arXiv subjects

Yuxuan Wang

Publications and source records attributed to Yuxuan Wang.

At least 235 records · Page 13Linked to original sources

arXiv2023

Shock interaction in sphere symmetry

We investigate the interaction of two oncoming shock waves in spherical symmetry for an ideal barotropic fluid. Our research problem is how to establish a local in time solution after the interaction point and determine the state behind the shock waves. This problem is a double free boundary problem, as the position of the shock waves in space time is unknown. Our work is based on a number of previous studies, including Lisibach's, who studied the case of plane symmetry. To solve this problem, we will use an iterative regime to establish a local in time solution.

math.AP↗

arXiv2023

Halo: Estimation and Reduction of Hallucinations in Open-Source Weak Large Language Models

Large Language Models (LLMs) have revolutionized Natural Language Processing (NLP). Although convenient for research and practical applications, open-source LLMs with fewer parameters often suffer from severe hallucinations compared to their larger counterparts. This paper focuses on measuring and reducing hallucinations in BLOOM 7B, a representative of such weaker open-source LLMs that are publicly available for research and commercial applications. We introduce HaloCheck, a lightweight BlackBox knowledge-free framework designed to quantify the severity of hallucinations in LLMs. Additionally, we explore techniques like knowledge injection and teacher-student approaches to alleviate hallucinations in low-parameter LLMs. Our experiments effectively demonstrate the reduction of hallucinations in challenging domains for these LLMs.

cs.CL↗

arXiv2023

Zero-Shot Accent Conversion using Pseudo Siamese Disentanglement Network

The goal of accent conversion (AC) is to convert the accent of speech into the target accent while preserving the content and speaker identity. AC enables a variety of applications, such as language learning, speech content creation, and data augmentation. Previous methods rely on reference utterances in the inference phase or are unable to preserve speaker identity. To address these issues, we propose a zero-shot reference-free accent conversion method, which is able to convert unseen speakers' utterances into a target accent. Pseudo Siamese Disentanglement Network (PSDN) is proposed to disentangle the accent from the content representation. Experimental results show that our model generates speech samples with much higher accentedness than the input and comparable naturalness, on two-way conversion including foreign-to-native and native-to-foreign.

eess.AS↗

arXiv2023

Learning Semantic-Agnostic and Spatial-Aware Representation for Generalizable Visual-Audio Navigation

Visual-audio navigation (VAN) is attracting more and more attention from the robotic community due to its broad applications, \emph{e.g.}, household robots and rescue robots. In this task, an embodied agent must search for and navigate to the sound source with egocentric visual and audio observations. However, the existing methods are limited in two aspects: 1) poor generalization to unheard sound categories; 2) sample inefficient in training. Focusing on these two problems, we propose a brain-inspired plug-and-play method to learn a semantic-agnostic and spatial-aware representation for generalizable visual-audio navigation. We meticulously design two auxiliary tasks for respectively accelerating learning representations with the above-desired characteristics. With these two auxiliary tasks, the agent learns a spatially-correlated representation of visual and audio inputs that can be applied to work on environments with novel sounds and maps. Experiment results on realistic 3D scenes (Replica and Matterport3D) demonstrate that our method achieves better generalization performance when zero-shot transferred to scenes with unseen maps and unheard sound categories.

cs.RO↗

arXiv2023

PolyVoice: Language Models for Speech to Speech Translation

We propose PolyVoice, a language model-based framework for speech-to-speech translation (S2ST) system. Our framework consists of two language models: a translation language model and a speech synthesis language model. We use discretized speech units, which are generated in a fully unsupervised way, and thus our framework can be used for unwritten languages. For the speech synthesis part, we adopt the existing VALL-E X approach and build a unit-based audio language model. This grants our framework the ability to preserve the voice characteristics and the speaking style of the original speech. We examine our system on Chinese $\rightarrow$ English and English $\rightarrow$ Spanish pairs. Experimental results show that our system can generate speech with high translation quality and audio quality. Speech samples are available at https://speechtranslation.github.io/polyvoice.

