Search

This study introduces an innovative approach to analyzing unlabeled data in high-energy physics (HEP) through the application of self-supervised learning (SSL). Faced with the increasing computational cost of producing high-quality labeled simulation samples at the CERN LHC, we propose leveraging large volumes of unlabeled data to overcome the limitations of supervised learning methods, which heavily rely on detailed labeled simulations. By pretraining models on these vast, mostly untapped datasets, we aim to learn generic representations that can be finetuned with smaller quantities of labeled data. Our methodology employs contrastive learning with augmentations on jet datasets to teach the model to recognize common representations of jets, addressing the unique challenges of LHC physics. Building on the groundwork laid by previous studies, our work demonstrates the critical ability of SSL to utilize large-scale unlabeled data effectively. We showcase the scalability and effectiveness of our models by gradually increasing the size of the pretraining dataset and assessing the resultant performance enhancements. Our results, obtained from experiments on two datasets -- JetClass, representing unlabeled data, and Top Tagging, serving as labeled simulation data -- show significant improvements in data efficiency, computational efficiency, and overall performance. These findings suggest that SSL can greatly enhance the adaptability of ML models to the HEP domain. This work opens new avenues for the use of unlabeled data in HEP and contributes to a better understanding the potential of SSL for scientific discovery., Comment: ACAT 2024 Proceedings

Heart sound auscultation holds significant importance in the diagnosis of congenital heart disease. However, existing methods for Heart Sound Diagnosis (HSD) tasks are predominantly limited to a few fixed categories, framing the HSD task as a rigid classification problem that does not fully align with medical practice and offers only limited information to physicians. Besides, such methods do not utilize echocardiography reports, the gold standard in the diagnosis of related diseases. To tackle this challenge, we introduce HSDreport, a new benchmark for HSD, which mandates the direct utilization of heart sounds obtained from auscultation to predict echocardiography reports. This benchmark aims to merge the convenience of auscultation with the comprehensive nature of echocardiography reports. First, we collect a new dataset for this benchmark, comprising 2,275 heart sound samples along with their corresponding reports. Subsequently, we develop a knowledge-aware query-based transformer to handle this task. The intent is to leverage the capabilities of medically pre-trained models and the internal knowledge of large language models (LLMs) to address the task's inherent complexity and variability, thereby enhancing the robustness and scientific validity of the method. Furthermore, our experimental results indicate that our method significantly outperforms traditional HSD approaches and existing multimodal LLMs in detecting key abnormalities in heart sounds.

The Segment Anything Model (SAM) exhibits impressive capabilities in zero-shot segmentation for natural images. Recently, SAM has gained a great deal of attention for its applications in medical image segmentation. However, to our best knowledge, no studies have shown how to harness the power of SAM for medical image classification. To fill this gap and make SAM a true ``foundation model'' for medical image analysis, it is highly desirable to customize SAM specifically for medical image classification. In this paper, we introduce SAMAug-C, an innovative augmentation method based on SAM for augmenting classification datasets by generating variants of the original images. The augmented datasets can be used to train a deep learning classification model, thereby boosting the classification performance. Furthermore, we propose a novel framework that simultaneously processes raw and SAMAug-C augmented image input, capitalizing on the complementary information that is offered by both. Experiments on three public datasets validate the effectiveness of our new approach.

Shape manipulation is a central research topic in computer graphics. Topology editing, such as breaking apart connections, joining disconnected ends, and filling/opening a topological hole, is generally more challenging than geometry editing. In this paper, we observe that the saddle points of the signed distance function (SDF) provide useful hints for altering surface topology deliberately. Based on this key observation, we parameterize the SDF into a cubic trivariate tensor-product B-spline function $F$ whose saddle points $\{\boldsymbol{s}_i\}$ can be quickly exhausted based on a subdivision-based root-finding technique coupled with Newton's method. Users can select one of the candidate points, say $\boldsymbol{s}_i$, to edit the topology in real time. In implementation, we add a compactly supported B-spline function rooted at $\boldsymbol{s}_i$, which we call a \textit{deformer} in this paper, to $F$, with its local coordinate system aligning with the three eigenvectors of the Hessian. Combined with ray marching technique, our interactive system operates at 30 FPS. Additionally, our system empowers users to create desired bulges or concavities on the surface. An extensive user study indicates that our system is user-friendly and intuitive to operate. We demonstrate the effectiveness and usefulness of our system in a range of applications, including fixing surface reconstruction errors, artistic work design, 3D medical imaging and simulation, and antiquity restoration. Please refer to the attached video for a demonstration., Comment: 10 pages, 18 figures

