arXiv subjects

Liang Zhao

Publications and source records attributed to Liang Zhao.

At least 235 records · Page 13Linked to original sources

arXiv2024

Investigating and Mitigating the Multimodal Hallucination Snowballing in Large Vision-Language Models

Though advanced in understanding visual information with human languages, Large Vision-Language Models (LVLMs) still suffer from multimodal hallucinations. A natural concern is that during multimodal interaction, the generated hallucinations could influence the LVLMs' subsequent generation. Thus, we raise a question: When presented with a query relevant to the previously generated hallucination, will LVLMs be misled and respond incorrectly, even though the ground visual information exists? To answer this, we propose a framework called MMHalSnowball to evaluate LVLMs' behaviors when encountering generated hallucinations, where LVLMs are required to answer specific visual questions within a curated hallucinatory conversation. Crucially, our experiment shows that the performance of open-source LVLMs drops by at least $31\%$, indicating that LVLMs are prone to accept the generated hallucinations and make false claims that they would not have supported without distractions. We term this phenomenon Multimodal Hallucination Snowballing. To mitigate this, we further propose a training-free method called Residual Visual Decoding, where we revise the output distribution of LVLMs with the one derived from the residual visual input, providing models with direct access to the visual information. Experiments show that our method can mitigate more than $24\%$ of the snowballed multimodal hallucination while maintaining capabilities.

cs.CV↗

arXiv2024

GraphSL: An Open-Source Library for Graph Source Localization Approaches and Benchmark Datasets

We introduce GraphSL, a new library for studying the graph source localization problem. graph diffusion and graph source localization are inverse problems in nature: graph diffusion predicts information diffusions from information sources, while graph source localization predicts information sources from information diffusions. GraphSL facilitates the exploration of various graph diffusion models for simulating information diffusions and enables the evaluation of cutting-edge source localization approaches on established benchmark datasets. The source code of GraphSL is made available at Github Repository (https://github.com/xianggebenben/GraphSL). Bug reports and feedback can be directed to the Github issues page (https://github.com/xianggebenben/GraphSL/issues).

cs.LG↗

arXiv2024

CLII: Visual-Text Inpainting via Cross-Modal Predictive Interaction

Image inpainting aims to fill missing pixels in damaged images and has achieved significant progress with cut-edging learning techniques. Nevertheless, state-of-the-art inpainting methods are mainly designed for nature images and cannot correctly recover text within scene text images, and training existing models on the scene text images cannot fix the issues. In this work, we identify the visual-text inpainting task to achieve high-quality scene text image restoration and text completion: Given a scene text image with unknown missing regions and the corresponding text with unknown missing characters, we aim to complete the missing information in both images and text by leveraging their complementary information. Intuitively, the input text, even if damaged, contains language priors of the contents within the images and can guide the image inpainting. Meanwhile, the scene text image includes the appearance cues of the characters that could benefit text recovery. To this end, we design the cross-modal predictive interaction (CLII) model containing two branches, i.e., ImgBranch and TxtBranch, for scene text inpainting and text completion, respectively while leveraging their complementary effectively. Moreover, we propose to embed our model into the SOTA scene text spotting method and significantly enhance its robustness against missing pixels, which demonstrates the practicality of the newly developed task. To validate the effectiveness of our method, we construct three real datasets based on existing text-related datasets, containing 1838 images and covering three scenarios with curved, incidental, and styled texts, and conduct extensive experiments to show that our method outperforms baselines significantly.

cs.CV↗

arXiv2024

Skywork-Math: Data Scaling Laws for Mathematical Reasoning in Large Language Models -- The Story Goes On

