arXiv subjects

Ziyu Liu

Publications and source records attributed to Ziyu Liu.

At least 73 records · Page 4Linked to original sources

arXiv2025

Asteroid (4337) Arecibo: Two ice-rich bodies forming a binary -- Based on Gaia astrometric data

Context. Binary asteroids are present in all populations of the Solar System, from near-Earth to trans-Neptunian regions. As is true for the small Solar System bodies (SSSBs), binary asteroids generally offer valuable insights into the formation of the Solar System, as well as its collisions and dynamic evolution. In particular, the binaries provide fundamental quantities and properties of these SSSBs, such as mass, angular momentum, and density, all of which are often hidden. The direct measurement of densities and porosities is of great value in revealing the gravitational aggregates and icy bodies that form the asteroid-comet continuum. Aims. Several observation techniques from space and ground-based platforms have provided many results in this regard. Here we show the value of the Gaia mission and its high-precision astrometry for analysing asteroid binaries and for individually deriving the masses of the components. Methods. We focus on the binary asteroid (4337) Arecibo, a member of the Themis family. We analysed the astrometry obtained in the Gaia FPR catalogue release, and performed orbital fitting for both the heliocentric orbit of the system and the relative orbit of the binary components. Results. We obtain an estimation of the component masses and their flux ratio, and derive bulk densities rho1 = 1.2 and rho2 = 1.6 for the primary and the secondary, respectively. The results are consistent with an ice-rich body in the outer main belt. They also show a significantly denser secondary or a less closely packed primary. Constraints on these densities and on macroscopic porosities are nevertheless limited by our poor knowledge of the sizes of the components. Observations of future mutual events, and of stellar occultations predicted in 2024 - 2025, will be essential for improving our knowledge of this system and its formation.

astro-ph.EP↗

arXiv2025

Notes on eventual continuity and ergodicity for SPDEs

These notes present an alternative approach to the asymptotic stability of stochastic partial differential equations driven by multiplicative noise, applicable to a wide range of dissipative systems. The method builds on general criteria established in \cite{GLLL2024b,L2023}, utilizing the eventual continuity and generalized coupling techniques.

math.PR↗

arXiv2025

Asymptotic stability for non-equicontinuous Markov semigroups

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.

math.PR↗

arXiv2025

Visual-RFT: Visual Reinforcement Fine-Tuning

Reinforcement Fine-Tuning (RFT) in Large Reasoning Models like OpenAI o1 learns from feedback on its answers, which is especially useful in applications when fine-tuning data is scarce. Recent open-source work like DeepSeek-R1 demonstrates that reinforcement learning with verifiable reward is one key direction in reproducing o1. While the R1-style model has demonstrated success in language models, its application in multi-modal domains remains under-explored. This work introduces Visual Reinforcement Fine-Tuning (Visual-RFT), which further extends the application areas of RFT on visual tasks. Specifically, Visual-RFT first uses Large Vision-Language Models (LVLMs) to generate multiple responses containing reasoning tokens and final answers for each input, and then uses our proposed visual perception verifiable reward functions to update the model via the policy optimization algorithm such as Group Relative Policy Optimization (GRPO). We design different verifiable reward functions for different perception tasks, such as the Intersection over Union (IoU) reward for object detection. Experimental results on fine-grained image classification, few-shot object detection, reasoning grounding, as well as open-vocabulary object detection benchmarks show the competitive performance and advanced generalization ability of Visual-RFT compared with Supervised Fine-tuning (SFT). For example, Visual-RFT improves accuracy by $24.3\%$ over the baseline in one-shot fine-grained image classification with around 100 samples. In few-shot object detection, Visual-RFT also exceeds the baseline by $21.9$ on COCO's two-shot setting and $15.4$ on LVIS. Our Visual-RFT represents a paradigm shift in fine-tuning LVLMs, offering a data-efficient, reward-driven approach that enhances reasoning and adaptability for domain-specific tasks.

cs.CV↗

arXiv2025

Large Language Models for Bioinformatics

With the rapid advancements in large language model (LLM) technology and the emergence of bioinformatics-specific language models (BioLMs), there is a growing need for a comprehensive analysis of the current landscape, computational characteristics, and diverse applications. This survey aims to address this need by providing a thorough review of BioLMs, focusing on their evolution, classification, and distinguishing features, alongside a detailed examination of training methodologies, datasets, and evaluation frameworks. We explore the wide-ranging applications of BioLMs in critical areas such as disease diagnosis, drug discovery, and vaccine development, highlighting their impact and transformative potential in bioinformatics. We identify key challenges and limitations inherent in BioLMs, including data privacy and security concerns, interpretability issues, biases in training data and model outputs, and domain adaptation complexities. Finally, we highlight emerging trends and future directions, offering valuable insights to guide researchers and clinicians toward advancing BioLMs for increasingly sophisticated biological and clinical applications.