The growing prevalence of visually rich documents, such as webpages and scanned/digital-born documents (images, PDFs, etc.), has led to increased interest in automatic document understanding and information extraction across academia and industry. Although various document modalities, including image, text, layout, and structure, facilitate human information retrieval, the interconnected nature of these modalities presents challenges for neural networks. In this paper, we introduce WebLM, a multimodal pre-training network designed to address the limitations of solely modeling text and structure modalities of HTML in webpages. Instead of processing document images as unified natural images, WebLM integrates the hierarchical structure of document images to enhance the understanding of markup-language-based documents. Additionally, we propose several pre-training tasks to model the interaction among text, structure, and image modalities effectively. Empirical results demonstrate that the pre-trained WebLM significantly surpasses previous state-of-the-art pre-trained models across several webpage understanding tasks. The pre-trained models and code are available at https://github.com/X-LANCE/weblm.

Rapid progress in multimodal large language models (MLLMs) highlights the need to introduce challenging yet realistic benchmarks to the academic community, while existing benchmarks primarily focus on understanding simple natural images and short context. In this paper, we present MULTI as a cutting-edge benchmark for evaluating MLLMs on understanding complex tables and images, and reasoning with long context. MULTI provides multimodal inputs and requires responses that are either precise or open-ended, reflecting real-life examination styles. MULTI includes over 18,000 questions and challenges MLLMs with a variety of tasks, ranging from formula derivation to image detail analysis and cross-modality reasoning. We also introduce MULTI-Elite, a 500-question selected hard subset, and MULTI-Extend, with more than 4,500 external knowledge context pieces. Our evaluation indicates significant potential for MLLM advancement, with GPT-4V achieving a 63.7% accuracy rate on MULTI, in contrast to other MLLMs scoring between 28.5% and 55.3%. MULTI serves not only as a robust evaluation platform but also paves the way for the development of expert-level AI., Comment: 16 pages, 9 figures, 10 tables. Details and access are available at: https://OpenDFM.github.io/MULTI-Benchmark/

Computational experiments have emerged as a valuable method for studying complex systems, involving the algorithmization of counterfactuals. However, accurately representing real social systems in Agent-based Modeling (ABM) is challenging due to the diverse and intricate characteristics of humans, including bounded rationality and heterogeneity. To address this limitation, the integration of Large Language Models (LLMs) has been proposed, enabling agents to possess anthropomorphic abilities such as complex reasoning and autonomous learning. These agents, known as LLM-based Agent, offer the potential to enhance the anthropomorphism lacking in ABM. Nonetheless, the absence of explicit explainability in LLMs significantly hinders their application in the social sciences. Conversely, computational experiments excel in providing causal analysis of individual behaviors and complex phenomena. Thus, combining computational experiments with LLM-based Agent holds substantial research potential. This paper aims to present a comprehensive exploration of this fusion. Primarily, it outlines the historical development of agent structures and their evolution into artificial societies, emphasizing their importance in computational experiments. Then it elucidates the advantages that computational experiments and LLM-based Agents offer each other, considering the perspectives of LLM-based Agent for computational experiments and vice versa. Finally, this paper addresses the challenges and future trends in this research domain, offering guidance for subsequent related studies.