In this paper, we investigate the underlying factors that potentially enhance the mathematical reasoning capabilities of large language models (LLMs). We argue that the data scaling law for math reasoning capabilities in modern LLMs is far from being saturated, highlighting how the model's quality improves with increases in data quantity. To support this claim, we introduce the Skywork-Math model series, supervised fine-tuned (SFT) on common 7B LLMs using our proposed 2.5M-instance Skywork-MathQA dataset. Skywork-Math 7B has achieved impressive accuracies of 51.2% on the competition-level MATH benchmark and 83.9% on the GSM8K benchmark using only SFT data, outperforming an early version of GPT-4 on MATH. The superior performance of Skywork-Math models contributes to our novel two-stage data synthesis and model SFT pipelines, which include three different augmentation methods and a diverse seed problem set, ensuring both the quantity and quality of Skywork-MathQA dataset across varying difficulty levels. Most importantly, we provide several practical takeaways to enhance math reasoning abilities in LLMs for both research and industry applications.

cs.AI↗

arXiv2024

Asymmetric fluctuations and self-folding of active interfaces

We study the structure and dynamics of the interface separating a passive fluid from a microtubule-based active fluid. Turbulent-like active flows power giant interfacial fluctuations, which exhibit pronounced asymmetry between regions of positive and negative curvature. Experiments, numerical simulations, and theoretical arguments reveal how the interface breaks up the spatial symmetry of the fundamental bend instability to generate local vortical flows that lead to asymmetric interface fluctuations. The magnitude of interface deformations increases with activity: In the high activity limit, the interface self-folds invaginating passive droplets and generating a foam-like phase, where active fluid is perforated with passive droplets. These results demonstrate how active stresses control the structure, dynamics, and break-up of soft, deformable, and reconfigurable liquid-liquid interfaces.

cond-mat.soft↗

arXiv2024

Merlin:Empowering Multimodal LLMs with Foresight Minds

Humans possess the remarkable ability to foresee the future to a certain extent based on present observations, a skill we term as foresight minds. However, this capability remains largely under explored within existing Multimodal Large Language Models (MLLMs), hindering their capacity to learn the fundamental principles of how things operate and the intentions behind the observed subjects. To address this issue, we introduce the integration of future modeling into the existing learning frameworks of MLLMs. By utilizing the subject trajectory, a highly structured representation of a consecutive frame sequence, as a learning objective, we aim to bridge the gap between the past and the future. We propose two innovative methods to empower MLLMs with foresight minds, Foresight Pre-Training (FPT) and Foresight Instruction-Tuning (FIT), which are inspired by the modern learning paradigm of LLMs. Specifically, FPT jointly training various tasks centered on trajectories, enabling MLLMs to learn how to attend and predict entire trajectories from a given initial observation. Then, FIT requires MLLMs to first predict trajectories of related objects and then reason about potential future events based on them. Aided by FPT and FIT, we build a novel and unified MLLM named Merlin that supports multi-images input and analysis about potential actions of multiple objects for the future reasoning. Experimental results show Merlin powerful foresight minds with impressive performance on both future reasoning and visual comprehension tasks.

cs.CV↗

arXiv2024

Self-consistent Deep Geometric Learning for Heterogeneous Multi-source Spatial Point Data Prediction

Multi-source spatial point data prediction is crucial in fields like environmental monitoring and natural resource management, where integrating data from various sensors is the key to achieving a holistic environmental understanding. Existing models in this area often fall short due to their domain-specific nature and lack a strategy for integrating information from various sources in the absence of ground truth labels. Key challenges include evaluating the quality of different data sources and modeling spatial relationships among them effectively. Addressing these issues, we introduce an innovative multi-source spatial point data prediction framework that adeptly aligns information from varied sources without relying on ground truth labels. A unique aspect of our method is the 'fidelity score,' a quantitative measure for evaluating the reliability of each data source. Furthermore, we develop a geo-location-aware graph neural network tailored to accurately depict spatial relationships between data points. Our framework has been rigorously tested on two real-world datasets and one synthetic dataset. The results consistently demonstrate its superior performance over existing state-of-the-art methods.

