arXiv subjects

Hao Yang

Publications and source records attributed to Hao Yang.

At least 253 records · Page 14Linked to original sources

arXiv2024

A Multitask Training Approach to Enhance Whisper with Contextual Biasing and Open-Vocabulary Keyword Spotting

The recognition of rare named entities, such as personal names and terminologies, is challenging for automatic speech recognition (ASR) systems, especially when they are not frequently observed in the training data. In this paper, we introduce keyword spotting enhanced Whisper (KWS-Whisper), a novel ASR system that leverages the Whisper model and performs open-vocabulary keyword spotting (OV-KWS) on the hidden states of the Whisper encoder to recognize user-defined named entities. These entities serve as prompts for the Whisper decoder. To optimize the model, we propose a multitask training approach that learns OV-KWS and contextual-ASR tasks. We evaluate our approach on Chinese Aishell hot word subsets and two internal code-switching test sets and show that it significantly improves the entity recall compared to the original Whisper model. Moreover, we demonstrate that the OV-KWS can be a plug-and-play module to enhance the ASR error correction methods and frozen Whisper models.

cs.AI↗

arXiv2024

Using Large Language Model for End-to-End Chinese ASR and NER

Mapping speech tokens to the same feature space as text tokens has become the paradigm for the integration of speech modality into decoder-only large language models (LLMs). An alternative approach is to use an encoder-decoder architecture that incorporates speech features through cross-attention. This approach, however, has received less attention in the literature. In this work, we connect the Whisper encoder with ChatGLM3 and provide in-depth comparisons of these two approaches using Chinese automatic speech recognition (ASR) and name entity recognition (NER) tasks. We evaluate them not only by conventional metrics like the F1 score but also by a novel fine-grained taxonomy of ASR-NER errors. Our experiments reveal that encoder-decoder architecture outperforms decoder-only architecture with a short context, while decoder-only architecture benefits from a long context as it fully exploits all layers of the LLM. By using LLM, we significantly reduced the entity omission errors and improved the entity ASR accuracy compared to the Conformer baseline. Additionally, we obtained a state-of-the-art (SOTA) F1 score of 0.805 on the AISHELL-NER test set by using chain-of-thought (CoT) NER which first infers long-form ASR transcriptions and then predicts NER labels.

cs.CL↗

arXiv2024

Exploring the impact of traffic signal control and connected and automated vehicles on intersections safety: A deep reinforcement learning approach

In transportation networks, intersections pose significant risks of collisions due to conflicting movements of vehicles approaching from different directions. To address this issue, various tools can exert influence on traffic safety both directly and indirectly. This study focuses on investigating the impact of adaptive signal control and connected and automated vehicles (CAVs) on intersection safety using a deep reinforcement learning approach. The objective is to assess the individual and combined effects of CAVs and adaptive traffic signal control on traffic safety, considering rear-end and crossing conflicts. The study employs a Deep Q Network (DQN) to regulate traffic signals and driving behaviors of both CAVs and Human Drive Vehicles (HDVs), and uses Time To Collision (TTC) metric to evaluate safety. The findings demonstrate a significant reduction in rear-end and crossing conflicts through the combined implementation of CAVs and DQNs-based traffic signal control. Additionally, the long-term positive effects of CAVs on safety are similar to the short-term effects of combined CAVs and DQNs-based traffic signal control. Overall, the study emphasizes the potential benefits of integrating CAVs and adaptive traffic signal control approaches in order to enhance traffic safety. The findings of this study could provide valuable insights for city officials and transportation authorities in developing effective strategies to improve safety at signalized intersections.

cs.AI↗

arXiv2024

Revisiting Counterfactual Regression through the Lens of Gromov-Wasserstein Information Bottleneck

As a promising individualized treatment effect (ITE) estimation method, counterfactual regression (CFR) maps individuals' covariates to a latent space and predicts their counterfactual outcomes. However, the selection bias between control and treatment groups often imbalances the two groups' latent distributions and negatively impacts this method's performance. In this study, we revisit counterfactual regression through the lens of information bottleneck and propose a novel learning paradigm called Gromov-Wasserstein information bottleneck (GWIB). In this paradigm, we learn CFR by maximizing the mutual information between covariates' latent representations and outcomes while penalizing the kernelized mutual information between the latent representations and the covariates. We demonstrate that the upper bound of the penalty term can be implemented as a new regularizer consisting of $i)$ the fused Gromov-Wasserstein distance between the latent representations of different groups and $ii)$ the gap between the transport cost generated by the model and the cross-group Gromov-Wasserstein distance between the latent representations and the covariates. GWIB effectively learns the CFR model through alternating optimization, suppressing selection bias while avoiding trivial latent distributions. Experiments on ITE estimation tasks show that GWIB consistently outperforms state-of-the-art CFR methods. To promote the research community, we release our project at https://github.com/peteryang1031/Causal-GWIB.

