arXiv subjects

Hao Liu

Publications and source records attributed to Hao Liu.

At least 325 records · Page 18Linked to original sources

arXiv2025

Reflections from the 2024 Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry

Here, we present the outcomes from the second Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry, which engaged participants across global hybrid locations, resulting in 34 team submissions. The submissions spanned seven key application areas and demonstrated the diverse utility of LLMs for applications in (1) molecular and material property prediction; (2) molecular and material design; (3) automation and novel interfaces; (4) scientific communication and education; (5) research data management and automation; (6) hypothesis generation and evaluation; and (7) knowledge extraction and reasoning from scientific literature. Each team submission is presented in a summary table with links to the code and as brief papers in the appendix. Beyond team results, we discuss the hackathon event and its hybrid format, which included physical hubs in Toronto, Montreal, San Francisco, Berlin, Lausanne, and Tokyo, alongside a global online hub to enable local and virtual collaboration. Overall, the event highlighted significant improvements in LLM capabilities since the previous year's hackathon, suggesting continued expansion of LLMs for applications in materials science and chemistry research. These outcomes demonstrate the dual utility of LLMs as both multipurpose models for diverse machine learning tasks and platforms for rapid prototyping custom applications in scientific research.

cs.LG↗

arXiv2024

The changing-look AGN SDSS J101152.98+544206.4 is returning to a type I state

Aims. We reported the discovery that a changing-look AGN SDSS J101152.98+544206.4 (J1011+5442 for short) gradually returns to the type 1 state after a short period between 2014 and 2019 in the faint type 1.9 state. Methods. Motivated by the rebrightening in optical and mid-infrared light curves from ZTF and WISE, we obtained the new spectroscopic observations by Xinglong 2.16-m, Lijiang 2.4-m, and MMT 6.5-m optical telescopes in 2024. Results. After changing the optical AGN type from 1 to 1.9 between 2003 and 2015 based on the repeat spectroscopy from the Time Domain Spectroscopic Survey, J1011+5442 returns to its type 1 state in 2024. We detect the significant and very broad Hbeta lines (FWHM > 5000 km/s) based on the new spectra, which suggests that J1011+5442 is in the intermediate state between the dim state in 2015 and the bright state in 2003. The long-term optical and mid-infrared light curves also show a brightening trend between 2019 and 2024 as the broad Hbeta line appears. The time lag of about 100 days between the mid-infrared and optical variability is consistent with the prediction of dust reverberation mapping. Conclusions. The behaviors of the photometric and spectroscopic observations of J1011+5442 are consistent with the argument that the repeating changing-look phenomenon is regulated by the variation of accretion rate.

astro-ph.HE↗

arXiv2024

Erase then Rectify: A Training-Free Parameter Editing Approach for Cost-Effective Graph Unlearning

Graph unlearning, which aims to eliminate the influence of specific nodes, edges, or attributes from a trained Graph Neural Network (GNN), is essential in applications where privacy, bias, or data obsolescence is a concern. However, existing graph unlearning techniques often necessitate additional training on the remaining data, leading to significant computational costs, particularly with large-scale graphs. To address these challenges, we propose a two-stage training-free approach, Erase then Rectify (ETR), designed for efficient and scalable graph unlearning while preserving the model utility. Specifically, we first build a theoretical foundation showing that masking parameters critical for unlearned samples enables effective unlearning. Building on this insight, the Erase stage strategically edits model parameters to eliminate the impact of unlearned samples and their propagated influence on intercorrelated nodes. To further ensure the GNN's utility, the Rectify stage devises a gradient approximation method to estimate the model's gradient on the remaining dataset, which is then used to enhance model performance. Overall, ETR achieves graph unlearning without additional training or full training data access, significantly reducing computational overhead and preserving data privacy. Extensive experiments on seven public datasets demonstrate the consistent superiority of ETR in model utility, unlearning efficiency, and unlearning effectiveness, establishing it as a promising solution for real-world graph unlearning challenges.