cs.LG↗

arXiv2024

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

We present DeepSeek-V2, a strong Mixture-of-Experts (MoE) language model characterized by economical training and efficient inference. It comprises 236B total parameters, of which 21B are activated for each token, and supports a context length of 128K tokens. DeepSeek-V2 adopts innovative architectures including Multi-head Latent Attention (MLA) and DeepSeekMoE. MLA guarantees efficient inference through significantly compressing the Key-Value (KV) cache into a latent vector, while DeepSeekMoE enables training strong models at an economical cost through sparse computation. Compared with DeepSeek 67B, DeepSeek-V2 achieves significantly stronger performance, and meanwhile saves 42.5% of training costs, reduces the KV cache by 93.3%, and boosts the maximum generation throughput to 5.76 times. We pretrain DeepSeek-V2 on a high-quality and multi-source corpus consisting of 8.1T tokens, and further perform Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) to fully unlock its potential. Evaluation results show that, even with only 21B activated parameters, DeepSeek-V2 and its chat versions still achieve top-tier performance among open-source models.

cs.CL↗

arXiv2024

A transformer boosted UNet for smoke segmentation in complex backgrounds in multispectral LandSat imagery

Many studies have been done to detect smokes from satellite imagery. However, these prior methods are not still effective in detecting various smokes in complex backgrounds. Smokes present challenges in detection due to variations in density, color, lighting, and backgrounds such as clouds, haze, and/or mist, as well as the contextual nature of thin smoke. This paper addresses these challenges by proposing a new segmentation model called VTrUNet which consists of a virtual band construction module to capture spectral patterns and a transformer boosted UNet to capture long range contextual features. The model takes imagery of six bands: red, green, blue, near infrared, and two shortwave infrared bands as input. To show the advantages of the proposed model, the paper presents extensive results for various possible model architectures improving UNet and draws interesting conclusions including that adding more modules to a model does not always lead to a better performance. The paper also compares the proposed model with very recently proposed and related models for smoke segmentation and shows that the proposed model performs the best and makes significant improvements on prediction performances

cs.CV↗

arXiv2024

Incorporating uncertainty quantification into travel mode choice modeling: a Bayesian neural network (BNN) approach and an uncertainty-guided active survey framework

Existing deep learning approaches for travel mode choice modeling fail to inform modelers about their prediction uncertainty. Even when facing scenarios that are out of the distribution of training data, which implies high prediction uncertainty, these approaches still provide deterministic answers, potentially leading to misguidance. To address this limitation, this study introduces the concept of uncertainty from the field of explainable artificial intelligence into travel mode choice modeling. We propose a Bayesian neural network-based travel mode prediction model (BTMP) that quantifies the uncertainty of travel mode predictions, enabling the model itself to "know" and "tell" what it doesn't know. With BTMP, we further propose an uncertainty-guided active survey framework, which dynamically formulates survey questions representing travel mode choice scenarios with high prediction uncertainty. Through iterative collection of responses to these dynamically tailored survey questions, BTMP is iteratively trained to achieve the desired accuracy faster with fewer questions, thereby reducing survey costs. Experimental validation using synthetic datasets confirms the effectiveness of BTMP in quantifying prediction uncertainty. Furthermore, experiments, utilizing both synthetic and real-world data, demonstrate that the BTMP model, trained with the uncertainty-guided active survey framework, requires 20% to 50% fewer survey responses to match the performance of the model trained on randomly collected survey data. Overall, the proposed BTMP model and active survey framework innovatively incorporate uncertainty quantification into travel mode choice modeling, providing model users with essential insights into prediction reliability while optimizing data collection for deep learning model training in a cost-efficient manner.

cs.LG↗

arXiv2024

A note for W^{1,p}(V) and W_0^{1,p}(V) on a locally finite graph

In this paper, we investigate the Sobolev spaces W^{1,p}(V) and W_0^{1,p}(V) on a locally finite graph G=(V,E), which are fundamental tools when we apply the variational methods to partial differential equations on graphs. As a key contribution of this note, we show that in general, W^{1,p}(V) is not equivalent to W_0^{1,p}(V) on locally finite graphs, which is different from the situation on Euclidean space R^N.

math.AP↗

arXiv2024

POND: Multi-Source Time Series Domain Adaptation with Information-Aware Prompt Tuning