cs.LG↗

arXiv2024

Deep Ensemble Shape Calibration: Multi-Field Post-hoc Calibration in Online Advertising

In the e-commerce advertising scenario, estimating the true probabilities (known as a calibrated estimate) on Click-Through Rate (CTR) and Conversion Rate (CVR) is critical. Previous research has introduced numerous solutions for addressing the calibration problem. These methods typically involve the training of calibrators using a validation set and subsequently applying these calibrators to correct the original estimated values during online inference. However, what sets e-commerce advertising scenarios apart is the challenge of multi-field calibration. Multi-field calibration requires achieving calibration in each field. In order to achieve multi-field calibration, it is necessary to have a strong data utilization ability. Because the quantity of pCTR specified range for a single field-value (such as user ID and item ID) sample is relatively small, this makes the calibrator more difficult to train. However, existing methods have difficulty effectively addressing these issues. To solve these problems, we propose a new method named Deep Ensemble Shape Calibration (DESC). In terms of business understanding and interpretability, we decompose multi-field calibration into value calibration and shape calibration. We introduce innovative basis calibration functions, which enhance both function expression capabilities and data utilization by combining these basis calibration functions. A significant advancement lies in the development of an allocator capable of allocating the most suitable calibrators to different estimation error distributions within diverse fields and values. We achieve significant improvements in both public and industrial datasets. In online experiments, we observe a +2.5% increase in CVR and +4.0% in GMV (Gross Merchandise Volume). Our code is now available at: https://github.com/HaoYang0123/DESC.

cs.LG↗

arXiv2024

Preliminary analyses on dynamics and thermodynamics of rotating regular black holes

We investigate the dynamic and thermodynamic laws governing rotating regular black holes. By analyzing dynamic properties, i.e., the interaction between scalar particles and rotating regular black holes, we establish the criteria that determine whether such black holes satisfy the laws of thermodynamics or not. In addition, we provide the general form of conserved quantities related to rotating regular black holes, including the relevant flows associated with neutral scalar particles. Meanwhile, we reexamine the relationship between the third law of thermodynamics and weak cosmic censorship conjecture for rotating regular black holes. In accordance with the criteria mentioned above, we discuss the laws of thermodynamics for three models of rotating regular black holes: Rotating Hayward black holes, Kerr black-bounce solutions, and loop quantum gravity black holes. Our findings indicate that none of the three models satisfies the first law of thermodynamics. In particular, the first and third models fail to comply with the three laws of thermodynamics, while the second model satisfies only the second and third laws of thermodynamics. Finally, we attempt to rescue the laws of thermodynamics by modifying entropy or extending phase space. However, the two scenarios are not able to ensure the three laws of thermodynamics in the three models, which reveals an unusual property of rotating regular black holes.

gr-qc↗

arXiv2024

CHisIEC: An Information Extraction Corpus for Ancient Chinese History

Natural Language Processing (NLP) plays a pivotal role in the realm of Digital Humanities (DH) and serves as the cornerstone for advancing the structural analysis of historical and cultural heritage texts. This is particularly true for the domains of named entity recognition (NER) and relation extraction (RE). In our commitment to expediting ancient history and culture, we present the ``Chinese Historical Information Extraction Corpus''(CHisIEC). CHisIEC is a meticulously curated dataset designed to develop and evaluate NER and RE tasks, offering a resource to facilitate research in the field. Spanning a remarkable historical timeline encompassing data from 13 dynasties spanning over 1830 years, CHisIEC epitomizes the extensive temporal range and text heterogeneity inherent in Chinese historical documents. The dataset encompasses four distinct entity types and twelve relation types, resulting in a meticulously labeled dataset comprising 14,194 entities and 8,609 relations. To establish the robustness and versatility of our dataset, we have undertaken comprehensive experimentation involving models of various sizes and paradigms. Additionally, we have evaluated the capabilities of Large Language Models (LLMs) in the context of tasks related to ancient Chinese history. The dataset and code are available at \url{https://github.com/tangxuemei1995/CHisIEC}.

cs.CL↗

arXiv2024

OSR-ViT: A Simple and Modular Framework for Open-Set Object Detection and Discovery

