arXiv subjects

Yichen Liu

Publications and source records attributed to Yichen Liu.

At least 73 records · Page 4Linked to original sources

arXiv2025

DeepDISC-photoz: Deep Learning-Based Photometric Redshift Estimation for Rubin LSST

Photometric redshifts will be a key data product for the Rubin Observatory Legacy Survey of Space and Time (LSST) as well as for future ground and space-based surveys. The need for photometric redshifts, or photo-zs, arises from sparse spectroscopic coverage of observed galaxies. LSST is expected to observe billions of objects, making it crucial to have a photo-z estimator that is accurate and efficient. To that end, we present DeepDISC photo-z, a photo-z estimator that is an extension of the DeepDISC framework. The base DeepDISC network simultaneously detects, segments, and classifies objects in multi-band coadded images. We introduce photo-z capabilities to DeepDISC by adding a redshift estimation Region of Interest head, which produces a photo-z probability distribution function for each detected object. On simulated LSST images, DeepDISC photo-z outperforms traditional catalog-based estimators, in both point estimate and probabilistic metrics. We validate DeepDISC by examining dependencies on systematics including galactic extinction, blending and PSF effects. We also examine the impact of the data quality and the size of the training set and model. We find that the biggest factor in DeepDISC photo-z quality is the signal-to-noise of the imaging data, and see a reduction in photo-z scatter approximately proportional to the image data signal-to-noise. Our code is fully public and integrated in the RAIL photo-z package for ease of use and comparison to other codes at https://github.com/LSSTDESC/rail_deepdisc

astro-ph.IM↗

arXiv2025

Slitless Areal Pure-Parallel HIgh-Redshift Emission Survey (SAPPHIRES): Early Data Release of Deep JWST/NIRCam Images and Spectra in MACS J0416 Parallel Field

We present the early data release (EDR) of SAPPHIRES, a JWST Cycle-3 Treasury imaging and spectroscopic survey using the powerful NIRCam wide-field slitless spectroscopic (WFSS) mode in pure parallel. SAPPHIRES will obtain NIRCam imaging and WFSS data in many cosmological deep fields totaling a telescope charged time of 709 hours (557-hour exposures). In this EDR, we present NIRCam imaging and WFSS data obtained in parallel to the Frontier Field galaxy cluster MACS J0416.1-2403, which are attached to primary observations JWST-GO-4750. With a total dual-channel exposure time of 47.2 hours, we obtain deep NIRCam imaging in 13 bands at 0.6--5.0 micron and deep WFSS at 3.1-5.0 micron through the F356W and F444W filters with grisms in orthogonal dispersion directions. We release reduced NIRCam images, photometric catalogs of 22107 sources and WFSS spectra of 1060 sources with confirmed redshifts ($z\simeq0-8.5$). Preliminary value-added catalogs including photometric redshifts, spectroscopic redshifts and physical properties (mass, star-formation rate, etc.) are also made available. We also characterize the data quality and demonstrate scientific applications, including (1) galaxy candidates at the redshift frontier ($z\gtrsim10$), (2) the ionized gas kinematics of a galaxy reconstructed from $R\sim1500$ grism spectra at orthogonal dispersion directions, (3) massive emission-line galaxies and active galactic nuclei (AGN) around the Epoch of Reionization.

astro-ph.GA↗

arXiv2025

SAPPHIRES: A Galaxy Over-Density in the Heart of Cosmic Reionization at $z=8.47$

We report the discovery of a galaxy proto-cluster candidate (dubbed MACS0416-OD-z8p5) at a spectroscopic redshift of $z\sim8.47$, dating back to $\sim550$Myr after the Big Bang. The observations are part of the JWST Cycle-3 treasury program, Slitless Areal Pure-Parallel HIgh-Redshift Emission Survey (SAPPHIRES) with NIRCam-grism. Using wide field slitless spectroscopy (WFSS) obtained in the MACS0416 parallel field, we robustly confirm nine galaxies at $z_{\rm spec}\sim8.47$ via emission line detections of [OIII]5008A (with $>5\,σ$) and tentatively confirm one additional galaxy (at $\sim3\,σ$). This discovery represents the highest-redshift, spectroscopically confirmed galaxy over-density known to date, which is $\sim6$--$8$ times more dense than the average volume density of galaxies at the same redshift. Furthermore, a galaxy hosting a low-mass active galactic nucleus (``Little-Red-Dot'') is found as a member, suggesting an early emergence of active, massive black holes and feedback between these black holes and their surrounding environments. We also discuss the spatial structures connecting the galaxy over-density to nearby massive star-forming galaxies (separated by $\sim 5$pMpc, including MACS0416-Y1 and MACS0416-JD. This finding of a massive dark matter halo hosting a galaxy over-density at $z\sim8.5$ is surprising given that our survey covered only a small, random field ($16.5\,{\rm arcmin^2}$) as part of a pure parallel observation. The comparison with cosmological simulations shows that the likelihood of finding such a large-scale structure is $<5\,\%$ under the current galaxy formation scenario and the observed survey volume. Our results demonstrate the power of WFSS observations to build a complete line-emitter sample and suggest an important role for over-densities in enhancing galaxy formation by funneling large-scale gas supplies into small cosmological volumes.