Large language models (LLMs) have established great success in the general domain of natural language processing. Their emerging task generalization and free-form dialogue capabilities can greatly help to design Chemical General Intelligence (CGI) to assist real-world research in chemistry. However, the existence of specialized language and knowledge in the field of chemistry, such as the highly informative SMILES notation, hinders the performance of general-domain LLMs in chemistry. To this end, we develop ChemDFM, the first LLM towards CGI. ChemDFM-13B is trained on 34B tokens from chemical literature, textbooks, and instructions as well as various data from the general domain. Therefore, it can store, understand, and reason over chemical knowledge and languages while still possessing advanced free-form language comprehension capabilities. Extensive quantitative evaluation shows that ChemDFM can significantly outperform the representative open-sourced LLMs. Moreover, ChemDFM can also surpass GPT-4 on a great portion of chemical tasks, despite the significant size difference. Further qualitative evaluations demonstrate the efficiency and effectiveness of ChemDFM in real-world research scenarios. We will open-source the ChemDFM model soon., Comment: 10 pages, 12 figures, 13 tables. Under Review

Dissipation is unavoidable in quantum systems. It usually induces decoherences and changes quantum correlations. To access the information of strongly correlated quantum matters, one has to overcome or suppress dissipation to extract out the underlying quantum phenomena. However, here we find an opposite effect that dissipation can be utilized as a powerful tool to probe the intrinsic correlations of quantum many-body systems. Applying highly-controllable dissipation in ultracold atomic systems, we observe a universal dissipative dynamics in strongly correlated one-dimensional quantum gases. The total particle number of this system follows a universal stretched-exponential decay, and the stretched exponent measures the anomalous dimension of the spectral function, a critical exponent characterizing strong quantum fluctuations of this system. This method could have broad applications in detecting strongly correlated features, including spin-charge separations and Fermi arcs in quantum materials.

Recently, there has been growing interest in using Large Language Models (LLMs) for scientific research. Numerous benchmarks have been proposed to evaluate the ability of LLMs for scientific research. However, current benchmarks are mostly based on pre-collected objective questions. This design suffers from data leakage problem and lacks the evaluation of subjective Q/A ability. In this paper, we propose SciEval, a comprehensive and multi-disciplinary evaluation benchmark to address these issues. Based on Bloom's taxonomy, SciEval covers four dimensions to systematically evaluate scientific research ability. In particular, we design a "dynamic" subset based on scientific principles to prevent evaluation from potential data leakage. Both objective and subjective questions are included in SciEval. These characteristics make SciEval a more effective benchmark for scientific research ability evaluation of LLMs. Comprehensive experiments on most advanced LLMs show that, although GPT-4 achieves SOTA performance compared to other LLMs, there is still substantial room for improvement, especially for dynamic questions. The data and codes are now publicly available., Comment: 12 pages, 17 figures, 12 tables. Under Review

While Large Language Models (LLMs) have demonstrated commendable performance across a myriad of domains and tasks, existing LLMs still exhibit a palpable deficit in handling multimodal functionalities, especially for the Spoken Question Answering (SQA) task which necessitates precise alignment and deep interaction between speech and text features. To address the SQA challenge on LLMs, we initially curated the free-form and open-ended LibriSQA dataset from Librispeech, comprising Part I with natural conversational formats and Part II encompassing multiple-choice questions followed by answers and analytical segments. Both parts collectively include 107k SQA pairs that cover various topics. Given the evident paucity of existing speech-text LLMs, we propose a lightweight, end-to-end framework to execute the SQA task on the LibriSQA, witnessing significant results. By reforming ASR into the SQA format, we further substantiate our framework's capability in handling ASR tasks. Our empirical findings bolster the LLMs' aptitude for aligning and comprehending multimodal information, paving the way for the development of universal multimodal LLMs. The dataset and demo can be found at https://github.com/ZihanZhaoSJTU/LibriSQA.

