffic monitoring, electricity usage, mechanical fault prognosis, and finance. These real-world datasets are diverse, covering a range from 1 to 12 channels, 2 to 10 classes, sequence lengths of 14 to 1280, and data frequencies from 250 Hz to daily intervals. The experimental results show that our proposed trend-seasonality-based augmentation recommendation algorithm can accurately identify the effective augmentations for a given time series dataset, achieving an average Recall@3 of 0.667, outperforming baselines. Our work provides guidance for studies employing contrastive learning in time series analysis, with wide-ranging applications. All the code, datasets, and analysis results will be released at https://github.com/DL4mHealth/TS-Contrastive-Augmentation-Recommendation., Comment: 20 pages, 11 figures

Understanding documents with rich layouts and multi-modal components is a long-standing and practical task. Recent Large Vision-Language Models (LVLMs) have made remarkable strides in various tasks, particularly in single-page document understanding (DU). However, their abilities on long-context DU remain an open problem. This work presents MMLongBench-Doc, a long-context, multi-modal benchmark comprising 1,062 expert-annotated questions. Distinct from previous datasets, it is constructed upon 130 lengthy PDF-formatted documents with an average of 49.4 pages and 20,971 textual tokens. Towards comprehensive evaluation, answers to these questions rely on pieces of evidence from (1) different sources (text, image, chart, table, and layout structure) and (2) various locations (i.e. page number). Moreover, 33.2% of the questions are cross-page questions requiring evidence across multiple pages. 22.8% of the questions are designed to be unanswerable for detecting potential hallucinations. Experiments on 14 LVLMs demonstrate that long-context DU greatly challenges current models. Notably, the best-performing model, GPT-4o, achieves an F1 score of only 42.7%, while the second-best, GPT-4V, scores 31.4%. Furthermore, 12 LVLMs (all except GPT-4o and GPT-4V) even present worse performance than their LLM counterparts which are fed with lossy-parsed OCR documents. These results validate the necessity of future research toward more capable long-context LVLMs. Project Page: https://mayubo2333.github.io/MMLongBench-Doc

Generating natural and meaningful responses to communicate with multi-modal human inputs is a fundamental capability of Large Vision-Language Models(LVLMs). While current open-source LVLMs demonstrate promising performance in simplified scenarios such as single-turn single-image input, they fall short in real-world conversation scenarios such as following instructions in a long context history with multi-turn and multi-images. Existing LVLM benchmarks primarily focus on single-choice questions or short-form responses, which do not adequately assess the capabilities of LVLMs in real-world human-AI interaction applications. Therefore, we introduce MMDU, a comprehensive benchmark, and MMDU-45k, a large-scale instruction tuning dataset, designed to evaluate and improve LVLMs' abilities in multi-turn and multi-image conversations. We employ the clustering algorithm to ffnd the relevant images and textual descriptions from the open-source Wikipedia and construct the question-answer pairs by human annotators with the assistance of the GPT-4o model. MMDU has a maximum of 18k image+text tokens, 20 images, and 27 turns, which is at least 5x longer than previous benchmarks and poses challenges to current LVLMs. Our in-depth analysis of 15 representative LVLMs using MMDU reveals that open-source LVLMs lag behind closed-source counterparts due to limited conversational instruction tuning data. We demonstrate that ffne-tuning open-source LVLMs on MMDU-45k signiffcantly address this gap, generating longer and more accurate conversations, and improving scores on MMDU and existing benchmarks (MMStar: +1.1%, MathVista: +1.5%, ChartQA:+1.2%). Our contributions pave the way for bridging the gap between current LVLM models and real-world application demands. This project is available at https://github.com/Liuziyu77/MMDU., Comment: This project is available at https://github.com/Liuziyu77/MMDU

