arXiv subjects

Xi Wang

Publications and source records attributed to Xi Wang.

At least 325 records · Page 18Linked to original sources

arXiv2023

Optimizing and Fine-tuning Large Language Model for Urban Renewal

This study aims to innovatively explore adaptive applications of large language models (LLM) in urban renewal. It also aims to improve its performance and text generation quality for knowledge question-answering (QA) tasks. Based on the ChatGLM, we automatically generate QA datasets using urban renewal scientific literature corpora in a self-instruct manner and then conduct joint fine-tuning training on the model using the Prefix and LoRA fine-tuning methods to create an LLM for urban renewal. By guiding the LLM to automatically generate QA data based on prompt words and given text, it is possible to quickly obtain datasets in the urban renewal field and provide data support for the fine-tuning training of LLMs. The experimental results show that the joint fine-tuning training method proposed in this study can significantly improve the performance of LLM on the QA tasks. Compared with LoRA fine-tuning, the method improves the Bleu and Rouge metrics on the test by about 5%; compared with the model before fine-tuning, the method improves the Bleu and Rouge metrics by about 15%-20%. This study demonstrates the effectiveness and superiority of the joint fine-tuning method using Prefix and LoRA for ChatGLM in the urban renewal knowledge QA tasks. It provides a new approach for fine-tuning LLMs on urban renewal-related tasks.

cs.CL↗

arXiv2023

A Social-aware Gaussian Pre-trained Model for Effective Cold-start Recommendation

The use of pre-training is an emerging technique to enhance a neural model's performance, which has been shown to be effective for many neural language models such as BERT. This technique has also been used to enhance the performance of recommender systems. In such recommender systems, pre-training models are used to learn a better initialisation for both users and items. However, recent existing pre-trained recommender systems tend to only incorporate the user interaction data at the pre-training stage, making it difficult to deliver good recommendations, especially when the interaction data is sparse. To alleviate this common data sparsity issue, we propose to pre-train the recommendation model not only with the interaction data but also with other available information such as the social relations among users, thereby providing the recommender system with a better initialisation compared with solely relying on the user interaction data. We propose a novel recommendation model, the Social-aware Gaussian Pre-trained model (SGP), which encodes the user social relations and interaction data at the pre-training stage in a Graph Neural Network (GNN). Afterwards, in the subsequent fine-tuning stage, our SGP model adopts a Gaussian Mixture Model (GMM) to factorise these pre-trained embeddings for further training, thereby benefiting the cold-start users from these pre-built social relations. Our extensive experiments on three public datasets show that, in comparison to 16 competitive baselines, our SGP model significantly outperforms the best baseline by upto 7.7% in terms of NDCG@10. In addition, we show that SGP permits to effectively alleviate the cold-start problem, especially when users newly register to the system through their friends' suggestions.

cs.IR↗

arXiv2023

Model-aware 3D Eye Gaze from Weak and Few-shot Supervisions

The task of predicting 3D eye gaze from eye images can be performed either by (a) end-to-end learning for image-to-gaze mapping or by (b) fitting a 3D eye model onto images. The former case requires 3D gaze labels, while the latter requires eye semantics or landmarks to facilitate the model fitting. Although obtaining eye semantics and landmarks is relatively easy, fitting an accurate 3D eye model on them remains to be very challenging due to its ill-posed nature in general. On the other hand, obtaining large-scale 3D gaze data is cumbersome due to the required hardware setups and computational demands. In this work, we propose to predict 3D eye gaze from weak supervision of eye semantic segmentation masks and direct supervision of a few 3D gaze vectors. The proposed method combines the best of both worlds by leveraging large amounts of weak annotations--which are easy to obtain, and only a few 3D gaze vectors--which alleviate the difficulty of fitting 3D eye models on the semantic segmentation of eye images. Thus, the eye gaze vectors, used in the model fitting, are directly supervised using the few-shot gaze labels. Additionally, we propose a transformer-based network architecture, that serves as a solid baseline for our improvements. Our experiments in diverse settings illustrate the significant benefits of the proposed method, achieving about 5 degrees lower angular gaze error over the baseline, when only 0.05% 3D annotations of the training images are used. The source code is available at https://github.com/dimitris-christodoulou57/Model-aware_3D_Eye_Gaze.