Time series domain adaptation stands as a pivotal and intricate challenge with diverse applications, including but not limited to human activity recognition, sleep stage classification, and machine fault diagnosis. Despite the numerous domain adaptation techniques proposed to tackle this complex problem, they primarily focus on domain adaptation from a single source domain. Yet, it is more crucial to investigate domain adaptation from multiple domains due to the potential for greater improvements. To address this, three important challenges need to be overcome: 1). The lack of exploration to utilize domain-specific information for domain adaptation, 2). The difficulty to learn domain-specific information that changes over time, and 3). The difficulty to evaluate learned domain-specific information. In order to tackle these challenges simultaneously, in this paper, we introduce PrOmpt-based domaiN Discrimination (POND), the first framework to utilize prompts for time series domain adaptation. Specifically, to address Challenge 1, we extend the idea of prompt tuning to time series analysis and learn prompts to capture common and domain-specific information from all source domains. To handle Challenge 2, we introduce a conditional module for each source domain to generate prompts from time series input data. For Challenge 3, we propose two criteria to select good prompts, which are used to choose the most suitable source domain for domain adaptation. The efficacy and robustness of our proposed POND model are extensively validated through experiments across 50 scenarios encompassing four datasets. Experimental results demonstrate that our proposed POND model outperforms all state-of-the-art comparison methods by up to $66\%$ on the F1-score.

cs.LG↗

arXiv2024

Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models

In this technical report, we introduce the training methodologies implemented in the development of Skywork-MoE, a high-performance mixture-of-experts (MoE) large language model (LLM) with 146 billion parameters and 16 experts. It is initialized from the pre-existing dense checkpoints of our Skywork-13B model. We explore the comparative effectiveness of upcycling versus training from scratch initializations. Our findings suggest that the choice between these two approaches should consider both the performance of the existing dense checkpoints and the MoE training budget. We highlight two innovative techniques: gating logit normalization, which improves expert diversification, and adaptive auxiliary loss coefficients, allowing for layer-specific adjustment of auxiliary loss coefficients. Our experimental results validate the effectiveness of these methods. Leveraging these techniques and insights, we trained our upcycled Skywork-MoE on a condensed subset of our SkyPile corpus. The evaluation results demonstrate that our model delivers strong performance across a wide range of benchmarks.

cs.CL↗

arXiv2024

LongSkywork: A Training Recipe for Efficiently Extending Context Length in Large Language Models

We introduce LongSkywork, a long-context Large Language Model (LLM) capable of processing up to 200,000 tokens. We provide a training recipe for efficiently extending context length of LLMs. We identify that the critical element in enhancing long-context processing capability is to incorporate a long-context SFT stage following the standard SFT stage. A mere 200 iterations can convert the standard SFT model into a long-context model. To reduce the effort in collecting and annotating data for long-context language modeling, we develop two novel methods for creating synthetic data. These methods are applied during the continual pretraining phase as well as the Supervised Fine-Tuning (SFT) phase, greatly enhancing the training efficiency of our long-context LLMs. Our findings suggest that synthetic long-context SFT data can surpass the performance of data curated by humans to some extent. LongSkywork achieves outstanding performance on a variety of long-context benchmarks. In the Needle test, a benchmark for long-context information retrieval, our models achieved perfect accuracy across multiple context spans. Moreover, in realistic application scenarios, LongSkywork-13B demonstrates performance on par with Claude2.1, the leading long-context model, underscoring the effectiveness of our proposed methods.

cs.CL↗

arXiv2024

TAGA: Text-Attributed Graph Self-Supervised Learning by Synergizing Graph and Text Mutual Transformations