Detecting objects in real-world scenes is a complex task due to various challenges, including the vast range of object categories, and potential encounters with previously unknown or unseen objects. The challenges necessitate the development of public benchmarks and challenges to advance the field of object detection. Inspired by the success of previous COCO and LVIS Challenges, we organize the V3Det Challenge 2024 in conjunction with the 4th Open World Vision Workshop: Visual Perception via Learning in an Open World (VPLOW) at CVPR 2024, Seattle, US. This challenge aims to push the boundaries of object detection research and encourage innovation in this field. The V3Det Challenge 2024 consists of two tracks: 1) Vast Vocabulary Object Detection: This track focuses on detecting objects from a large set of 13204 categories, testing the detection algorithm's ability to recognize and locate diverse objects. 2) Open Vocabulary Object Detection: This track goes a step further, requiring algorithms to detect objects from an open set of categories, including unknown objects. In the following sections, we will provide a comprehensive summary and analysis of the solutions submitted by participants. By analyzing the methods and solutions presented, we aim to inspire future research directions in vast vocabulary and open-vocabulary object detection, driving progress in this field. Challenge homepage: https://v3det.openxlab.org.cn/challenge

We present TinyLLaVA Factory, an open-source modular codebase for small-scale large multimodal models (LMMs) with a focus on simplicity of code implementations, extensibility of new features, and reproducibility of training results. Following the design philosophy of the factory pattern in software engineering, TinyLLaVA Factory modularizes the entire system into interchangeable components, with each component integrating a suite of cutting-edge models and methods, meanwhile leaving room for extensions to more features. In addition to allowing users to customize their own LMMs, TinyLLaVA Factory provides popular training recipes to let users pretrain and finetune their models with less coding effort. Empirical experiments validate the effectiveness of our codebase. The goal of TinyLLaVA Factory is to assist researchers and practitioners in exploring the wide landscape of designing and training small-scale LMMs with affordable computational resources., Comment: Our codebase is made public at https://github.com/TinyLLaVA/TinyLLaVA_Factory with documentation available at https://tinyllava-factory.readthedocs.io/en/latest/

Trusted Execution Environments (TEEs) have become a promising solution to secure DNN models on edge devices. However, the existing solutions either provide inadequate protection or introduce large performance overhead. Taking both security and performance into consideration, this paper presents TBNet, a TEE-based defense framework that protects DNN model from a neural architectural perspective. Specifically, TBNet generates a novel Two-Branch substitution model, to respectively exploit (1) the computational resources in the untrusted Rich Execution Environment (REE) for latency reduction and (2) the physically-isolated TEE for model protection. Experimental results on a Raspberry Pi across diverse DNN model architectures and datasets demonstrate that TBNet achieves efficient model protection at a low cost.

CLIP (Contrastive Language-Image Pre-training) uses contrastive learning from noise image-text pairs to excel at recognizing a wide array of candidates, yet its focus on broad associations hinders the precision in distinguishing subtle differences among fine-grained items. Conversely, Multimodal Large Language Models (MLLMs) excel at classifying fine-grained categories, thanks to their substantial knowledge from pre-training on web-level corpora. However, the performance of MLLMs declines with an increase in category numbers, primarily due to growing complexity and constraints of limited context window size. To synergize the strengths of both approaches and enhance the few-shot/zero-shot recognition abilities for datasets characterized by extensive and fine-grained vocabularies, this paper introduces RAR, a Retrieving And Ranking augmented method for MLLMs. We initially establish a multi-modal retriever based on CLIP to create and store explicit memory for different categories beyond the immediate context window. During inference, RAR retrieves the top-k similar results from the memory and uses MLLMs to rank and make the final predictions. Our proposed approach not only addresses the inherent limitations in fine-grained recognition but also preserves the model's comprehensive knowledge base, significantly boosting accuracy across a range of vision-language recognition tasks. Notably, our approach demonstrates a significant improvement in performance on 5 fine-grained visual recognition benchmarks, 11 few-shot image recognition datasets, and the 2 object detection datasets under the zero-shot recognition setting., Comment: Project: https://github.com/Liuziyu77/RAR

Self-supervised learning (SSL) has recently emerged as a powerful approach to learning representations from large-scale unlabeled data, showing promising results in time series analysis. The self-supervised representation learning can be categorized into two mainstream: contrastive and generative. In this paper, we will present a comprehensive comparative study between contrastive and generative methods in time series. We first introduce the basic frameworks for contrastive and generative SSL, respectively, and discuss how to obtain the supervision signal that guides the model optimization. We then implement classical algorithms (SimCLR vs. MAE) for each type and conduct a comparative analysis in fair settings. Our results provide insights into the strengths and weaknesses of each approach and offer practical recommendations for choosing suitable SSL methods. We also discuss the implications of our findings for the broader field of representation learning and propose future research directions. All the code and data are released at \url{https://github.com/DL4mHealth/SSL_Comparison}., Comment: Published at the AI4TS Workshop, IJCAI 2023