q-bio.QM↗

arXiv2024

Ergodicity for eventually continuous Markov--Feller semigroups on Polish spaces

This paper investigates the ergodicity of Markov--Feller semigroups on Polish spaces, focusing on very weak regularity conditions, particularly the Cesàro eventual continuity. First, it is showed that the Cesàro average of such semigroups weakly converges to an ergodic measure when starting from its support. This leads to a characterization of the relationship between Cesàro eventual continuity, Cesàro e-property, and weak-* mean ergodicity. Next, serval criteria are provided for the existence and uniqueness of invariant measures via Cesàro eventual continuity and lower bound conditions, establishing an equivalence relation between weak-* mean ergodicity and a lower bound condition. Additionally, some refined properties of ergodic decomposition are derived. Finally, the results are applied to several non-trivial examples, including iterated function systems, Hopf's turbulence model with random forces, and Lorenz system with noisy perturbations, either with or without Cesàro eventual continuity.

math.PR↗

arXiv2024

MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations

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

cs.CV↗

arXiv2024

MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs

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.

cs.CV↗

arXiv2024

MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models

Visual preference alignment involves training Large Vision-Language Models (LVLMs) to predict human preferences between visual inputs. This is typically achieved by using labeled datasets of chosen/rejected pairs and employing optimization algorithms like direct preference optimization (DPO). Existing visual alignment methods, primarily designed for single-image scenarios, struggle to effectively handle the complexity of multi-image tasks due to the scarcity of diverse training data and the high cost of annotating chosen/rejected pairs. We present Multi-Image Augmented Direct Preference Optimization (MIA-DPO), a visual preference alignment approach that effectively handles multi-image inputs. MIA-DPO mitigates the scarcity of diverse multi-image training data by extending single-image data with unrelated images arranged in grid collages or pic-in-pic formats, significantly reducing the costs associated with multi-image data annotations. Our observation reveals that attention values of LVLMs vary considerably across different images. We use attention values to identify and filter out rejected responses the model may have mistakenly focused on. Our attention-aware selection for constructing the chosen/rejected pairs without relying on (i) human annotation, (ii) extra data, and (iii) external models or APIs. MIA-DPO is compatible with various architectures and outperforms existing methods on five multi-image benchmarks, achieving an average performance boost of 3.0% on LLaVA-v1.5 and 4.3% on the recent InternLM-XC2.5. Moreover, MIA-DPO has a minimal effect on the model's ability to understand single images.

cs.CV↗

arXiv2024

Local large deviations for randomly forced nonlinear wave equations with localized damping

We study the large deviation principle (LDP) for locally damped nonlinear wave equations perturbed by a bounded noise. When the noise is sufficiently non-degenerate, we establish the LDP for empirical distributions with lower bound of a local type. The primary challenge is the lack of compactness due to the absence of smoothing effect. This is overcome by exploiting the asymptotic compactness for the dynamics of waves, introducing the concept of asymptotic exponential tightness for random measures, and establishing a new LDP approach for random dynamical systems.

math.AP↗

arXiv2024

Exponential mixing for random nonlinear wave equations: weak dissipation and localized control

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.

math.AP↗

arXiv2024

Guidelines for Augmentation Selection in Contrastive Learning for Time Series Classification

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.

cs.LG↗

arXiv2024

V3Det Challenge 2024 on Vast Vocabulary and Open Vocabulary Object Detection: Methods and Results

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

cs.CV↗

arXiv2024

TinyLLaVA Factory: A Modularized Codebase for Small-scale Large Multimodal Models

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.

cs.LG↗

arXiv2024

TBNet: A Neural Architectural Defense Framework Facilitating DNN Model Protection in Trusted Execution Environments

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.

cs.CR↗

arXiv2024

Self-Supervised Learning for Time Series: Contrastive or Generative?

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}.

cs.LG↗

arXiv2023

MirrorNet: A TEE-Friendly Framework for Secure On-device DNN Inference

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.

cs.CR↗

arXiv2023

Charge-transfer Contact to a High-Mobility Monolayer Semiconductor

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.

cond-mat.mes-hall↗