Inspired by the insights in cognitive science with respect to human memory and reasoning mechanism, a novel evolvable LLM-based (Large Language Model) agent framework is proposed as REMEMBERER. By equipping the LLM with a long-term experience memory, REMEMBERER is capable of exploiting the experiences from the past episodes even for different task goals, which excels an LLM-based agent with fixed exemplars or equipped with a transient working memory. We further introduce Reinforcement Learning with Experience Memory (RLEM) to update the memory. Thus, the whole system can learn from the experiences of both success and failure, and evolve its capability without fine-tuning the parameters of the LLM. In this way, the proposed REMEMBERER constitutes a semi-parametric RL agent. Extensive experiments are conducted on two RL task sets to evaluate the proposed framework. The average results with different initialization and training sets exceed the prior SOTA by 4% and 2% for the success rate on two task sets and demonstrate the superiority and robustness of REMEMBERER.

The Graphical User Interface (GUI) is pivotal for human interaction with the digital world, enabling efficient device control and the completion of complex tasks. Recent progress in Large Language Models (LLMs) and Vision Language Models (VLMs) offers the chance to create advanced GUI agents. To ensure their effectiveness, there's a pressing need for qualified benchmarks that provide trustworthy and reproducible evaluations -- a challenge current benchmarks often fail to address. To tackle this issue, we introduce Mobile-Env, a comprehensive toolkit tailored for creating GUI benchmarks in the Android mobile environment. Mobile-Env offers an isolated and controllable setting for reliable evaluations, and accommodates intermediate instructions and rewards to reflect real-world usage more naturally. Utilizing Mobile-Env, we collect an open-world task set across various real-world apps and a fixed world set, WikiHow, which captures a significant amount of dynamic online contents for fully controllable and reproducible evaluation. We conduct comprehensive evaluations of LLM agents using these benchmarks. Our findings reveal that even advanced models (e.g., GPT-4V and LLaMA-3) struggle with tasks that are relatively simple for humans. This highlights a crucial gap in current models and underscores the importance of developing more capable foundation models and more effective GUI agent frameworks.

We develop a theoretical model for calibrating the absorption imaging of cold atoms under high magnetic fields. Comparing to zero or low magnetic fields, the efficiency of the absorption imaging becomes lower while it requires an additional correction factor to obtain the absolute atom number under the Beer-Lambert law. Our model is based on the rate equations and can account many experimental imperfections such as Zeeman level crossing, failures of hyperfine structures, off-resonant couplings, and low repumping efficiency, etc. Based on this method, we can precisely calculate the correction factor for atom number measurement without any empirical or fitting parameters. Meanwhile, we use a cold-atom apparatus of rubidium-85 to experimentally verify our model. Besides these, we find our work can also serve as a benchmark to measure the polarization impurity of a circular-polarized laser beam with high sensitivities. We believe this work will bring convenience for most of cold-atom experiments using absorption imaging., Comment: 9 pages, 5 figures

Multimodal emotion recognition is a challenging research area that aims to fuse different modalities to predict human emotion. However, most existing models that are based on attention mechanisms have difficulty in learning emotionally relevant parts on their own. To solve this problem, we propose to incorporate external emotion-related knowledge in the co-attention based fusion of pre-trained models. To effectively incorporate this knowledge, we enhance the co-attention model with a Bayesian attention module (BAM) where a prior distribution is estimated using the emotion-related knowledge. Experimental results on the IEMOCAP dataset show that the proposed approach can outperform several state-of-the-art approaches by at least 0.7% unweighted accuracy (UA)., Comment: Accepted to IEEE ICASSP 2023

Power electronics converters have been widely used in aerospace system, DC transmission, distributed energy, smart grid and so forth, and the reliability of power electronics converters has been a hotspot in academia and industry. It is of great significance to carry out power electronics converters open-circuit faults monitoring and intelligent fault diagnosis to avoid secondary faults, reduce time and cost of operation and maintenance, and improve the reliability of power electronics system. Firstly, the faults features of power electronic converters are analyzed and summarized. Secondly, some AI-based fault diagnosis methods and application examples in power electronics converters are reviewed, and a fault diagnosis method based on the combination of random forests and transient fault features is proposed for three-phase power electronics converters. Finally, the future research challenges and directions of AI-based fault diagnosis methods are pointed out., Comment: Power System Technology