Text-Attributed Graphs (TAGs) enhance graph structures with natural language descriptions, enabling detailed representation of data and their relationships across a broad spectrum of real-world scenarios. Despite the potential for deeper insights, existing TAG representation learning primarily relies on supervised methods, necessitating extensive labeled data and limiting applicability across diverse contexts. This paper introduces a new self-supervised learning framework, Text-And-Graph Multi-View Alignment (TAGA), which overcomes these constraints by integrating TAGs' structural and semantic dimensions. TAGA constructs two complementary views: Text-of-Graph view, which organizes node texts into structured documents based on graph topology, and the Graph-of-Text view, which converts textual nodes and connections into graph data. By aligning representations from both views, TAGA captures joint textual and structural information. In addition, a novel structure-preserving random walk algorithm is proposed for efficient training on large-sized TAGs. Our framework demonstrates strong performance in zero-shot and few-shot scenarios across eight real-world datasets.

cs.LG↗

arXiv2024

Network Interdiction Goes Neural

Network interdiction problems are combinatorial optimization problems involving two players: one aims to solve an optimization problem on a network, while the other seeks to modify the network to thwart the first player's objectives. Such problems typically emerge in an attacker-defender context, encompassing areas such as military operations, disease spread analysis, and communication network management. The primary bottleneck in network interdiction arises from the high time complexity of using conventional exact solvers and the challenges associated with devising efficient heuristic solvers. GNNs, recognized as a cutting-edge methodology, have shown significant effectiveness in addressing single-level CO problems on graphs, such as the traveling salesman problem, graph matching, and graph edit distance. Nevertheless, network interdiction presents a bi-level optimization challenge, which current GNNs find difficult to manage. To address this gap, we represent network interdiction problems as Mixed-Integer Linear Programming (MILP) instances, then apply a multipartite GNN with sufficient representational capacity to learn these formulations. This approach ensures that our neural network is more compatible with the mathematical algorithms designed to solve network interdiction problems, resulting in improved generalization. Through two distinct tasks, we demonstrate that our proposed method outperforms theoretical baseline models and provides advantages over traditional exact solvers.

cs.AI↗

arXiv2024

Focus Anywhere for Fine-grained Multi-page Document Understanding

Modern LVLMs still struggle to achieve fine-grained document understanding, such as OCR/translation/caption for regions of interest to the user, tasks that require the context of the entire page, or even multiple pages. Accordingly, this paper proposes Fox, an effective pipeline, hybrid data, and tuning strategy, that catalyzes LVLMs to focus anywhere on single/multi-page documents. We introduce a novel task to boost the document understanding by making LVLMs focus attention on the document-level region, such as redefining full-page OCR as foreground focus. We employ multiple vision vocabularies to extract visual hybrid knowledge for interleaved document pages (e.g., a page containing a photo). Meanwhile, we render cross-vocabulary vision data as the catalyzer to achieve a full reaction of multiple visual vocabularies and in-document figure understanding. Further, without modifying the weights of multiple vision vocabularies, the above catalyzed fine-grained understanding capabilities can be efficiently tuned to multi-page documents, enabling the model to focus anywhere in both format-free and page-free manners. Besides, we build a benchmark including 9 fine-grained sub-tasks (e.g., region-level OCR/summary, color-guided OCR) to promote document analysis in the community. The experimental results verify the superiority of our model.

cs.CV↗

arXiv2024

Point Cloud Compression with Implicit Neural Representations: A Unified Framework

Point clouds have become increasingly vital across various applications thanks to their ability to realistically depict 3D objects and scenes. Nevertheless, effectively compressing unstructured, high-precision point cloud data remains a significant challenge. In this paper, we present a pioneering point cloud compression framework capable of handling both geometry and attribute components. Unlike traditional approaches and existing learning-based methods, our framework utilizes two coordinate-based neural networks to implicitly represent a voxelized point cloud. The first network generates the occupancy status of a voxel, while the second network determines the attributes of an occupied voxel. To tackle an immense number of voxels within the volumetric space, we partition the space into smaller cubes and focus solely on voxels within non-empty cubes. By feeding the coordinates of these voxels into the respective networks, we reconstruct the geometry and attribute components of the original point cloud. The neural network parameters are further quantized and compressed. Experimental results underscore the superior performance of our proposed method compared to the octree-based approach employed in the latest G-PCC standards. Moreover, our method exhibits high universality when contrasted with existing learning-based techniques.

cs.CV↗