cs.CV↗

arXiv2023

Lepton flavor violating decays $l_j\rightarrow l_i γγ$

In this paper, we study the lepton flavor violating decays of the $l_j\rightarrow l_i γγ$ (j=2, 3; i=1, 2) processes under the $U(1)_X$SSM. The $U(1)_X$SSM is the addition of three singlet new Higgs superfields and right-handed neutrinos to the minimal supersymmetric standard model (MSSM). Based on the latest experimental constraints of $l_j\rightarrow l_i γγ$, we analyze the effects of different sensitive parameters on the results and made reasonable predictions for future experimental development. Numerical analysis shows that many parameters have a greater or lesser effect on lepton flavor violation(LFV), but the main sensitive parameters and sources leading to LFV are the non-diagonal elements involving the initial and final leptons. This work could provide a basis for the discovery of the existence of new physics (NP).

hep-ph↗

arXiv2023

Improving Conversational Recommendation Systems via Bias Analysis and Language-Model-Enhanced Data Augmentation

Conversational Recommendation System (CRS) is a rapidly growing research area that has gained significant attention alongside advancements in language modelling techniques. However, the current state of conversational recommendation faces numerous challenges due to its relative novelty and limited existing contributions. In this study, we delve into benchmark datasets for developing CRS models and address potential biases arising from the feedback loop inherent in multi-turn interactions, including selection bias and multiple popularity bias variants. Drawing inspiration from the success of generative data via using language models and data augmentation techniques, we present two novel strategies, 'Once-Aug' and 'PopNudge', to enhance model performance while mitigating biases. Through extensive experiments on ReDial and TG-ReDial benchmark datasets, we show a consistent improvement of CRS techniques with our data augmentation approaches and offer additional insights on addressing multiple newly formulated biases.

cs.CL↗

arXiv2023

A Unified Framework for Modality-Agnostic Deepfakes Detection

As AI-generated content (AIGC) thrives, deepfakes have expanded from single-modality falsification to cross-modal fake content creation, where either audio or visual components can be manipulated. While using two unimodal detectors can detect audio-visual deepfakes, cross-modal forgery clues could be overlooked. Existing multimodal deepfake detection methods typically establish correspondence between the audio and visual modalities for binary real/fake classification, and require the co-occurrence of both modalities. However, in real-world multi-modal applications, missing modality scenarios may occur where either modality is unavailable. In such cases, audio-visual detection methods are less practical than two independent unimodal methods. Consequently, the detector can not always obtain the number or type of manipulated modalities beforehand, necessitating a fake-modality-agnostic audio-visual detector. In this work, we introduce a comprehensive framework that is agnostic to fake modalities, which facilitates the identification of multimodal deepfakes and handles situations with missing modalities, regardless of the manipulations embedded in audio, video, or even cross-modal forms. To enhance the modeling of cross-modal forgery clues, we employ audio-visual speech recognition (AVSR) as a preliminary task. This efficiently extracts speech correlations across modalities, a feature challenging for deepfakes to replicate. Additionally, we propose a dual-label detection approach that follows the structure of AVSR to support the independent detection of each modality. Extensive experiments on three audio-visual datasets show that our scheme outperforms state-of-the-art detection methods with promising performance on modality-agnostic audio/video deepfakes.

cs.MM↗

arXiv2023

The strong first order electroweak phase transition in the $U(1)_X$SSM

In the $U(1)_X$ extension of the minimal supersymmetric standard model, there are three Higgs singlets and the corresponding trilinear terms in the Higgs effective potential. These new terms can allow a strongly first order electroweak phase transition(EWPT) for a wide parameter space. We use codes CosmoTransitions to analyze the thermal evolution of the Higgs effective potential and calculate nucleation temperature. To find reasonable parameter spaces for strongly first order EWPT, we randomly scan many parameters, which is numerically expensive. The diagrams are shown, that can lead to the 125 GeV Higgs mass and satisfy the first order EWPT. This work benefits the phenomenology of $U(1)_X$SSM and exploring new physics beyond the SM.