An object detector's ability to detect and flag \textit{novel} objects during open-world deployments is critical for many real-world applications. Unfortunately, much of the work in open object detection today is disjointed and fails to adequately address applications that prioritize unknown object recall \textit{in addition to} known-class accuracy. To close this gap, we present a new task called Open-Set Object Detection and Discovery (OSODD) and as a solution propose the Open-Set Regions with ViT features (OSR-ViT) detection framework. OSR-ViT combines a class-agnostic proposal network with a powerful ViT-based classifier. Its modular design simplifies optimization and allows users to easily swap proposal solutions and feature extractors to best suit their application. Using our multifaceted evaluation protocol, we show that OSR-ViT obtains performance levels that far exceed state-of-the-art supervised methods. Our method also excels in low-data settings, outperforming supervised baselines using a fraction of the training data.

cs.CV↗

arXiv2024

A Novel Paradigm Boosting Translation Capabilities of Large Language Models

This paper presents a study on strategies to enhance the translation capabilities of large language models (LLMs) in the context of machine translation (MT) tasks. The paper proposes a novel paradigm consisting of three stages: Secondary Pre-training using Extensive Monolingual Data, Continual Pre-training with Interlinear Text Format Documents, and Leveraging Source-Language Consistent Instruction for Supervised Fine-Tuning. Previous research on LLMs focused on various strategies for supervised fine-tuning (SFT), but their effectiveness has been limited. While traditional machine translation approaches rely on vast amounts of parallel bilingual data, our paradigm highlights the importance of using smaller sets of high-quality bilingual data. We argue that the focus should be on augmenting LLMs' cross-lingual alignment abilities during pre-training rather than solely relying on extensive bilingual data during SFT. Experimental results conducted using the Llama2 model, particularly on Chinese-Llama2 after monolingual augmentation, demonstrate the improved translation capabilities of LLMs. A significant contribution of our approach lies in Stage2: Continual Pre-training with Interlinear Text Format Documents, which requires less than 1B training data, making our method highly efficient. Additionally, in Stage3, we observed that setting instructions consistent with the source language benefits the supervised fine-tuning process. Experimental results demonstrate that our approach surpasses previous work and achieves superior performance compared to models such as NLLB-54B and GPT3.5-text-davinci-003, despite having a significantly smaller parameter count of only 7B or 13B. This achievement establishes our method as a pioneering strategy in the field of machine translation.

cs.CL↗

arXiv2024

Mixed-Query Transformer: A Unified Image Segmentation Architecture

Existing unified image segmentation models either employ a unified architecture across multiple tasks but use separate weights tailored to each dataset, or apply a single set of weights to multiple datasets but are limited to a single task. In this paper, we introduce the Mixed-Query Transformer (MQ-Former), a unified architecture for multi-task and multi-dataset image segmentation using a single set of weights. To enable this, we propose a mixed query strategy, which can effectively and dynamically accommodate different types of objects without heuristic designs. In addition, the unified architecture allows us to use data augmentation with synthetic masks and captions to further improve model generalization. Experiments demonstrate that MQ-Former can not only effectively handle multiple segmentation datasets and tasks compared to specialized state-of-the-art models with competitive performance, but also generalize better to open-set segmentation tasks, evidenced by over 7 points higher performance than the prior art on the open-vocabulary SeginW benchmark.

cs.CV↗

arXiv2024

Doubly heavy hadrons production in ultraperipheral collision

We study the double heavy baryon $Ξ_{QQ'}$ and tetraquark $T_{QQ}$ production through photon-photon and photon-gluon fusion via ultraperipheral collisions at the LHC and FCC within the framework of nonrelativistic QCD factorization formalism. Various ion-ion collisions are taken into account, two cc(bb)-diquark configurations ($[cc(bb),{^3S_1}\mbox{-}\bar{\bm{3}}]$ and $[cc(bb),{^1S_0}\mbox{-}\bm{6}]$) and four bc-diquark configurations ($[bc,{^3S_1}\mbox{-}\bar{\bm{3}}]$, $[bc,{^3S_1}\mbox{-}\bm{6}]$, $[bc,{^1S_0}\mbox{-}\bar{\bm{3}}]$ and $[bc,{^1S_0}\mbox{-}\bm{6}]$) are considered in the calculation. Numerical results indicate that the $[cc,{^3S_1}\mbox{-}\bar{\bm{3}}]$ diquark provides dominant contribution for $Ξ_{cc}$ ($T_{cc}$) production, and a considerable number of $Ξ_{cc}$ ($T_{cc}$) can be produced. Due to the event topologies for ultraperipheral collision are very clear, the background from various QCD interactions can be suppressed, hence the experimental investigation for $Ξ_{cc}$ and $T_{cc}$ are feasible. The productions for $Ξ_{bc/bb}$ are also discussed, leaving only slightly possibility for $Ξ_{bc}$ through photon-gluon fusion with ultraperipheral collisions at the FCC.

