Searcharxiv⌕ Search

arXiv subjects

Liang Zhang

Publications and source records attributed to Liang Zhang.

At least 253 records · Page 14Linked to original sources
arXiv2023

A systematic study of the high-frequency bump in the black-hole low-mass X-ray binary GX 339-4

The high-frequency bump, characterized by a frequency exceeding ~30 Hz, represents a seldom-explored time-variability feature in the power density spectrum (PDS) of black-hole X-ray binaries. In the 2002, 2004, 2007 and 2010 outbursts of GX 339-4, the bump has been occasionally observed in conjunction with type-C quasi-periodic oscillations (QPOs). We systematically study the properties of the bump during these four outbursts observed by Rossi X-ray Timing Explorer (RXTE) in the 2-60 keV bands and detect the bump in 39 observations. While the frequencies of the type-C QPOs are in the range of ~0.1-9 Hz, the root-mean-square (rms) amplitude of the bump shows an evolution in the hardness ratio versus the type-C QPO frequency plot. By comparing the rms amplitude of the bump with the corona temperature and simultaneous radio jet flux of the source, as previously studied in GRS 1915+105, we establish that in the hard state of GX 339-4, the bump is always strong, with the measurements of the rms amplitude in the range of 4-10%. At the same time, the corona temperature is high and the radio flux is low. These findings indicate that, using the bump as a proxy, the majority of the accretion energy is directed towards the hot corona rather than being channeled into the radio jet. We discuss this phenomenon in terms of an inefficient energy transfer mechanism between the corona and jet in GX 339-4.

astro-ph.HE↗
arXiv2023

MobileNVC: Real-time 1080p Neural Video Compression on a Mobile Device

Neural video codecs have recently become competitive with standard codecs such as HEVC in the low-delay setting. However, most neural codecs are large floating-point networks that use pixel-dense warping operations for temporal modeling, making them too computationally expensive for deployment on mobile devices. Recent work has demonstrated that running a neural decoder in real time on mobile is feasible, but shows this only for 720p RGB video. This work presents the first neural video codec that decodes 1080p YUV420 video in real time on a mobile device. Our codec relies on two major contributions. First, we design an efficient codec that uses a block-based motion compensation algorithm available on the warping core of the mobile accelerator, and we show how to quantize this model to integer precision. Second, we implement a fast decoder pipeline that concurrently runs neural network components on the neural signal processor, parallel entropy coding on the mobile GPU, and warping on the warping core. Our codec outperforms the previous on-device codec by a large margin with up to 48% BD-rate savings, while reducing the MAC count on the receiver side by $10 \times$. We perform a careful ablation to demonstrate the effect of the introduced motion compensation scheme, and ablate the effect of model quantization.

eess.IV↗
arXiv2023

Taxonomy, Semantic Data Schema, and Schema Alignment for Open Data in Urban Building Energy Modeling

Urban Building Energy Modeling (UBEM) is a critical tool to provide quantitative analysis on building decarbonization, sustainability, building-to-grid integration, and renewable energy applications on city, regional, and national scales. Researchers usually use open data as inputs to build and calibrate UBEM. However, open data are from thousands of sources covering various perspectives of weather, building characteristics, etc. Besides, a lack of semantic features of open data further increases the engineering effort to process information to be directly used for UBEM as inputs. In this paper, we first reviewed open data types used for UBEM and developed a taxonomy to categorize open data. Based on that, we further developed a semantic data schema for each open data category to maintain data consistency and improve model automation for UBEM. In a case study, we use three popular open data to show how they can be automatically processed based on the proposed schematic data structure using large language models. The accurate results generated by large language models indicate the machine-readability and human-interpretability of the developed semantic data schema.

cs.DB↗
arXiv2023

Beam test of a 180 nm CMOS Pixel Sensor for the CEPC vertex detector

The proposed Circular Electron Positron Collider (CEPC) imposes new challenges for the vertex detector in terms of pixel size and material budget. A Monolithic Active Pixel Sensor (MAPS) prototype called TaichuPix, based on a column drain readout architecture, has been developed to address the need for high spatial resolution. In order to evaluate the performance of the TaichuPix-3 chips, a beam test was carried out at DESY II TB21 in December 2022. Meanwhile, the Data Acquisition (DAQ) for a muti-plane configuration was tested during the beam test. This work presents the characterization of the TaichuPix-3 chips with two different processes, including cluster size, spatial resolution, and detection efficiency. The analysis results indicate the spatial resolution better than 5 $μm$ and the detection efficiency exceeds 99.5 % for both TaichuPix-3 chips with the two different processes.