astro-ph.GA↗

arXiv2025

Deep Learning for Time Series Forecasting: A Survey

Time series forecasting (TSF) has long been a crucial task in both industry and daily life. Most classical statistical models may have certain limitations when applied to practical scenarios in fields such as energy, healthcare, traffic, meteorology, and economics, especially when high accuracy is required. With the continuous development of deep learning, numerous new models have emerged in the field of time series forecasting in recent years. However, existing surveys have not provided a unified summary of the wide range of model architectures in this field, nor have they given detailed summaries of works in feature extraction and datasets. To address this gap, in this review, we comprehensively study the previous works and summarize the general paradigms of Deep Time Series Forecasting (DTSF) in terms of model architectures. Besides, we take an innovative approach by focusing on the composition of time series and systematically explain important feature extraction methods. Additionally, we provide an overall compilation of datasets from various domains in existing works. Finally, we systematically emphasize the significant challenges faced and future research directions in this field.

cs.LG↗

arXiv2025

Dwarf Active Galactic Nuclei from Variability for the Origins of Seeds (DAVOS): Properties of Variability-Selected AGNs in the Dark Energy Survey Deep Fields

We study the black hole mass $-$ host galaxy stellar mass relation, $M_{\rm{BH}}-M_{\ast}$, for a sample of 706 $z \lesssim 1.5$ and $i \lesssim 24$ optically-variable active galactic nuclei (AGNs) in three Dark Energy Survey (DES) deep fields: C3, X3, E2, which partially cover Chandra Deep Field-South, XMM Large Scale Structure survey, and European Large Area ISO Survey, respectively. The parent sample was identified by optical variability from the DES supernova survey program imaging. Using publicly available spectra and photometric catalogs, we consolidate their spectroscopic redshifts, estimate their black hole masses using broad line widths and luminosities, and obtain improved stellar masses using spectral energy distribution fitting from X-ray to mid-infrared wavelengths. Our results confirm previous work from Hyper-Suprime Camera imaging that variability searches with deep, high-precision photometry can reliably identify AGNs in low-mass galaxies up to $z\sim1$. However, we find that the hosted black holes are overmassive than predicted by the local AGN relation, fixing host galaxy stellar mass. Instead, $z\sim 0.1-1.5$ variability-selected AGNs lie in between the $M_{\rm{BH}}-M_{\ast}$ relation for local inactive early-type galaxies and local active galaxies. This result agrees with most previous studies of $M_{\rm{BH}}-M_{\ast}$ relation for AGNs at similar redshifts, regardless of selection technique. We demonstrate that studies of variability selected AGN provide critical insights into the low-mass end of the $M_{\rm{BH}}-M_{\ast}$ relation, shedding light on the occupation fraction of that provides constraints on early BH seeding mechanisms and self-regulated feedback processes during their growth and co-evolution with their hosts.

astro-ph.GA↗

arXiv2025

UniMLVG: Unified Framework for Multi-view Long Video Generation with Comprehensive Control Capabilities for Autonomous Driving

The creation of diverse and realistic driving scenarios has become essential to enhance perception and planning capabilities of the autonomous driving system. However, generating long-duration, surround-view consistent driving videos remains a significant challenge. To address this, we present UniMLVG, a unified framework designed to generate extended street multi-perspective videos under precise control. By integrating single- and multi-view driving videos into the training data, our approach updates a DiT-based diffusion model equipped with cross-frame and cross-view modules across three stages with multi training objectives, substantially boosting the diversity and quality of generated visual content. Importantly, we propose an innovative explicit viewpoint modeling approach for multi-view video generation to effectively improve motion transition consistency. Capable of handling various input reference formats (e.g., text, images, or video), our UniMLVG generates high-quality multi-view videos according to the corresponding condition constraints such as 3D bounding boxes or frame-level text descriptions. Compared to the best models with similar capabilities, our framework achieves improvements of 48.2% in FID and 35.2% in FVD.