Deep neural network (DNN) models have become prevalent in edge devices for real-time inference. However, they are vulnerable to model extraction attacks and require protection. Existing defense approaches either fail to fully safeguard model confidentiality or result in significant latency issues. To overcome these challenges, this paper presents MirrorNet, which leverages Trusted Execution Environment (TEE) to enable secure on-device DNN inference. It generates a TEE-friendly implementation for any given DNN model to protect the model confidentiality, while meeting the stringent computation and storage constraints of TEE. The framework consists of two key components: the backbone model (BackboneNet), which is stored in the normal world but achieves lower inference accuracy, and the Companion Partial Monitor (CPM), a lightweight mirrored branch stored in the secure world, preserving model confidentiality. During inference, the CPM monitors the intermediate results from the BackboneNet and rectifies the classification output to achieve higher accuracy. To enhance flexibility, MirrorNet incorporates two modules: the CPM Strategy Generator, which generates various protection strategies, and the Performance Emulator, which estimates the performance of each strategy and selects the most optimal one. Extensive experiments demonstrate the effectiveness of MirrorNet in providing security guarantees while maintaining low computation latency, making MirrorNet a practical and promising solution for secure on-device DNN inference. For the evaluation, MirrorNet can achieve a 18.6% accuracy gap between authenticated and illegal use, while only introducing 0.99% hardware overhead., Comment: Accepted by ICCAD 2023

Two-dimensional (2D) semiconductors, such as the transition metal dichalcogenides, have demonstrated tremendous promise for the development of highly tunable quantum devices. Realizing this potential requires low-resistance electrical contacts that perform well at low temperatures and low densities where quantum properties are relevant. Here we present a new device architecture for 2D semiconductors that utilizes a charge-transfer layer to achieve large hole doping in the contact region, and implement this technique to measure magneto-transport properties of high-purity monolayer WSe$_2$. We measure a record-high hole mobility of 80,000 cm$^2$/Vs and access channel carrier densities as low as $1.6\times10^{11}$ cm$^{-2}$, an order of magnitude lower than previously achievable. Our ability to realize transparent contact to high-mobility devices at low density enables transport measurement of correlation-driven quantum phases including observation of a low temperature metal-insulator transition in a density and temperature regime where Wigner crystal formation is expected, and observation of the fractional quantum Hall effect under large magnetic fields. The charge transfer contact scheme paves the way for discovery and manipulation of new quantum phenomena in 2D semiconductors and their heterostructures.

Medical image segmentation is critical for diagnosing and treating spinal disorders. However, the presence of high noise, ambiguity, and uncertainty makes this task highly challenging. Factors such as unclear anatomical boundaries, inter-class similarities, and irrational annotations contribute to this challenge. Achieving both accurate and diverse segmentation templates is essential to support radiologists in clinical practice. In recent years, denoising diffusion probabilistic modeling (DDPM) has emerged as a prominent research topic in computer vision. It has demonstrated effectiveness in various vision tasks, including image deblurring, super-resolution, anomaly detection, and even semantic representation generation at the pixel level. Despite the robustness of existing diffusion models in visual generation tasks, they still struggle with discrete masks and their various effects. To address the need for accurate and diverse spine medical image segmentation templates, we propose an end-to-end framework called VerseDiff-UNet, which leverages the denoising diffusion probabilistic model (DDPM). Our approach integrates the diffusion model into a standard U-shaped architecture. At each step, we combine the noise-added image with the labeled mask to guide the diffusion direction accurately towards the target region. Furthermore, to capture specific anatomical a priori information in medical images, we incorporate a shape a priori module. This module efficiently extracts structural semantic information from the input spine images. We evaluate our method on a single dataset of spine images acquired through X-ray imaging. Our results demonstrate that VerseDiff-UNet significantly outperforms other state-of-the-art methods in terms of accuracy while preserving the natural features and variations of anatomy.