hep-ph↗

arXiv2023

ContextSpeech: Expressive and Efficient Text-to-Speech for Paragraph Reading

While state-of-the-art Text-to-Speech systems can generate natural speech of very high quality at sentence level, they still meet great challenges in speech generation for paragraph / long-form reading. Such deficiencies are due to i) ignorance of cross-sentence contextual information, and ii) high computation and memory cost for long-form synthesis. To address these issues, this work develops a lightweight yet effective TTS system, ContextSpeech. Specifically, we first design a memory-cached recurrence mechanism to incorporate global text and speech context into sentence encoding. Then we construct hierarchically-structured textual semantics to broaden the scope for global context enhancement. Additionally, we integrate linearized self-attention to improve model efficiency. Experiments show that ContextSpeech significantly improves the voice quality and prosody expressiveness in paragraph reading with competitive model efficiency. Audio samples are available at: https://contextspeech.github.io/demo/

cs.CL↗

arXiv2023

LoRA ensembles for large language model fine-tuning

Finetuned LLMs often exhibit poor uncertainty quantification, manifesting as overconfidence, poor calibration, and unreliable prediction results on test data or out-of-distribution samples. One approach commonly used in vision for alleviating this issue is a deep ensemble, which constructs an ensemble by training the same model multiple times using different random initializations. However, there is a huge challenge to ensembling LLMs: the most effective LLMs are very, very large. Keeping a single LLM in memory is already challenging enough: keeping an ensemble of e.g. 5 LLMs in memory is impossible in many settings. To address these issues, we propose an ensemble approach using Low-Rank Adapters (LoRA), a parameter-efficient fine-tuning technique. Critically, these low-rank adapters represent a very small number of parameters, orders of magnitude less than the underlying pre-trained model. Thus, it is possible to construct large ensembles of LoRA adapters with almost the same computational overhead as using the original model. We find that LoRA ensembles, applied on its own or on top of pre-existing regularization techniques, gives consistent improvements in predictive accuracy and uncertainty quantification.

cs.LG↗

arXiv2023

OSM-Net: One-to-Many One-shot Talking Head Generation with Spontaneous Head Motions

One-shot talking head generation has no explicit head movement reference, thus it is difficult to generate talking heads with head motions. Some existing works only edit the mouth area and generate still talking heads, leading to unreal talking head performance. Other works construct one-to-one mapping between audio signal and head motion sequences, introducing ambiguity correspondences into the mapping since people can behave differently in head motions when speaking the same content. This unreasonable mapping form fails to model the diversity and produces either nearly static or even exaggerated head motions, which are unnatural and strange. Therefore, the one-shot talking head generation task is actually a one-to-many ill-posed problem and people present diverse head motions when speaking. Based on the above observation, we propose OSM-Net, a \textit{one-to-many} one-shot talking head generation network with natural head motions. OSM-Net constructs a motion space that contains rich and various clip-level head motion features. Each basis of the space represents a feature of meaningful head motion in a clip rather than just a frame, thus providing more coherent and natural motion changes in talking heads. The driving audio is mapped into the motion space, around which various motion features can be sampled within a reasonable range to achieve the one-to-many mapping. Besides, the landmark constraint and time window feature input improve the accurate expression feature extraction and video generation. Extensive experiments show that OSM-Net generates more natural realistic head motions under reasonable one-to-many mapping paradigm compared with other methods.