cs.LG↗

arXiv2024

LLMLight: Large Language Models as Traffic Signal Control Agents

Traffic Signal Control (TSC) is a crucial component in urban traffic management, aiming to optimize road network efficiency and reduce congestion. Traditional TSC methods, primarily based on transportation engineering and reinforcement learning (RL), often struggle with generalization abilities across varied traffic scenarios and lack interpretability. This paper presents LLMLight, a novel framework employing Large Language Models (LLMs) as decision-making agents for TSC. Specifically, the framework begins by instructing the LLM with a knowledgeable prompt detailing real-time traffic conditions. Leveraging the advanced generalization capabilities of LLMs, LLMLight engages a reasoning and decision-making process akin to human intuition for effective traffic control. Moreover, we build LightGPT, a specialized backbone LLM tailored for TSC tasks. By learning nuanced traffic patterns and control strategies, LightGPT enhances the LLMLight framework cost-effectively. Extensive experiments conducted on ten real-world and synthetic datasets, along with evaluations by fifteen human experts, demonstrate the exceptional effectiveness, generalization ability, and interpretability of LLMLight with LightGPT, outperforming nine baseline methods and ten advanced LLMs.

cs.AI↗

arXiv2024

Lightweight Method for Interactive 3D Medical Image Segmentation with Multi-Round Result Fusion

In medical imaging, precise annotation of lesions or organs is often required. However, 3D volumetric images typically consist of hundreds or thousands of slices, making the annotation process extremely time-consuming and laborious. Recently, the Segment Anything Model (SAM) has drawn widespread attention due to its remarkable zero-shot generalization capabilities in interactive segmentation. While researchers have explored adapting SAM for medical applications, such as using SAM adapters or constructing 3D SAM models, a key question remains: Can traditional CNN networks achieve the same strong zero-shot generalization in this task? In this paper, we propose the Lightweight Interactive Network for 3D Medical Image Segmentation (LIM-Net), a novel approach demonstrating the potential of compact CNN-based models. Built upon a 2D CNN backbone, LIM-Net initiates segmentation by generating a 2D prompt mask from user hints. This mask is then propagated through the 3D sequence via the Memory Module. To refine and stabilize results during interaction, the Multi-Round Result Fusion (MRF) Module selects and merges optimal masks from multiple rounds. Our extensive experiments across multiple datasets and modalities demonstrate LIM-Net's competitive performance. It exhibits stronger generalization to unseen data compared to SAM-based models, with competitive accuracy while requiring fewer interactions. Notably, LIM-Net's lightweight design offers significant advantages in deployment and inference efficiency, with low GPU memory consumption suitable for resource-constrained environments. These promising results demonstrate LIM-Net can serve as a strong baseline, complementing and contrasting with popular SAM models to further boost effective interactive medical image segmentation. The code will be released at \url{https://github.com/goodtime-123/LIM-Net}.

cs.CV↗

arXiv2024

Euler's Elastica Based Cartoon-Smooth-Texture Image Decomposition

We propose a novel model for decomposing grayscale images into three distinct components: the structural part, representing sharp boundaries and regions with strong light-to-dark transitions; the smooth part, capturing soft shadows and shades; and the oscillatory part, characterizing textures and noise. To capture the homogeneous structures, we introduce a combination of $L^0$-gradient and curvature regularization on level lines. This new regularization term enforces strong sparsity on the image gradient while reducing the undesirable staircase effects as well as preserving the geometry of contours. For the smoothly varying component, we utilize the $L^2$-norm of the Laplacian that favors isotropic smoothness. To capture the oscillation, we use the inverse Sobolev seminorm. To solve the associated minimization problem, we design an efficient operator-splitting algorithm. Our algorithm effectively addresses the challenging non-convex non-smooth problem by separating it into sub-problems. Each sub-problem can be solved either directly using closed-form solutions or efficiently using the Fast Fourier Transform (FFT). We provide systematic experiments, including ablation and comparison studies, to analyze our model's behaviors and demonstrate its effectiveness as well as efficiency.

cs.CV↗

arXiv2024

Behavior Backdoor for Deep Learning Models

The various post-processing methods for deep-learning-based models, such as quantification, pruning, and fine-tuning, play an increasingly important role in artificial intelligence technology, with pre-train large models as one of the main development directions. However, this popular series of post-processing behaviors targeting pre-training deep models has become a breeding ground for new adversarial security issues. In this study, we take the first step towards ``behavioral backdoor'' attack, which is defined as a behavior-triggered backdoor model training procedure, to reveal a new paradigm of backdoor attacks. In practice, we propose the first pipeline of implementing behavior backdoor, i.e., the Quantification Backdoor (QB) attack, upon exploiting model quantification method as the set trigger. Specifically, to adapt the optimization goal of behavior backdoor, we introduce the behavior-driven backdoor object optimizing method by a bi-target behavior backdoor training loss, thus we could guide the poisoned model optimization direction. To update the parameters across multiple models, we adopt the address-shared backdoor model training, thereby the gradient information could be utilized for multimodel collaborative optimization. Extensive experiments have been conducted on different models, datasets, and tasks, demonstrating the effectiveness of this novel backdoor attack and its potential application threats.