The research and applications of multimodal emotion recognition have become increasingly popular recently. However, multimodal emotion recognition faces the challenge of lack of data. To solve this problem, we propose to use transfer learning which leverages state-of-the-art pre-trained models including wav2vec 2.0 and BERT for this task. Multi-level fusion approaches including coattention-based early fusion and late fusion with the models trained on both embeddings are explored. Also, a multi-granularity framework which extracts not only frame-level speech embeddings but also segment-level embeddings including phone, syllable and word-level speech embeddings is proposed to further boost the performance. By combining our coattention-based early fusion model and late fusion model with the multi-granularity feature extraction framework, we obtain result that outperforms best baseline approaches by 1.3% unweighted accuracy (UA) on the IEMOCAP dataset., Comment: Accepted to INTERSPEECH 2022

We propose the boost asymmetry of the diboson productions in pp collisions as a new experimental observable, which can provide unique information on the proton structure. The boost asymmetry rises as the difference in the kinematics of the two bosons, that are coupled to the two different quark and antiquark initial states, respectively, and thus reflects different features of the quark and antiquark parton densities. By comparing the kinematics of the two bosons, such as the boson energy or rapidity, the diboson events with antiquark having higher energy than quark can be distinguished from those with quark having higher energy than antiquark. This would provide unique information in some special parton momentum fraction regions, which cannot be directly proved by current W and Z measurements at the Large Hadron Collider or other deep inelastic scattering experients.

Recently, the structural reading comprehension (SRC) task on web pages has attracted increasing research interests. Although previous SRC work has leveraged extra information such as HTML tags or XPaths, the informative topology of web pages is not effectively exploited. In this work, we propose a Topological Information Enhanced model (TIE), which transforms the token-level task into a tag-level task by introducing a two-stage process (i.e. node locating and answer refining). Based on that, TIE integrates Graph Attention Network (GAT) and Pre-trained Language Model (PLM) to leverage the topological information of both logical structures and spatial structures. Experimental results demonstrate that our model outperforms strong baselines and achieves state-of-the-art performances on the web-based SRC benchmark WebSRC at the time of writing. The code of TIE will be publicly available at https://github.com/X-LANCE/TIE., Comment: Accepted to NAACL 2022

We propose a scheme to realize bosonic fractional quantum Hall conductance in shaken honeycomb optical lattices. This scheme does not require a very flat band, and the necessary long-range interaction relies on s-wave scattering, which is common in many ultracold-atom experiments. By filling the lattice at 1/4 with identical bosons under Feshbach resonance, two degenerate many-body ground states share one Chern number of 1 and correspond exactly to the fractional quantum Hall conductance of 1/2. Meanwhile, we prove that the fractional quantum Hall state can be prepared by adiabatically turning on the lattice shaking, and the fractional conductance is robust in the shaken lattice. This provides an easy way to initialize and prepare the fractional quantum Hall states in ultracold-atom platforms, and it paves the way to investigate and simulate strongly correlated quantum matters with degenerate quantum gas.

Breathing solitons are nonlinear waves in which the energy concentrates in a localized and oscillatory fashion. Similarly to stationary solitons, breathers in dissipative systems can form stable bound states displaying molecule-like dynamics, which are frequently called breather molecules. So far, the experimental observation of optical breather molecules and the real-time detection of their dynamics have been limited to diatomic molecules, that is, bound states of only two breathers. In this work, we report on the observation of different types of breather complexes in a mode-locked fibre laser: multi-breather molecules, and molecular complexes originating from the binding of two breather-pair molecules or a breather pair molecule and a single breather. The inter-molecular temporal separation of the molecular complexes attains several hundreds of picoseconds, which is more than an order of magnitude larger than that of their stationary soliton counterparts and is a signature of long-range interactions. Numerical simulations of the laser model support our experimental findings. Moreover, non-equilibrium dynamics of breathing solitons are also observed, including breather collisions and annihilation. Our work opens the possibility of studying the dynamics of many-body systems in which breathers are the elementary constituents.