Given a topologically transitive subshift of finite type, the $u$-dimension of the $\alpha$-level set of the quotient of Birkhoff sums is a well-studied topic. In this paper, we consider the uniform $\alpha$-level set, which is a subset of the $\alpha$-level set. We shall show that the $\alpha$-level set and the uniform $\alpha$-level set have the same $u$-dimension. Moreover, we also consider two types of subsets of the $\alpha$-level set, whose elements are sequences satisfying some constraints on their subwords. We shall show that for $\alpha$ not on the boundary of the dimension spectrum, these subsets also have the same $u$-dimension as the $\alpha$-level set. As an application, we shall perform a multifractal analysis of the Hoelder regularity of a Gibbs measure on a one-dimensional manifold.

We formulate a new criterion of the asymptotic stability for some non-equicontinuous Markov semigroups, the so-called eventually continuous semigroups. In particular, we provide a non-equicontinuous Markov semigroup example with essential randomness, which is asymptotically stable.

We investigate the relation between the e-property and the eventual continuity, or called the asymptotic equicontinuity, which is a generalization of the e-property. We prove that, for any discrete-time or strongly continuous continuous-time eventually continuous Markov-Feller semigroup with an ergodic measure, if the interior of the support of the ergodic measure is nonempty, then the e-property is satisfied on the interior of the support. In particular, it implies that, restricted on the support of each ergodic measure, the e-property and the eventual continuity are equivalent for the discrete-time and the strongly continuous continuous-time Markov-Feller semigroups.

Personalized federated learning considers learning models unique to each client in a heterogeneous network. The resulting client-specific models have been purported to improve metrics such as accuracy, fairness, and robustness in federated networks. However, despite a plethora of work in this area, it remains unclear: (1) which personalization techniques are most effective in various settings, and (2) how important personalization truly is for realistic federated applications. To better answer these questions, we propose Motley, a benchmark for personalized federated learning. Motley consists of a suite of cross-device and cross-silo federated datasets from varied problem domains, as well as thorough evaluation metrics for better understanding the possible impacts of personalization. We establish baselines on the benchmark by comparing a number of representative personalized federated learning methods. These initial results highlight strengths and weaknesses of existing approaches, and raise several open questions for the community. Motley aims to provide a reproducible means with which to advance developments in personalized and heterogeneity-aware federated learning, as well as the related areas of transfer learning, meta-learning, and multi-task learning., Comment: 40 pages, 10 figures, 7 tables. EMNIST and Landmarks fine-tuning results are corrected in (and after) v5. Code: https://github.com/google-research/federated/tree/master/personalization_benchmark

While the application of differential privacy (DP) has been well-studied in cross-device federated learning (FL), there is a lack of work considering DP and its implications for cross-silo FL, a setting characterized by a limited number of clients each containing many data subjects. In cross-silo FL, usual notions of client-level DP are less suitable as real-world privacy regulations typically concern the in-silo data subjects rather than the silos themselves. In this work, we instead consider an alternative notion of silo-specific sample-level DP, where silos set their own privacy targets for their local examples. Under this setting, we reconsider the roles of personalization in federated learning. In particular, we show that mean-regularized multi-task learning (MR-MTL), a simple personalization framework, is a strong baseline for cross-silo FL: under stronger privacy requirements, silos are incentivized to federate more with each other to mitigate DP noise, resulting in consistent improvements relative to standard baseline methods. We provide an empirical study of competing methods as well as a theoretical characterization of MR-MTL for mean estimation, highlighting the interplay between privacy and cross-silo data heterogeneity. Our work serves to establish baselines for private cross-silo FL as well as identify key directions of future work in this area., Comment: NeurIPS 2022, 37 pages

Impacts of domain textures on low-lying neutral excitations in the bulk of fractional quantum Hall effect (FQHE) systems are probed by resonant inelastic light scattering. We demonstrate that large domains of quantum fluids support long-wavelength neutral collective excitations with well-defined wave vector (momentum) dispersion that could be interpreted by theories for uniform phases. Access to dispersive low-lying neutral collective modes in large domains of FQHE fluids such as long wavelength magnetorotons at filling factor v=1/3 offer significant experimental access to strong electron correlation physics in the FQHE., Comment: 11 pages, 4 figures, and Supplemental Material