physics.ins-det↗
arXiv2023

CDR-Adapter: Learning Adapters to Dig Out More Transferring Ability for Cross-Domain Recommendation Models

Data sparsity and cold-start problems are persistent challenges in recommendation systems. Cross-domain recommendation (CDR) is a promising solution that utilizes knowledge from the source domain to improve the recommendation performance in the target domain. Previous CDR approaches have mainly followed the Embedding and Mapping (EMCDR) framework, which involves learning a mapping function to facilitate knowledge transfer. However, these approaches necessitate re-engineering and re-training the network structure to incorporate transferrable knowledge, which can be computationally expensive and may result in catastrophic forgetting of the original knowledge. In this paper, we present a scalable and efficient paradigm to address data sparsity and cold-start issues in CDR, named CDR-Adapter, by decoupling the original recommendation model from the mapping function, without requiring re-engineering the network structure. Specifically, CDR-Adapter is a novel plug-and-play module that employs adapter modules to align feature representations, allowing for flexible knowledge transfer across different domains and efficient fine-tuning with minimal training costs. We conducted extensive experiments on the benchmark dataset, which demonstrated the effectiveness of our approach over several state-of-the-art CDR approaches.

cs.IR↗
arXiv2023

Learning Descriptive Image Captioning via Semipermeable Maximum Likelihood Estimation

Image captioning aims to describe visual content in natural language. As 'a picture is worth a thousand words', there could be various correct descriptions for an image. However, with maximum likelihood estimation as the training objective, the captioning model is penalized whenever its prediction mismatches with the label. For instance, when the model predicts a word expressing richer semantics than the label, it will be penalized and optimized to prefer more concise expressions, referred to as conciseness optimization. In contrast, predictions that are more concise than labels lead to richness optimization. Such conflicting optimization directions could eventually result in the model generating general descriptions. In this work, we introduce Semipermeable MaxImum Likelihood Estimation (SMILE), which allows richness optimization while blocking conciseness optimization, thus encouraging the model to generate longer captions with more details. Extensive experiments on two mainstream image captioning datasets MSCOCO and Flickr30K demonstrate that SMILE significantly enhances the descriptiveness of generated captions. We further provide in-depth investigations to facilitate a better understanding of how SMILE works.

cs.CL↗
arXiv2023

Restoring the Broken Covenant Between Compilers and Deep Learning Accelerators

Deep learning accelerators address the computational demands of Deep Neural Networks (DNNs), departing from the traditional Von Neumann execution model. They leverage specialized hardware to align with the application domain's structure. Compilers for these accelerators face distinct challenges compared to those for general-purpose processors. These challenges include exposing and managing more micro-architectural features, handling software-managed scratch pads for on-chip storage, explicitly managing data movement, and matching DNN layers with varying hardware capabilities. These complexities necessitate a new approach to compiler design, as traditional compilers mainly focused on generating fine-grained instruction sequences while abstracting micro-architecture details. This paper introduces the Architecture Covenant Graph (ACG), an abstract representation of an architectural structure's components and their programmable capabilities. By enabling the compiler to work with the ACG, it allows for adaptable compilation workflows when making changes to accelerator design, reducing the need for a complete compiler redevelopment. Codelets, which express DNN operation functionality and evolve into execution mappings on the ACG, are key to this process. The Covenant compiler efficiently targets diverse deep learning accelerators, achieving 93.8% performance compared to state-of-the-art, hand-tuned DNN layer implementations when compiling 14 DNN layers from various models on two different architectures.

cs.DC↗
arXiv2023

UE4-NeRF:Neural Radiance Field for Real-Time Rendering of Large-Scale Scene

Neural Radiance Fields (NeRF) is a novel implicit 3D reconstruction method that shows immense potential and has been gaining increasing attention. It enables the reconstruction of 3D scenes solely from a set of photographs. However, its real-time rendering capability, especially for interactive real-time rendering of large-scale scenes, still has significant limitations. To address these challenges, in this paper, we propose a novel neural rendering system called UE4-NeRF, specifically designed for real-time rendering of large-scale scenes. We partitioned each large scene into different sub-NeRFs. In order to represent the partitioned independent scene, we initialize polygonal meshes by constructing multiple regular octahedra within the scene and the vertices of the polygonal faces are continuously optimized during the training process. Drawing inspiration from Level of Detail (LOD) techniques, we trained meshes of varying levels of detail for different observation levels. Our approach combines with the rasterization pipeline in Unreal Engine 4 (UE4), achieving real-time rendering of large-scale scenes at 4K resolution with a frame rate of up to 43 FPS. Rendering within UE4 also facilitates scene editing in subsequent stages. Furthermore, through experiments, we have demonstrated that our method achieves rendering quality comparable to state-of-the-art approaches. Project page: https://jamchaos.github.io/UE4-NeRF/.