cs.CL↗

arXiv2023

Query Encoder Distillation via Embedding Alignment is a Strong Baseline Method to Boost Dense Retriever Online Efficiency

The information retrieval community has made significant progress in improving the efficiency of Dual Encoder (DE) dense passage retrieval systems, making them suitable for latency-sensitive settings. However, many proposed procedures are often too complex or resource-intensive, which makes it difficult for practitioners to adopt them or identify sources of empirical gains. Therefore, in this work, we propose a trivially simple recipe to serve as a baseline method for boosting the efficiency of DE retrievers leveraging an asymmetric architecture. Our results demonstrate that even a 2-layer, BERT-based query encoder can still retain 92.5% of the full DE performance on the BEIR benchmark via unsupervised distillation and proper student initialization. We hope that our findings will encourage the community to re-evaluate the trade-offs between method complexity and performance improvements.

cs.IR↗

arXiv2023

VSTAR: A Video-grounded Dialogue Dataset for Situated Semantic Understanding with Scene and Topic Transitions

Video-grounded dialogue understanding is a challenging problem that requires machine to perceive, parse and reason over situated semantics extracted from weakly aligned video and dialogues. Most existing benchmarks treat both modalities the same as a frame-independent visual understanding task, while neglecting the intrinsic attributes in multimodal dialogues, such as scene and topic transitions. In this paper, we present Video-grounded Scene&Topic AwaRe dialogue (VSTAR) dataset, a large scale video-grounded dialogue understanding dataset based on 395 TV series. Based on VSTAR, we propose two benchmarks for video-grounded dialogue understanding: scene segmentation and topic segmentation, and one benchmark for video-grounded dialogue generation. Comprehensive experiments are performed on these benchmarks to demonstrate the importance of multimodal information and segments in video-grounded dialogue understanding and generation.

cs.CV↗

arXiv2023

Shuo Wen Jie Zi: Rethinking Dictionaries and Glyphs for Chinese Language Pre-training

We introduce CDBERT, a new learning paradigm that enhances the semantics understanding ability of the Chinese PLMs with dictionary knowledge and structure of Chinese characters. We name the two core modules of CDBERT as Shuowen and Jiezi, where Shuowen refers to the process of retrieving the most appropriate meaning from Chinese dictionaries and Jiezi refers to the process of enhancing characters' glyph representations with structure understanding. To facilitate dictionary understanding, we propose three pre-training tasks, i.e., Masked Entry Modeling, Contrastive Learning for Synonym and Antonym, and Example Learning. We evaluate our method on both modern Chinese understanding benchmark CLUE and ancient Chinese benchmark CCLUE. Moreover, we propose a new polysemy discrimination task PolyMRC based on the collected dictionary of ancient Chinese. Our paradigm demonstrates consistent improvements on previous Chinese PLMs across all tasks. Moreover, our approach yields significant boosting on few-shot setting of ancient Chinese understanding.

cs.CL↗

arXiv2023

Efficient Neural Music Generation

Recent progress in music generation has been remarkably advanced by the state-of-the-art MusicLM, which comprises a hierarchy of three LMs, respectively, for semantic, coarse acoustic, and fine acoustic modelings. Yet, sampling with the MusicLM requires processing through these LMs one by one to obtain the fine-grained acoustic tokens, making it computationally expensive and prohibitive for a real-time generation. Efficient music generation with a quality on par with MusicLM remains a significant challenge. In this paper, we present MeLoDy (M for music; L for LM; D for diffusion), an LM-guided diffusion model that generates music audios of state-of-the-art quality meanwhile reducing 95.7% or 99.6% forward passes in MusicLM, respectively, for sampling 10s or 30s music. MeLoDy inherits the highest-level LM from MusicLM for semantic modeling, and applies a novel dual-path diffusion (DPD) model and an audio VAE-GAN to efficiently decode the conditioning semantic tokens into waveform. DPD is proposed to simultaneously model the coarse and fine acoustics by incorporating the semantic information into segments of latents effectively via cross-attention at each denoising step. Our experimental results suggest the superiority of MeLoDy, not only in its practical advantages on sampling speed and infinitely continuable generation, but also in its state-of-the-art musicality, audio quality, and text correlation. Our samples are available at https://Efficient-MeLoDy.github.io/.