cs.CV↗

arXiv2023

Selecting which Dense Retriever to use for Zero-Shot Search

We propose the new problem of choosing which dense retrieval model to use when searching on a new collection for which no labels are available, i.e. in a zero-shot setting. Many dense retrieval models are readily available. Each model however is characterized by very differing search effectiveness -- not just on the test portion of the datasets in which the dense representations have been learned but, importantly, also across different datasets for which data was not used to learn the dense representations. This is because dense retrievers typically require training on a large amount of labeled data to achieve satisfactory search effectiveness in a specific dataset or domain. Moreover, effectiveness gains obtained by dense retrievers on datasets for which they are able to observe labels during training, do not necessarily generalise to datasets that have not been observed during training. This is however a hard problem: through empirical experimentation we show that methods inspired by recent work in unsupervised performance evaluation with the presence of domain shift in the area of computer vision and machine learning are not effective for choosing highly performing dense retrievers in our setup. The availability of reliable methods for the selection of dense retrieval models in zero-shot settings that do not require the collection of labels for evaluation would allow to streamline the widespread adoption of dense retrieval. This is therefore an important new problem we believe the information retrieval community should consider. Implementation of methods, along with raw result files and analysis scripts are made publicly available at https://www.github.com/anonymized.

cs.IR↗

arXiv2023

MuLanTTS: The Microsoft Speech Synthesis System for Blizzard Challenge 2023

In this paper, we present MuLanTTS, the Microsoft end-to-end neural text-to-speech (TTS) system designed for the Blizzard Challenge 2023. About 50 hours of audiobook corpus for French TTS as hub task and another 2 hours of speaker adaptation as spoke task are released to build synthesized voices for different test purposes including sentences, paragraphs, homographs, lists, etc. Building upon DelightfulTTS, we adopt contextual and emotion encoders to adapt the audiobook data to enrich beyond sentences for long-form prosody and dialogue expressiveness. Regarding the recording quality, we also apply denoise algorithms and long audio processing for both corpora. For the hub task, only the 50-hour single speaker data is used for building the TTS system, while for the spoke task, a multi-speaker source model is used for target speaker fine tuning. MuLanTTS achieves mean scores of quality assessment 4.3 and 4.5 in the respective tasks, statistically comparable with natural speech while keeping good similarity according to similarity assessment. The excellent and similarity in this year's new and dense statistical evaluation show the effectiveness of our proposed system in both tasks.

eess.AS↗

arXiv2023

Spatial Perceptual Quality Aware Adaptive Volumetric Video Streaming

Volumetric video offers a highly immersive viewing experience, but poses challenges in ensuring quality of experience (QoE) due to its high bandwidth requirements. In this paper, we explore the effect of viewing distance introduced by six degrees of freedom (6DoF) spatial navigation on user's perceived quality. By considering human visual resolution limitations, we propose a visual acuity model that describes the relationship between the virtual viewing distance and the tolerable boundary point cloud density. The proposed model satisfies spatial visual requirements during 6DoF exploration. Additionally, it dynamically adjusts quality levels to balance perceptual quality and bandwidth consumption. Furthermore, we present a QoE model to represent user's perceived quality at different viewing distances precisely. Extensive experimental results demonstrate that, the proposed scheme can effectively improve the overall average QoE by up to 26% over real networks and user traces, compared to existing baselines.

cs.MM↗

arXiv2023

Theoretical Corrections of $R_D$ and $R_{D^*}$

$R_{D^{(*)}}$ is the ratio of branching ratio $\overline{B} \rightarrow D^{(*)}τ\overlineν_τ$ to $\overline{B} \rightarrow D^{(*)}l\overlineν_{l}~(l=e,~μ)$. There is a gap of 2$σ_{exp}$ or more between its experimental value and the prediction under the standard model(SM). People extend the MSSM with the local gauge group $U(1)_X$ to obtain the $U(1)_X$SSM. Compared with MSSM, $U(1)_X$SSM has more superfields and effects. In $U(1)_X$SSM, we research the semileptonic decays $\overline{B} \rightarrow D^{(*)}l\overlineν_{l}$ and calculate $R_{D^{(*)}}$. The numerical results of $R_{D^{(*)}}$ are further corrected under $U(1)_X$SSM, which are much better than the SM predictions. After correction, the theoretical value of $R_{D^{(*)}}$ can reach one $σ_{exp}$ range of the averaged experiment central value.