cs.LG↗

arXiv2024

SoK: Detection and Repair of Accessibility Issues

There is an increasing global emphasis on information accessibility, with numerous researchers actively developing automated tools to detect and repair accessibility issues, thereby ensuring that individuals with diverse abilities can independently access software products and services. However, current research still encounters significant challenges in two key areas: the absence of a comprehensive taxonomy of accessibility issue types, and the lack of comprehensive analysis of the capabilities of detection and repair tools, as well as the status of corresponding datasets. To address these challenges, this paper introduces the Accessibility Issue Analysis (AIA) framework. Utilizing this framework, we develop a comprehensive taxonomy that categorizes 55 types of accessibility issues across four pivotal dimensions: Perceivability, Operability, Understandability, and Robustness. This taxonomy has been rigorously recognized through a questionnaire survey (n=130). Building on this taxonomy, we conduct an in-depth analysis of existing detection and repair tools, as well as the status of corresponding datasets. In terms of tools, our findings indicate that 14 detection tools can identify 31 issue types, achieving a 56.3% rate (31/55). Meanwhile, 9 repair tools address just 13 issue types, with a 23.6% rate. In terms of datasets, those for detection tools cover 21 issue types, at a 38.1% coverage rate, whereas those for repair tools cover only 7 types, at a 12.7% coverage rate.

cs.SE↗

arXiv2024

3D Scene Graph Guided Vision-Language Pre-training

3D vision-language (VL) reasoning has gained significant attention due to its potential to bridge the 3D physical world with natural language descriptions. Existing approaches typically follow task-specific, highly specialized paradigms. Therefore, these methods focus on a limited range of reasoning sub-tasks and rely heavily on the hand-crafted modules and auxiliary losses. This highlights the need for a simpler, unified and general-purpose model. In this paper, we leverage the inherent connection between 3D scene graphs and natural language, proposing a 3D scene graph-guided vision-language pre-training (VLP) framework. Our approach utilizes modality encoders, graph convolutional layers and cross-attention layers to learn universal representations that adapt to a variety of 3D VL reasoning tasks, thereby eliminating the need for task-specific designs. The pre-training objectives include: 1) Scene graph-guided contrastive learning, which leverages the strong correlation between 3D scene graphs and natural language to align 3D objects with textual features at various fine-grained levels; and 2) Masked modality learning, which uses cross-modality information to reconstruct masked words and 3D objects. Instead of directly reconstructing the 3D point clouds of masked objects, we use position clues to predict their semantic categories. Extensive experiments demonstrate that our pre-training model, when fine-tuned on several downstream tasks, achieves performance comparable to or better than existing methods in tasks such as 3D visual grounding, 3D dense captioning, and 3D question answering.

cs.CV↗

arXiv2024

Point Cloud Unsupervised Pre-training via 3D Gaussian Splatting

Pre-training on large-scale unlabeled datasets contribute to the model achieving powerful performance on 3D vision tasks, especially when annotations are limited. However, existing rendering-based self-supervised frameworks are computationally demanding and memory-intensive during pre-training due to the inherent nature of volume rendering. In this paper, we propose an efficient framework named GS$^3$ to learn point cloud representation, which seamlessly integrates fast 3D Gaussian Splatting into the rendering-based framework. The core idea behind our framework is to pre-train the point cloud encoder by comparing rendered RGB images with real RGB images, as only Gaussian points enriched with learned rich geometric and appearance information can produce high-quality renderings. Specifically, we back-project the input RGB-D images into 3D space and use a point cloud encoder to extract point-wise features. Then, we predict 3D Gaussian points of the scene from the learned point cloud features and uses a tile-based rasterizer for image rendering. Finally, the pre-trained point cloud encoder can be fine-tuned to adapt to various downstream 3D tasks, including high-level perception tasks such as 3D segmentation and detection, as well as low-level tasks such as 3D scene reconstruction. Extensive experiments on downstream tasks demonstrate the strong transferability of the pre-trained point cloud encoder and the effectiveness of our self-supervised learning framework. In addition, our GS$^3$ framework is highly efficient, achieving approximately 9$\times$ pre-training speedup and less than 0.25$\times$ memory cost compared to the previous rendering-based framework Ponder.