cs.CV↗
arXiv2023

Type-A quasi-periodic oscillation in the black hole transient MAXI J1348-630

We present a detailed analysis of the spectral and timing characteristics of a 7-Hz type-A quasi-periodic oscillation (QPO) detected in NICER observations of the black hole X-ray binary MAXI J1348-630 during its high-soft state. The QPO is broad and weak, with an integrated fractional rms amplitude of 0.9 per cent in the 0.5-10 keV band. Thanks to the large effective area of NICER, combined with the high flux of the source and a relatively long accumulative exposure time, we construct the first rms and phase-lag spectra for a type-A QPO. Our analysis reveals that the fractional rms amplitude of the QPO increases with energy from below 1 per cent at 1 keV to 3 per cent at 6 keV. The shape of the QPO spectrum is similar to that of the Comptonised component, suggesting that the Comptonised region is driving the variability. The phase lags at the QPO frequency are always soft taking the lowest energy as reference. By jointly fitting the time-averaged spectrum of the source and the rms and phase-lag spectra of the QPO with the time-dependent Comptonisation model vkompthdk, we find that the radiative properties of the type-A QPO can be explained by a vertically extended Comptonised region with a size of 2300 km.

astro-ph.HE↗
arXiv2023

Leveraging Queue Length and Attention Mechanisms for Enhanced Traffic Signal Control Optimization

Reinforcement learning (RL) techniques for traffic signal control (TSC) have gained increasing popularity in recent years. However, most existing RL-based TSC methods tend to focus primarily on the RL model structure while neglecting the significance of proper traffic state representation. Furthermore, some RL-based methods heavily rely on expert-designed traffic signal phase competition. In this paper, we present a novel approach to TSC that utilizes queue length as an efficient state representation. We propose two new methods: (1) Max Queue-Length (M-QL), an optimization-based traditional method designed based on the property of queue length; and (2) AttentionLight, an RL model that employs the self-attention mechanism to capture the signal phase correlation without requiring human knowledge of phase relationships. Comprehensive experiments on multiple real-world datasets demonstrate the effectiveness of our approach: (1) the M-QL method outperforms the latest RL-based methods; (2) AttentionLight achieves a new state-of-the-art performance; and (3) our results highlight the significance of proper state representation, which is as crucial as neural network design in TSC methods. Our findings have important implications for advancing the development of more effective and efficient TSC methods. Our code is released on Github (https://github. com/LiangZhang1996/AttentionLight).

cs.LG↗
arXiv2023

Automatic Data Transformation Using Large Language Model: An Experimental Study on Building Energy Data

Existing approaches to automatic data transformation are insufficient to meet the requirements in many real-world scenarios, such as the building sector. First, there is no convenient interface for domain experts to provide domain knowledge easily. Second, they require significant training data collection overheads. Third, the accuracy suffers from complicated schema changes. To bridge this gap, we present a novel approach that leverages the unique capabilities of large language models (LLMs) in coding, complex reasoning, and zero-shot learning to generate SQL code that transforms the source datasets into the target datasets. We demonstrate the viability of this approach by designing an LLM-based framework, termed SQLMorpher, which comprises a prompt generator that integrates the initial prompt with optional domain knowledge and historical patterns in external databases. It also implements an iterative prompt optimization mechanism that automatically improves the prompt based on flaw detection. The key contributions of this work include (1) pioneering an end-to-end LLM-based solution for data transformation, (2) developing a benchmark dataset of 105 real-world building energy data transformation problems, and (3) conducting an extensive empirical evaluation where our approach achieved 96% accuracy in all 105 problems. SQLMorpher demonstrates the effectiveness of utilizing LLMs in complex, domain-specific challenges, highlighting the potential of their potential to drive sustainable solutions.