hep-ph↗

arXiv2024

CoachLM: Automatic Instruction Revisions Improve the Data Quality in LLM Instruction Tuning

Instruction tuning is crucial for enabling Language Learning Models (LLMs) in responding to human instructions. The quality of instruction pairs used for tuning greatly affects the performance of LLMs. However, the manual creation of high-quality instruction datasets is costly, leading to the adoption of automatic generation of instruction pairs by LLMs as a popular alternative. To ensure the high quality of LLM-generated instruction datasets, several approaches have been proposed. Nevertheless, existing methods either compromise dataset integrity by filtering a large proportion of samples, or are unsuitable for industrial applications. In this paper, instead of discarding low-quality samples, we propose CoachLM, a novel approach to enhance the quality of instruction datasets through automatic revisions on samples in the dataset. CoachLM is trained from the samples revised by human experts and significantly increases the proportion of high-quality samples in the dataset from 17.7% to 78.9%. The effectiveness of CoachLM is further assessed on various real-world instruction test sets. The results show that CoachLM improves the instruction-following capabilities of the instruction-tuned LLM by an average of 29.9%, which even surpasses larger LLMs with nearly twice the number of parameters. Furthermore, CoachLM is successfully deployed in a data management system for LLMs at Huawei, resulting in an efficiency improvement of up to 20% in the cleaning of 40k real-world instruction pairs. We release various assets of CoachLM, including the training data, code and test set (https://github.com/lunyiliu/CoachLM).

cs.CL↗

arXiv2024

Consistency Enhancement-Based Deep Multiview Clustering via Contrastive Learning

Multiview clustering (MVC) segregates data samples into meaningful clusters by synthesizing information across multiple views. Moreover, deep learning-based methods have demonstrated their strong feature learning capabilities in MVC scenarios. However, effectively generalizing feature representations while maintaining consistency is still an intractable problem. In addition, most existing deep clustering methods based on contrastive learning overlook the consistency of the clustering representations during the clustering process. In this paper, we show how the above problems can be overcome and propose a consistent enhancement-based deep MVC method via contrastive learning (CCEC). Specifically, semantic connection blocks are incorporated into a feature representation to preserve the consistent information among multiple views. Furthermore, the representation process for clustering is enhanced through spectral clustering, and the consistency across multiple views is improved. Experiments conducted on five datasets demonstrate the effectiveness and superiority of our method in comparison with the state-of-the-art (SOTA) methods. The code for this method can be accessed at https://anonymous.4open.science/r/CCEC-E84E/.

cs.LG↗

arXiv2024

Picotesla-sensitivity microcavity optomechanical magnetometry

Cavity optomechanical systems have enabled precision sensing of magnetic fields, by leveraging the optical resonance-enhanced readout and mechanical resonance-enhanced response. Previous studies have successfully achieved scalable and reproducible microcavity optomechanical magnetometry (MCOM) by incorporating Terfenol-D thin films into high-quality ($Q$) factor whispering gallery mode (WGM) microcavities. However, the sensitivity was limited to 585 pT/Hz$^{1/2}$, over 20 times inferior to those using Terfenol-D particles. In this work, we propose and demonstrate a high-sensitivity and scalable MCOM approach by sputtering a FeGaB thin film onto a high-$Q$ SiO$_2$ WGM microdisk. Theoretical studies are conducted to explore the magnetic actuation constant and noise-limited sensitivity by varying the parameters of the FeGaB film and SiO$_2$ microdisk. Multiple magnetometers with different radii are fabricated and characterized. By utilizing a microdisk with a radius of 355 $μ$m and a thickness of 1 $μ$m, along with a FeGaB film with a radius of 330 $μ$m and a thickness of 1.3 $μ$m, we have achieved a remarkable peak sensitivity of 1.68 pT/Hz$^{1/2}$ at 9.52 MHz. This represents a significant improvement of over two orders of magnitude compared with previous studies employing sputtered Terfenol-D film. Notably, the magnetometer operates without a bias magnetic field, thanks to the remarkable soft magnetic properties of the FeGaB film. Furthermore, as a proof-of-concept, we have demonstrated the real-time measurement of a pulsed magnetic field simulating the corona current in a high-voltage transmission line using our developed magnetometer. These high-sensitivity magnetometers hold great potential for various applications, such as magnetic induction tomography and corona current monitoring.

physics.optics↗

arXiv2024

Musketeer: Joint Training for Multi-task Vision Language Model with Task Explanation Prompts