This paper presents SigVM, a novel blockchain virtual machine that supports an event-driven execution model, enabling developers to build autonomous smart contracts. Contracts in SigVM can emit signal events, on which other contracts can listen. Once an event is triggered, corresponding handler functions are automatically executed as signal transactions. We build an end-to-end blockchain platform SigChain and a contract language compiler SigSolid to realize the potential of SigVM. Experimental results show that our benchmark applications can be reimplemented with SigVM in an autonomous way, eliminating the dependency on unreliable mechanisms like off-chain relay servers. The development effort of reimplementing these contracts with SigVM is small, i.e., we modified on average 2.6% of the contract code., Comment: 14 Pages

Web search is an essential way for humans to obtain information, but it's still a great challenge for machines to understand the contents of web pages. In this paper, we introduce the task of structural reading comprehension (SRC) on web. Given a web page and a question about it, the task is to find the answer from the web page. This task requires a system not only to understand the semantics of texts but also the structure of the web page. Moreover, we proposed WebSRC, a novel Web-based Structural Reading Comprehension dataset. WebSRC consists of 400K question-answer pairs, which are collected from 6.4K web pages. Along with the QA pairs, corresponding HTML source code, screenshots, and metadata are also provided in our dataset. Each question in WebSRC requires a certain structural understanding of a web page to answer, and the answer is either a text span on the web page or yes/no. We evaluate various baselines on our dataset to show the difficulty of our task. We also investigate the usefulness of structural information and visual features. Our dataset and baselines have been publicly available at https://x-lance.github.io/WebSRC/., Comment: EMNLP 2021

Recently, pre-trained language models like BERT have shown promising performance on multiple natural language processing tasks. However, the application of these models has been limited due to their huge size. To reduce its size, a popular and efficient way is quantization. Nevertheless, most of the works focusing on BERT quantization adapted primary linear clustering as the quantization scheme, and few works try to upgrade it. That limits the performance of quantization significantly. In this paper, we implement k-means quantization and compare its performance on the fix-precision quantization of BERT with linear quantization. Through the comparison, we verify that the effect of the underlying quantization scheme upgrading is underestimated and there is a huge development potential of k-means quantization. Besides, we also compare the two quantization schemes on ALBERT models to explore the robustness differences between different pre-trained models., Comment: Accepted to NLPCC 2020

Zero-shot learning has been actively studied for image classification task to relieve the burden of annotating image labels. Interestingly, semantic segmentation task requires more labor-intensive pixel-wise annotation, but zero-shot semantic segmentation has only attracted limited research interest. Thus, we focus on zero-shot semantic segmentation, which aims to segment unseen objects with only category-level semantic representations provided for unseen categories. In this paper, we propose a novel Context-aware feature Generation Network (CaGNet), which can synthesize context-aware pixel-wise visual features for unseen categories based on category-level semantic representations and pixel-wise contextual information. The synthesized features are used to finetune the classifier to enable segmenting unseen objects. Furthermore, we extend pixel-wise feature generation and finetuning to patch-wise feature generation and finetuning, which additionally considers inter-pixel relationship. Experimental results on Pascal-VOC, Pascal-Context, and COCO-stuff show that our method significantly outperforms the existing zero-shot semantic segmentation methods. Code is available at https://github.com/bcmi/CaGNetv2-Zero-Shot-Semantic-Segmentation., Comment: accepted by TNNLS

Existing semantic segmentation models heavily rely on dense pixel-wise annotations. To reduce the annotation pressure, we focus on a challenging task named zero-shot semantic segmentation, which aims to segment unseen objects with zero annotations. This task can be accomplished by transferring knowledge across categories via semantic word embeddings. In this paper, we propose a novel context-aware feature generation method for zero-shot segmentation named CaGNet. In particular, with the observation that a pixel-wise feature highly depends on its contextual information, we insert a contextual module in a segmentation network to capture the pixel-wise contextual information, which guides the process of generating more diverse and context-aware features from semantic word embeddings. Our method achieves state-of-the-art results on three benchmark datasets for zero-shot segmentation. Codes are available at: https://github.com/bcmi/CaGNet-Zero-Shot-Semantic-Segmentation., Comment: Accepted by ACM MM 2020