cs.DB↗
arXiv2023

Simulation study of BESIII with stitched CMOS pixel detector using ACTS

Reconstruction of tracks of charged particles with high precision is very crucial for HEP experiments to achieve their physics goals. As the tracking detector of BESIII experiment, the BESIII drift chamber has suffered from aging effects resulting in degraded tracking performance after operation for about 15 years. To preserve and enhance the tracking performance of BESIII, one of the proposals is to add one layer of thin CMOS pixel sensor in cylindrical shape based on the state-of-the-art stitching technology, between the beam pipe and the drift chamber. The improvement of tracking performance of BESIII with such an additional pixel detector compared to that with only the existing drift chamber is studied using the modern common tracking software ACTS, which provides a set of detector-agnostic and highly performant tracking algorithms that have demonstrated promising performance for a few high energy physics and nuclear physics experiments.

physics.ins-det↗
arXiv2023

AntM$^{2}$C: A Large Scale Dataset For Multi-Scenario Multi-Modal CTR Prediction

Click-through rate (CTR) prediction is a crucial issue in recommendation systems. There has been an emergence of various public CTR datasets. However, existing datasets primarily suffer from the following limitations. Firstly, users generally click different types of items from multiple scenarios, and modeling from multiple scenarios can provide a more comprehensive understanding of users. Existing datasets only include data for the same type of items from a single scenario. Secondly, multi-modal features are essential in multi-scenario prediction as they address the issue of inconsistent ID encoding between different scenarios. The existing datasets are based on ID features and lack multi-modal features. Third, a large-scale dataset can provide a more reliable evaluation of models, fully reflecting the performance differences between models. The scale of existing datasets is around 100 million, which is relatively small compared to the real-world CTR prediction. To address these limitations, we propose AntM$^{2}$C, a Multi-Scenario Multi-Modal CTR dataset based on industrial data from Alipay. Specifically, AntM$^{2}$C provides the following advantages: 1) It covers CTR data of 5 different types of items, providing insights into the preferences of users for different items, including advertisements, vouchers, mini-programs, contents, and videos. 2) Apart from ID-based features, AntM$^{2}$C also provides 2 multi-modal features, raw text and image features, which can effectively establish connections between items with different IDs. 3) AntM$^{2}$C provides 1 billion CTR data with 200 features, including 200 million users and 6 million items. It is currently the largest-scale CTR dataset available. Based on AntM$^{2}$C, we construct several typical CTR tasks and provide comparisons with baseline methods. The dataset homepage is available at https://www.atecup.cn/home.

cs.IR↗
arXiv2023

Graph Edit Distance Learning via Different Attention

Recently, more and more research has focused on using Graph Neural Networks (GNN) to solve the Graph Similarity Computation problem (GSC), i.e., computing the Graph Edit Distance (GED) between two graphs. These methods treat GSC as an end-to-end learnable task, and the core of their architecture is the feature fusion modules to interact with the features of two graphs. Existing methods consider that graph-level embedding is difficult to capture the differences in local small structures between two graphs, and thus perform fine-grained feature fusion on node-level embedding can improve the accuracy, but leads to greater time and memory consumption in the training and inference phases. However, this paper proposes a novel graph-level fusion module Different Attention (DiffAtt), and demonstrates that graph-level fusion embeddings can substantially outperform these complex node-level fusion embeddings. We posit that the relative difference structure of the two graphs plays an important role in calculating their GED values. To this end, DiffAtt uses the difference between two graph-level embeddings as an attentional mechanism to capture the graph structural difference of the two graphs. Based on DiffAtt, a new GSC method, named Graph Edit Distance Learning via Different Attention (REDRAFT), is proposed, and experimental results demonstrate that REDRAFT achieves state-of-the-art performance in 23 out of 25 metrics in five benchmark datasets. Especially on MSE, it respectively outperforms the second best by 19.9%, 48.8%, 29.1%, 31.6%, and 2.2%. Moreover, we propose a quantitative test Remaining Subgraph Alignment Test (RESAT) to verify that among all graph-level fusion modules, the fusion embedding generated by DiffAtt can best capture the structural differences between two graphs.