cs.CV↗

arXiv2025

Two-dimensional fully-compensated Ferrimagnetism

Antiferromagnetic spintronics has long been a subject of intense research interest, and the recent introduction of altermagnetism has further ignited enthusiasm in the field. However, fully-compensated ferrimagnetism, which exhibits band spin splitting but zero net magnetization, has yet to receive enough attention. Since the experimental preparation of two-dimensional (2D) magnetic van der Waals (vdW) materials in 2017, 2D magnetic materials, thanks to their super tunability, have quickly become an important playground for spintronics. Here, we extend the concept of fully-compensated ferrimagnetism (fFIM) to two dimensions and propose 2D \textit{filling-enforced} fFIM, demonstrate its stability and ease of manipulation, and present three feasible realization schemes with respective exemplary candidate materials. A simple model for 2D fully-compensated ferrimagnets (fFIMs) is developed. Further investigation of 2D fFIMs' physical properties reveals that they not only exhibit significant magneto-optical response but also show fully spin-polarized currents and the anomalous Hall effect in the half-metallic states, displaying characteristics previously almost exclusive to ferromagnetic materials, greatly broadening the research and application prospects of spintronic materials.

cond-mat.mtrl-sci↗

arXiv2025

MaskGWM: A Generalizable Driving World Model with Video Mask Reconstruction

World models that forecast environmental changes from actions are vital for autonomous driving models with strong generalization. The prevailing driving world model mainly build on video prediction model. Although these models can produce high-fidelity video sequences with advanced diffusion-based generator, they are constrained by their predictive duration and overall generalization capabilities. In this paper, we explore to solve this problem by combining generation loss with MAE-style feature-level context learning. In particular, we instantiate this target with three key design: (1) A more scalable Diffusion Transformer (DiT) structure trained with extra mask construction task. (2) we devise diffusion-related mask tokens to deal with the fuzzy relations between mask reconstruction and generative diffusion process. (3) we extend mask construction task to spatial-temporal domain by utilizing row-wise mask for shifted self-attention rather than masked self-attention in MAE. Then, we adopt a row-wise cross-view module to align with this mask design. Based on above improvement, we propose MaskGWM: a Generalizable driving World Model embodied with Video Mask reconstruction. Our model contains two variants: MaskGWM-long, focusing on long-horizon prediction, and MaskGWM-mview, dedicated to multi-view generation. Comprehensive experiments on standard benchmarks validate the effectiveness of the proposed method, which contain normal validation of Nuscene dataset, long-horizon rollout of OpenDV-2K dataset and zero-shot validation of Waymo dataset. Quantitative metrics on these datasets show our method notably improving state-of-the-art driving world model.

cs.CV↗

arXiv2024

Music Genre Classification: Ensemble Learning with Subcomponents-level Attention

Music Genre Classification is one of the most popular topics in the fields of Music Information Retrieval (MIR) and digital signal processing. Deep Learning has emerged as the top performer for classifying music genres among various methods. The letter introduces a novel approach by combining ensemble learning with attention to sub-components, aiming to enhance the accuracy of identifying music genres. The core innovation of our work is the proposal to classify the subcomponents of the music pieces separately, allowing our model to capture distinct characteristics from those sub components. By applying ensemble learning techniques to these individual classifications, we make the final classification decision on the genre of the music. The proposed method has superior advantages in terms of accuracy compared to the other state-of-the-art techniques trained and tested on the GTZAN dataset.

cs.SD↗

arXiv2024

Mobility-LLM: Learning Visiting Intentions and Travel Preferences from Human Mobility Data with Large Language Models

Location-based services (LBS) have accumulated extensive human mobility data on diverse behaviors through check-in sequences. These sequences offer valuable insights into users' intentions and preferences. Yet, existing models analyzing check-in sequences fail to consider the semantics contained in these sequences, which closely reflect human visiting intentions and travel preferences, leading to an incomplete comprehension. Drawing inspiration from the exceptional semantic understanding and contextual information processing capabilities of large language models (LLMs) across various domains, we present Mobility-LLM, a novel framework that leverages LLMs to analyze check-in sequences for multiple tasks. Since LLMs cannot directly interpret check-ins, we reprogram these sequences to help LLMs comprehensively understand the semantics of human visiting intentions and travel preferences. Specifically, we introduce a visiting intention memory network (VIMN) to capture the visiting intentions at each record, along with a shared pool of human travel preference prompts (HTPP) to guide the LLM in understanding users' travel preferences. These components enhance the model's ability to extract and leverage semantic information from human mobility data effectively. Extensive experiments on four benchmark datasets and three downstream tasks demonstrate that our approach significantly outperforms existing models, underscoring the effectiveness of Mobility-LLM in advancing our understanding of human mobility data within LBS contexts.