cs.CV↗

arXiv2024

DocPedia: Unleashing the Power of Large Multimodal Model in the Frequency Domain for Versatile Document Understanding

This work presents DocPedia, a novel large multimodal model (LMM) for versatile OCR-free document understanding, capable of parsing images up to 2,560$\times$2,560 resolution. Unlike existing work either struggle with high-resolution documents or give up the large language model thus vision or language ability constrained, our DocPedia directly processes visual input in the frequency domain rather than the pixel space. The unique characteristic enables DocPedia to capture a greater amount of visual and textual information using a limited number of visual tokens. To consistently enhance both perception and comprehension abilities of our model, we develop a dual-stage training strategy and enrich instructions/annotations of all training tasks covering multiple document types. Extensive quantitative and qualitative experiments conducted on various publicly available benchmarks confirm the mutual benefits of jointly learning perception and comprehension tasks. The results provide further evidence of the effectiveness and superior performance of our DocPedia over other methods.

cs.CV↗

arXiv2024

Ultra-High-Efficiency Dual-Band Thin-Film Lithium Niobate Modulator Incorporating Low-k Underfill with 220 GHz Extrapolated Bandwidth for 390 Gbit/s PAM8 Transmission

High-performance electro-optic modulators play a critical role in modern telecommunication networks and intra-datacenter interconnects. Low driving voltage, large electro-optic bandwidth, compact device size, and multi-band operation ability are essential for various application scenarios, especially energy-efficient high-speed data transmission. However, it is challenging to meet all these requirements simultaneously. Here, we demonstrate a high-performance dual-band thin-film lithium niobate electro-optic modulator with low-k underfill to achieve overall performance improvement. The low-k material helps reduce the RF loss of the modulator and achieve perfect velocity matching with narrow electrode gap to overcome the voltage-bandwidth limitation, extending electro-optic bandwidth and enhancing modulation efficiency simultaneously. The fabricated 7-mm-long modulator exhibits a low half-wave voltage of 1.9 V at C-band and 1.54 V at O-band, featuring a low half-wave voltage-length product of 1.33 V*cm and 1.08 V*cm, respectively. Meanwhile, the novel design yields an ultra-wide extrapolated 3 dB bandwidth of 220 GHz (218 GHz) in the C-band (O-band). High-speed data transmission in both C- and O-bands using the same device has been demonstrated for the first time by PAM8 with data rates up to 390 Gbit/s, corresponding to a record-low energy consumption of 0.69 fJ/bit for next-generation cost-effective ultra-high-speed optical communications.

physics.optics↗

arXiv2024

Nd-BiMamba2: A Unified Bidirectional Architecture for Multi-Dimensional Data Processing

Deep learning models often require specially designed architectures to process data of different dimensions, such as 1D time series, 2D images, and 3D volumetric data. Existing bidirectional models mainly focus on sequential data, making it difficult to scale effectively to higher dimensions. To address this issue, we propose a novel multi-dimensional bidirectional neural network architecture, named Nd-BiMamba2, which efficiently handles 1D, 2D, and 3D data. Nd-BiMamba2 is based on the Mamba2 module and introduces innovative bidirectional processing mechanisms and adaptive padding strategies to capture bidirectional information in multi-dimensional data while maintaining computational efficiency. Unlike existing methods that require designing specific architectures for different dimensional data, Nd-BiMamba2 adopts a unified architecture with a modular design, simplifying development and maintenance costs. To verify the portability and flexibility of Nd-BiMamba2, we successfully exported it to ONNX and TorchScript and tested it on different hardware platforms (e.g., CPU, GPU, and mobile devices). Experimental results show that Nd-BiMamba2 runs efficiently on multiple platforms, demonstrating its potential in practical applications. The code is open-source: https://github.com/Human9000/nd-Mamba2-torch

cs.LG↗

arXiv2024

Gravitational lensing effect of black holes in effective quantum gravity

In the present work, we investigate the gravitational lensing effects of two quantum-modified black hole models recently proposed in effective quantum gravity. The light deflection angles are calculated for both the weak-field and strong-field limits. Furthermore, using the data for the supermassive black holes SgrA* and M87*, we calculate the lensing observables in the strong-field limit. We find that the quantum parameter plays a role analogous to the electric charge in weak gravitational lensing. In the strong-field limit, in contrast, the effects of the quantum parameter on the deflection angle, the angular separation, and the relative magnification are opposite to those of the electric charge, the scalar charge, and the quantum parameters in some gravity theories. The results indicate the crucial difference between the classical black holes and the two quantum-modified black hole models that depend on the quantum correction, making them a valuable tool for distinguishing these black hole models.