We present a vision-language model whose parameters are jointly trained on all tasks and fully shared among multiple heterogeneous tasks which may interfere with each other, resulting in a single model which we named Musketeer. The integration of knowledge across heterogeneous tasks is enabled by a novel feature called Task Explanation Prompt (TEP). With rich and structured information such as task input/output format, TEP reduces interference among tasks, allowing the model to focus on their shared structure. With a single model, Musketeer achieves results comparable to or better than strong baselines trained on single tasks, almost uniformly across multiple tasks.

cs.CV↗

arXiv2024

DeepSeek-VL: Towards Real-World Vision-Language Understanding

We present DeepSeek-VL, an open-source Vision-Language (VL) Model designed for real-world vision and language understanding applications. Our approach is structured around three key dimensions: We strive to ensure our data is diverse, scalable, and extensively covers real-world scenarios including web screenshots, PDFs, OCR, charts, and knowledge-based content, aiming for a comprehensive representation of practical contexts. Further, we create a use case taxonomy from real user scenarios and construct an instruction tuning dataset accordingly. The fine-tuning with this dataset substantially improves the model's user experience in practical applications. Considering efficiency and the demands of most real-world scenarios, DeepSeek-VL incorporates a hybrid vision encoder that efficiently processes high-resolution images (1024 x 1024), while maintaining a relatively low computational overhead. This design choice ensures the model's ability to capture critical semantic and detailed information across various visual tasks. We posit that a proficient Vision-Language Model should, foremost, possess strong language abilities. To ensure the preservation of LLM capabilities during pretraining, we investigate an effective VL pretraining strategy by integrating LLM training from the beginning and carefully managing the competitive dynamics observed between vision and language modalities. The DeepSeek-VL family (both 1.3B and 7B models) showcases superior user experiences as a vision-language chatbot in real-world applications, achieving state-of-the-art or competitive performance across a wide range of visual-language benchmarks at the same model size while maintaining robust performance on language-centric benchmarks. We have made both 1.3B and 7B models publicly accessible to foster innovations based on this foundation model.

cs.AI↗

arXiv2024

Hunting for sterile neutrino with future collider signatures

We study the feasibility to observe sterile neutrino at the high energy colliders with direct production channels through $e^+e^-$, $ep$ collision, and indirect production channels through decays of heavy meson, baryon and Higgs. For $e^+e^-$ collision, the $e^+e^-\to\barν_e N$ channel is explored with new signal selection method which tends to be efficient for light $m_N$, the constraints of active-sterile mixing $|U_{eN}|^2$ at the SuperKEKB, CEPC and ILC are expected to reach better lower limits than current experiments. For $ep$ collision, We investigate the heavy sterile neutrino production through a new channel via proton bremsstrahlung, i.e., $e^-γ\to NW^-$, hundreds of GeV heavy sterile neutrino can be probe and new limit on mixing is given. For heavy hadrons decay, the lepton-number-violating decays of $Λ_c,\ Ξ_{c},\ Ξ_{cc}$ and $Λ_b$ are explored via an intermediate on-shell Majorana neutrino in GeV scale. The branching fractions and the constraints for $|U_{\ell N}|^2$ are given, and hence may put new limits on this mass region. The ${\rm Higgs} \to Wμμπ$ channel is also considered to test massive neutrino within Higgs sector.

hep-ph↗

arXiv2024

Swin-UMamba: Mamba-based UNet with ImageNet-based pretraining

Accurate medical image segmentation demands the integration of multi-scale information, spanning from local features to global dependencies. However, it is challenging for existing methods to model long-range global information, where convolutional neural networks (CNNs) are constrained by their local receptive fields, and vision transformers (ViTs) suffer from high quadratic complexity of their attention mechanism. Recently, Mamba-based models have gained great attention for their impressive ability in long sequence modeling. Several studies have demonstrated that these models can outperform popular vision models in various tasks, offering higher accuracy, lower memory consumption, and less computational burden. However, existing Mamba-based models are mostly trained from scratch and do not explore the power of pretraining, which has been proven to be quite effective for data-efficient medical image analysis. This paper introduces a novel Mamba-based model, Swin-UMamba, designed specifically for medical image segmentation tasks, leveraging the advantages of ImageNet-based pretraining. Our experimental results reveal the vital role of ImageNet-based training in enhancing the performance of Mamba-based models. Swin-UMamba demonstrates superior performance with a large margin compared to CNNs, ViTs, and latest Mamba-based models. Notably, on AbdomenMRI, Encoscopy, and Microscopy datasets, Swin-UMamba outperforms its closest counterpart U-Mamba_Enc by an average score of 2.72%.

eess.IV↗