cs.AI↗
arXiv2023

Explore and Tell: Embodied Visual Captioning in 3D Environments

While current visual captioning models have achieved impressive performance, they often assume that the image is well-captured and provides a complete view of the scene. In real-world scenarios, however, a single image may not offer a good viewpoint, hindering fine-grained scene understanding. To overcome this limitation, we propose a novel task called Embodied Captioning, which equips visual captioning models with navigation capabilities, enabling them to actively explore the scene and reduce visual ambiguity from suboptimal viewpoints. Specifically, starting at a random viewpoint, an agent must navigate the environment to gather information from different viewpoints and generate a comprehensive paragraph describing all objects in the scene. To support this task, we build the ET-Cap dataset with Kubric simulator, consisting of 10K 3D scenes with cluttered objects and three annotated paragraphs per scene. We propose a Cascade Embodied Captioning model (CaBOT), which comprises of a navigator and a captioner, to tackle this task. The navigator predicts which actions to take in the environment, while the captioner generates a paragraph description based on the whole navigation trajectory. Extensive experiments demonstrate that our model outperforms other carefully designed baselines. Our dataset, codes and models are available at https://aim3-ruc.github.io/ExploreAndTell.

cs.CV↗
arXiv2023

TrajPAC: Towards Robustness Verification of Pedestrian Trajectory Prediction Models

Robust pedestrian trajectory forecasting is crucial to developing safe autonomous vehicles. Although previous works have studied adversarial robustness in the context of trajectory forecasting, some significant issues remain unaddressed. In this work, we try to tackle these crucial problems. Firstly, the previous definitions of robustness in trajectory prediction are ambiguous. We thus provide formal definitions for two kinds of robustness, namely label robustness and pure robustness. Secondly, as previous works fail to consider robustness about all points in a disturbance interval, we utilise a probably approximately correct (PAC) framework for robustness verification. Additionally, this framework can not only identify potential counterexamples, but also provides interpretable analyses of the original methods. Our approach is applied using a prototype tool named TrajPAC. With TrajPAC, we evaluate the robustness of four state-of-the-art trajectory prediction models -- Trajectron++, MemoNet, AgentFormer, and MID -- on trajectories from five scenes of the ETH/UCY dataset and scenes of the Stanford Drone Dataset. Using our framework, we also experimentally study various factors that could influence robustness performance.

cs.AI↗
arXiv2023

Search for ultralight dark matter with a frequency adjustable diamagnetic levitated sensor

Among several dark matter candidates, bosonic ultralight (sub meV) dark matter is well motivated because it could couple to the Standard Model (SM) and induce new forces. Previous MICROSCOPE and Eot Wash torsion experiments have achieved high accuracy in the sub-1 Hz region, but at higher frequencies there is still a lack of relevant experimental research. We propose an experimental scheme based on the diamagnetic levitated micromechanical oscillator, one of the most sensitive sensors for acceleration sensitivity below the kilohertz scale. In order to improve the measurement range, we used the sensor whose resonance frequency could be adjusted from 0.1Hz to 100Hz. The limits of the coupling constant are improved by more than 10 times compared to previous reports, and it may be possible to achieve higher accuracy by using the array of sensors in the future.

astro-ph.CO↗
arXiv2023

A variable corona during the transition from type-C to type-B quasi-periodic oscillations in the black hole X-ray binary MAXI J1820+070

We analyze a Neutron Star Interior Composition Explorer (NICER) observation of the black hole X-ray binary MAXI J1820+070 during a transition from type-C to type-B quasi-periodic oscillations (QPOs). We find that below ~2 keV, for the type-B QPOs the rms amplitude is lower and the magnitude of the phase lags is larger than for the type-C QPOs. Above that energy, the rms and phase-lag spectra of the type-B and type-C QPOs are consistent with being the same. We perform a joint fit of the time-averaged spectra of the source, and the rms and phase-lag spectra of the QPOs with the time-dependent Comptonization model vkompth to study the geometry of the corona during the transition. We find that the data can be well-fitted with a model consisting of a small and a large corona that are physically connected. The sizes of the small and large coronae increase gradually during the type-C QPO phase whereas they decrease abruptly at the transition to type-B QPO. At the same time, the inner radius of the disc moves inward at the QPO transition. Combined with simultaneous radio observations showing that discrete jet ejections happen around the time of the QPO transition, we propose that a corona that expands horizontally during the type-C QPO phase, from ~10^{4} km (~800 Rg) to ~10^{5} km (~8000 Rg) overlying the accretion disc, transforms into a vertical jet-like corona extending over ~10^{4} km (~800 Rg) during the type-B QPO phase.

astro-ph.HE↗