cs.SD↗

arXiv2023

Quantum chaos and phase transition in the Yukawa-SYK model

We analyze the quantum chaotic behavior of the Yukawa-SYK model as a function of filling and temperature, which describes random Yukawa interactions between $N$ complex fermions and $M$ bosons in zero spatial dimensions, for both the non-Fermi liquid and insulating states at finite temperature and chemical potential. We solve the ladder equations for the out-of-time-order correlator (OTOC) for both the bosons and fermions. Despite the appearance of the chemical potential in the Hamiltonian, which explicitly introduces an additional energy scale, the OTOCs for the fermions and bosons in the non-Fermi liquid state turn out to be unaffected, and the Lyapunov exponents that diagnose chaos remain maximal. As the chemical potential increases, the system is known to experience a first-order transition from a critical phase to a gapped insulating phase. We postulate that the boundary of the region in parameter space where each phase is (meta)stable coincides with the curve on which the Lyapunov exponent is maximal. By calculating the exponent in the insulating phase and comparing to numerical results on the boundaries of stability, we show that this is plausible.

cond-mat.str-el↗

arXiv2023

Two Results on Low-Rank Heavy-Tailed Multiresponse Regressions

This paper gives two theoretical results on estimating low-rank parameter matrices for linear models with multivariate responses. We first focus on robust parameter estimation of low-rank multi-task learning with heavy-tailed data and quantization scenarios. It comprises two cases: quantization under heavy-tailed responses and quantization with both heavy-tailed covariate and response variables. For each case, our theory shows that the proposed estimator has a minmax near-optimal convergence rate. We then further investigate low-rank linear models with heavy-tailed matrix-type responses. The theory shows that when the random noise has only $(2+ε)$-order moment, our robust estimator still has almost the same statistical convergence rate as that of sub-Gaussian data. Moreover, our simulation experiments confirm the correctness of theories and show the superiority of our estimators.

math.ST↗

arXiv2023

Language-Universal Phonetic Representation in Multilingual Speech Pretraining for Low-Resource Speech Recognition

We improve low-resource ASR by integrating the ideas of multilingual training and self-supervised learning. Concretely, we leverage an International Phonetic Alphabet (IPA) multilingual model to create frame-level pseudo labels for unlabeled speech, and use these pseudo labels to guide hidden-unit BERT (HuBERT) based speech pretraining in a phonetically-informed manner. The experiments on the Multilingual Speech (MLS) Corpus show that the proposed approach consistently outperforms the standard HuBERT on all the target languages. Moreover, on 3 of the 4 languages, comparing to the standard HuBERT, the approach performs better, meanwhile is able to save supervised training data by 1.5k hours (75%) at most. Our approach outperforms most of the state of the arts, with much less pretraining data in terms of hours and language diversity. Compared to XLSR-53 and a retraining based multilingual method, our approach performs better with full and limited finetuning data scenarios.

eess.AS↗

arXiv2023

Language-universal phonetic encoder for low-resource speech recognition

Multilingual training is effective in improving low-resource ASR, which may partially be explained by phonetic representation sharing between languages. In end-to-end (E2E) ASR systems, graphemes are often used as basic modeling units, however graphemes may not be ideal for multilingual phonetic sharing. In this paper, we leverage International Phonetic Alphabet (IPA) based language-universal phonetic model to improve low-resource ASR performances, for the first time within the attention encoder-decoder architecture. We propose an adaptation method on the phonetic IPA model to further improve the proposed approach on extreme low-resource languages. Experiments carried out on the open-source MLS corpus and our internal databases show our approach outperforms baseline monolingual models and most state-of-the-art works. Our main approach and adaptation are effective on extremely low-resource languages, even within domain- and language-mismatched scenarios.

eess.AS↗

arXiv2023

Higher-order topological superconductivity in monolayer WTe$_2$ from repulsive interactions