hep-ph↗

arXiv2023

Large-Scale Automatic Audiobook Creation

An audiobook can dramatically improve a work of literature's accessibility and improve reader engagement. However, audiobooks can take hundreds of hours of human effort to create, edit, and publish. In this work, we present a system that can automatically generate high-quality audiobooks from online e-books. In particular, we leverage recent advances in neural text-to-speech to create and release thousands of human-quality, open-license audiobooks from the Project Gutenberg e-book collection. Our method can identify the proper subset of e-book content to read for a wide collection of diversely structured books and can operate on hundreds of books in parallel. Our system allows users to customize an audiobook's speaking speed and style, emotional intonation, and can even match a desired voice using a small amount of sample audio. This work contributed over five thousand open-license audiobooks and an interactive demo that allows users to quickly create their own customized audiobooks. To listen to the audiobook collection visit \url{https://aka.ms/audiobook}.

cs.SD↗

arXiv2023

BluNF: Blueprint Neural Field

Neural Radiance Fields (NeRFs) have revolutionized scene novel view synthesis, offering visually realistic, precise, and robust implicit reconstructions. While recent approaches enable NeRF editing, such as object removal, 3D shape modification, or material property manipulation, the manual annotation prior to such edits makes the process tedious. Additionally, traditional 2D interaction tools lack an accurate sense of 3D space, preventing precise manipulation and editing of scenes. In this paper, we introduce a novel approach, called Blueprint Neural Field (BluNF), to address these editing issues. BluNF provides a robust and user-friendly 2D blueprint, enabling intuitive scene editing. By leveraging implicit neural representation, BluNF constructs a blueprint of a scene using prior semantic and depth information. The generated blueprint allows effortless editing and manipulation of NeRF representations. We demonstrate BluNF's editability through an intuitive click-and-change mechanism, enabling 3D manipulations, such as masking, appearance modification, and object removal. Our approach significantly contributes to visual content creation, paving the way for further research in this area.

cs.CV↗

arXiv2023

MFR-Net: Multi-faceted Responsive Listening Head Generation via Denoising Diffusion Model

Face-to-face communication is a common scenario including roles of speakers and listeners. Most existing research methods focus on producing speaker videos, while the generation of listener heads remains largely overlooked. Responsive listening head generation is an important task that aims to model face-to-face communication scenarios by generating a listener head video given a speaker video and a listener head image. An ideal generated responsive listening video should respond to the speaker with attitude or viewpoint expressing while maintaining diversity in interaction patterns and accuracy in listener identity information. To achieve this goal, we propose the \textbf{M}ulti-\textbf{F}aceted \textbf{R}esponsive Listening Head Generation Network (MFR-Net). Specifically, MFR-Net employs the probabilistic denoising diffusion model to predict diverse head pose and expression features. In order to perform multi-faceted response to the speaker video, while maintaining accurate listener identity preservation, we design the Feature Aggregation Module to boost listener identity features and fuse them with other speaker-related features. Finally, a renderer finetuned with identity consistency loss produces the final listening head videos. Our extensive experiments demonstrate that MFR-Net not only achieves multi-faceted responses in diversity and speaker identity information but also in attitude and viewpoint expression.

cs.CV↗

arXiv2023

Riemannian Optimistic Algorithms

In this paper, we consider Riemannian online convex optimization with dynamic regret. First, we propose two novel algorithms, namely the Riemannian Online Optimistic Gradient Descent (R-OOGD) and the Riemannian Adaptive Online Optimistic Gradient Descent (R-AOOGD), which combine the advantages of classical optimistic algorithms with the rich geometric properties of Riemannian manifolds. We analyze the dynamic regrets of the R-OOGD and R-AOOGD in terms of regularity of the sequence of cost functions and comparators. Next, we apply the R-OOGD to Riemannian zero-sum games, leading to the Riemannian Optimistic Gradient Descent Ascent algorithm (R-OGDA). We analyze the average iterate and best-iterate of the R-OGDA in seeking Nash equilibrium for a two-player, zero-sum, g-convex-concave games. We also prove the last-iterate convergence of the R-OGDA for g-strongly convex-strongly concave problems. Our theoretical analysis shows that all proposed algorithms achieve results in regret and convergence that match their counterparts in Euclidean spaces. Finally, we conduct several experiments to verify our theoretical findings.

math.OC↗