gr-qc↗

arXiv2024

Evaluation of the single-component thermal dust emission model in CMB experiments

It is well known that multiple Galactic thermal dust emission components may exist along the line of sight, but a single-component approximation is still widely used, since a full multi-component estimation requires a large number of frequency bands that are only available with future experiments. In light of this, we present a reliable, quantitative, and sensitive criterion to test the goodness of all kinds of dust emission estimations. This can not only give a definite answer to the quality of current single-component approximations; but also help determine preconditions of future multi-component estimations. Upon the former, previous works usually depend on a more complicated model to improve the single-component dust emission; however, our method is free from any additional model, and is sensitive enough to directly discover a substantial discrepancy between the Planck HFI data (100-857 GHz) and associated single-component dust emission estimations. This is the first time that the single-component estimation is ruled out by the data itself. For the latter, a similar procedure will be able to answer two important questions for estimating the complicated Galactic emissions: the number of necessary foreground components and their types.

astro-ph.CO↗

arXiv2024

Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs

Although Large Language Models (LLMs) have demonstrated significant capabilities in executing complex tasks in a zero-shot manner, they are susceptible to jailbreak attacks and can be manipulated to produce harmful outputs. Recently, a growing body of research has categorized jailbreak attacks into token-level and prompt-level attacks. However, previous work primarily overlooks the diverse key factors of jailbreak attacks, with most studies concentrating on LLM vulnerabilities and lacking exploration of defense-enhanced LLMs. To address these issues, we introduced $\textbf{JailTrickBench}$ to evaluate the impact of various attack settings on LLM performance and provide a baseline for jailbreak attacks, encouraging the adoption of a standardized evaluation framework. Specifically, we evaluate the eight key factors of implementing jailbreak attacks on LLMs from both target-level and attack-level perspectives. We further conduct seven representative jailbreak attacks on six defense methods across two widely used datasets, encompassing approximately 354 experiments with about 55,000 GPU hours on A800-80G. Our experimental results highlight the need for standardized benchmarking to evaluate these attacks on defense-enhanced LLMs. Our code is available at https://github.com/usail-hkust/JailTrickBench.

cs.CR↗

arXiv2024

Target Detection of Safety Protective Gear Using the Improved YOLOv5

In high-risk railway construction, personal protective equipment monitoring is critical but challenging due to small and frequently obstructed targets. We propose YOLO-EA, an innovative model that enhances safety measure detection by integrating ECA into its backbone's convolutional layers, improving discernment of minuscule objects like hardhats. YOLO-EA further refines target recognition under occlusion by replacing GIoU with EIoU loss. YOLO-EA's effectiveness was empirically substantiated using a dataset derived from real-world railway construction site surveillance footage. It outperforms YOLOv5, achieving 98.9% precision and 94.7% recall, up 2.5% and 0.5% respectively, while maintaining real-time performance at 70.774 fps. This highly efficient and precise YOLO-EA holds great promise for practical application in intricate construction scenarios, enforcing stringent safety compliance during complex railway construction projects.

cs.CV↗

arXiv2024

Exploring Intrinsic Magnetic Topological Insulators: The Case of EuIn$_2$As$_2$

In this study, ultrafast optical spectroscopy was employed to elucidate the intricate topological features of EuIn$_2$As$_2$, a promising candidate for a magnetic topological-crystalline axion insulator. Our investigation, focusing on the real-time evolution of topological states, unveiled a narrow surface magnetic gap (2$Δ_0$ $\simeq$ 8.2 meV)) emerging at the antiferromagnetic transition temperature ($T_N$ $\approx$ 16 K). Below $T_N$, two extremely low-energy collective modes, $ω_1$ and $ω_2$, with frequencies of $\sim$9.9 and 21.6 GHz at $T$ = 4 K, respectively, were observed, exhibiting strong temperature dependence. $ω_1$ correlates with an acoustic phonon, while $ω_2$ is associated with a magnon. The results suggest that EuIn$_2$As$_2$ has the potential to manifest a magnetic topological-crystalline axion insulator, presenting a small magnetic energy gap on the (001) surface. The findings further our understanding of the interplay between magnetism and topology in this material, showcasing its potential for applications in quantum information processing and spintronics.

cond-mat.str-el↗