cs.LG↗

arXiv2024

A Lower Bound of the Hofer-Zehnder Capacity via Delzant Polytopes

Given a symplectic toric manifold, the moment maps of sub-circle actions can be modified to be admissible functions in the sense of Hofer-Zehnder. By exploiting the relationship between the period of Hamiltonian sub-circle actions of a symplectic toric manifold and its Delzant polytope, we develop an invariant of Delzant polytopes which gives a lower bound of the Hofer-Zehnder capacity.

math.SG↗

arXiv2024

Optimized Biomedical Question-Answering Services with LLM and Multi-BERT Integration

We present a refined approach to biomedical question-answering (QA) services by integrating large language models (LLMs) with Multi-BERT configurations. By enhancing the ability to process and prioritize vast amounts of complex biomedical data, this system aims to support healthcare professionals in delivering better patient outcomes and informed decision-making. Through innovative use of BERT and BioBERT models, combined with a multi-layer perceptron (MLP) layer, we enable more specialized and efficient responses to the growing demands of the healthcare sector. Our approach not only addresses the challenge of overfitting by freezing one BERT model while training another but also improves the overall adaptability of QA services. The use of extensive datasets, such as BioASQ and BioMRC, demonstrates the system's ability to synthesize critical information. This work highlights how advanced language models can make a tangible difference in healthcare, providing reliable and responsive tools for professionals to manage complex information, ultimately serving the broader goal of improved care and data-driven insights.

cs.CL↗

arXiv2024

Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learning

Humanoid robots, with their human-like skeletal structure, are especially suited for tasks in human-centric environments. However, this structure is accompanied by additional challenges in locomotion controller design, especially in complex real-world environments. As a result, existing humanoid robots are limited to relatively simple terrains, either with model-based control or model-free reinforcement learning. In this work, we introduce Denoising World Model Learning (DWL), an end-to-end reinforcement learning framework for humanoid locomotion control, which demonstrates the world's first humanoid robot to master real-world challenging terrains such as snowy and inclined land in the wild, up and down stairs, and extremely uneven terrains. All scenarios run the same learned neural network with zero-shot sim-to-real transfer, indicating the superior robustness and generalization capability of the proposed method.

cs.RO↗

arXiv2024

PTrajM: Efficient and Semantic-rich Trajectory Learning with Pretrained Trajectory-Mamba

Vehicle trajectories provide crucial movement information for various real-world applications. To better utilize vehicle trajectories, it is essential to develop a trajectory learning approach that can effectively and efficiently extract rich semantic information, including movement behavior and travel purposes, to support accurate downstream applications. However, creating such an approach presents two significant challenges. First, movement behavior are inherently spatio-temporally continuous, making them difficult to extract efficiently from irregular and discrete trajectory points. Second, travel purposes are related to the functionalities of areas and road segments traversed by vehicles. These functionalities are not available from the raw spatio-temporal trajectory features and are hard to extract directly from complex textual features associated with these areas and road segments. To address these challenges, we propose PTrajM, a novel method capable of efficient and semantic-rich vehicle trajectory learning. To support efficient modeling of movement behavior, we introduce Trajectory-Mamba as the learnable model of PTrajM, which effectively extracts continuous movement behavior while being more computationally efficient than existing structures. To facilitate efficient extraction of travel purposes, we propose a travel purpose-aware pre-training procedure, which enables PTrajM to discern the travel purposes of trajectories without additional computational resources during its embedding process. Extensive experiments on two real-world datasets and comparisons with several state-of-the-art trajectory learning methods demonstrate the effectiveness of PTrajM. Code is available at https://anonymous.4open.science/r/PTrajM-C973.

cs.LG↗

arXiv2024

Multi-Garment Customized Model Generation

This paper introduces Multi-Garment Customized Model Generation, a unified framework based on Latent Diffusion Models (LDMs) aimed at addressing the unexplored task of synthesizing images with free combinations of multiple pieces of clothing. The method focuses on generating customized models wearing various targeted outfits according to different text prompts. The primary challenge lies in maintaining the natural appearance of the dressed model while preserving the complex textures of each piece of clothing, ensuring that the information from different garments does not interfere with each other. To tackle these challenges, we first developed a garment encoder, which is a trainable UNet copy with shared weights, capable of extracting detailed features of garments in parallel. Secondly, our framework supports the conditional generation of multiple garments through decoupled multi-garment feature fusion, allowing multiple clothing features to be injected into the backbone network, significantly alleviating conflicts between garment information. Additionally, the proposed garment encoder is a plug-and-play module that can be combined with other extension modules such as IP-Adapter and ControlNet, enhancing the diversity and controllability of the generated models. Extensive experiments demonstrate the superiority of our approach over existing alternatives, opening up new avenues for the task of generating images with multiple-piece clothing combinations

cs.CV↗

arXiv2024

Confidence-aware Self-Semantic Distillation on Knowledge Graph Embedding

Knowledge Graph Embedding (KGE), which projects entities and relations into continuous vector spaces, has garnered significant attention. Although high-dimensional KGE methods offer better performance, they come at the expense of significant computation and memory overheads. Decreasing embedding dimensions significantly deteriorates model performance. While several recent efforts utilize knowledge distillation or non-Euclidean representation learning to augment the effectiveness of low-dimensional KGE, they either necessitate a pre-trained high-dimensional teacher model or involve complex non-Euclidean operations, thereby incurring considerable additional computational costs. To address this, this work proposes Confidence-aware Self-Knowledge Distillation (CSD) that learns from the model itself to enhance KGE in a low-dimensional space. Specifically, CSD extracts knowledge from embeddings in previous iterations, which would be utilized to supervise the learning of the model in the next iterations. Moreover, a specific semantic module is developed to filter reliable knowledge by estimating the confidence of previously learned embeddings. This straightforward strategy bypasses the need for time-consuming pre-training of teacher models and can be integrated into various KGE methods to improve their performance. Our comprehensive experiments on six KGE backbones and four datasets underscore the effectiveness of the proposed CSD.

cs.LG↗

arXiv2024

PromptSAM+: Malware Detection based on Prompt Segment Anything Model

Machine learning and deep learning (ML/DL) have been extensively applied in malware detection, and some existing methods demonstrate robust performance. However, several issues persist in the field of malware detection: (1) Existing work often overemphasizes accuracy at the expense of practicality, rarely considering false positive and false negative rates as important metrics. (2) Considering the evolution of malware, the performance of classifiers significantly declines over time, greatly reducing the practicality of malware detectors. (3) Prior ML/DL-based efforts heavily rely on ample labeled data for model training, largely dependent on feature engineering or domain knowledge to build feature databases, making them vulnerable if correct labels are scarce. With the development of computer vision, vision-based malware detection technology has also rapidly evolved. In this paper, we propose a visual malware general enhancement classification framework, `PromptSAM+', based on a large visual network segmentation model, the Prompt Segment Anything Model(named PromptSAM+). Our experimental results indicate that 'PromptSAM+' is effective and efficient in malware detection and classification, achieving high accuracy and low rates of false positives and negatives. The proposed method outperforms the most advanced image-based malware detection technologies on several datasets. 'PromptSAM+' can mitigate aging in existing image-based malware classifiers, reducing the considerable manpower needed for labeling new malware samples through active learning. We conducted experiments on datasets for both Windows and Android platforms, achieving favorable outcomes. Additionally, our ablation experiments on several datasets demonstrate that our model identifies effective modules within the large visual network.

cs.CR↗

arXiv2024

Crossed real nodal-line phonons in gold monobromide

Spacetime inversion symmetry can generate intriguing types of spinless excitations in crystalline materials. Here, we propose a topological phase protected by spacetime inversion symmetry - the crossed real nodal line (RNL) in the phonon spectrum of gold monobromide (AuBr). In AuBr, there exist four straight nodal lines, which are linked by a crossed nodal line formed by two lower bands. Remarkably, each adjacent two of the four straight nodal lines is a pair, forming a crossed RNL with nontrivial real Chern number. Such configuration and pairing mode of RNL have never been reported. The crossed RNL exhibits unique surface and hinge states distinguished from that of the conventional RNLs. The symmetry protection and the transformation under the symmetry-preserving strain of the crossed RNL are also investigated. Our results open the door to a new class of topological states, and predict its realization in experimentally synthesized material.

cond-mat.mtrl-sci↗