Superconductivity has been experimentally observed in monolayer WTe2, which in-plane field measurements suggested are of spin-triplet nature. Furthermore, it has been proposed that with a $p$-wave pairing, the material is a second-order topological superconductor with a pair of Majorana zero modes at the corners of a finite sample. We show that for a repulsive on-site interaction and sizable Fermi surfaces, the desired p-wave state arises naturally due to the Kohn-Luttinger mechanism, and indeed a finite superconducting sample hosts corner Majorana zero modes. We study the behavior of the critical temperature in response to external in-plane magnetic fields. We find an enhancement to the critical temperature that depends on the direction of the magnetic field, which can be directly verified experimentally.

cond-mat.supr-con↗

arXiv2023

Ph3pyWF: An automated workflow software package for ceramic lattice thermal conductivity calculation

This paper presents a Python software package, Ph3pyWF, providing a more convenient platform to realize high-throughput analysis of lattice thermal conductivity for ceramic materials. The interface of Ph3pyWF is friendly for users with different needs and from different level. For novices of interests, the inputs can be quite simple, just with initial unit cell structure. Other parameters would be automatically filled. And for expert-level researchers with varied requirements, plenty of procedure parameters can be customized. The core concept of Ph3pyWF is to build a data exchange and task management system with high efficiency. The design details of the Ph3pyWF will be clarified in this paper and following with a few typical oxide ceramics examples to demonstrate the applicability of this software package.

cond-mat.mtrl-sci↗

arXiv2023

Significant Light Extraction and Power Efficiency Enhancement of Organic Light Emitting Diodes by Subwavelength Dielectric-Nanomesh Using Large-area Nanoimprint

To improve the power efficiency of light emitting diodes (OLEDs), we developed a novel OLED structure, termed Dielectric-Nanomesh OLED (DNM-OLED), fabricated by large-area nanoimprint lithography (NIL). A dielectric-nanomesh substrate with a subwavelength nanomesh grating patterned into glass releases the photons trapped in ITO and organic layers by guided modes into leaky modes. And the dielectric-nanomesh substrate modifies the entire OLED layers into a corrugated configuration, which further lowers the parasitic resistance and hence the operating voltage. For a red phosphorescent OLED in our demonstration, with the DNM-OLED structure, the light extraction efficiency was enhanced by 1.33 fold and the operating voltage was lowered by 46%, acting together, leading to a 1.8-fold enhancement in power efficiency. Besides red OELDs, the DNM-OLED structure was also shown to be able to work for green and blue OELDs and achieved enhanced light extraction efficiency (1.31 fold for green light, 1.45 fold for blue light) without further structure modification, which demonstrated the light extraction enhancement by the DNM-OLED is broadband.

physics.optics↗

arXiv2023

Over 100% Light Extraction Enhancement of Organic Light Emitting Diodes Using Flat Moire Micro-Lens Array Fabricated by Double Nanoimprint Lithography Over a Large Area

To improve the light extraction efficiency of organic light emitting diodes (OLEDs), we developed a novel substrate, i.e., a metamaterial based flat Moire micro-lens array formed using double nanoimprint, termed Mlens-array, consisting of a hexagonal moiré pattern pillar array. By choosing a low refractive index dielectric material for the pillar array and a high refractive index dielectric material for the layer capped on top of the pillar array, we fabricated the Mlens-array behaving as a conventional convex optical micro-lens array. The Mlens-array was fabricated on a 4-inch wafer-size glass substrate by double-cycle compositional nanoimprint lithography (NIL) which is easy for achieving high throughput fabrication in large-scale. Applying the Mlens-array substrate in a typical green-emitting OLED, the light extraction efficiency was enhanced by over 100% (2.08-fold) compared to a control device fabricated on the conventional planar glass substrate.

physics.optics↗

arXiv2023

Enhancing Light Extraction of Organic Light Emitting Diodes by Deep-Groove High-index Dielectric Nanomesh Using Large-area Nanoimprint

To solve the conventional conflict between maintaining good charge transport property and achieving high light extraction efficiency when using micro/nanostructure patterned substrates to extract light from organic light emitting diodes (OLEDs), we developed a novel OLED structure, termed High-index Deep-Groove Dielectric Nanomesh OLED (HDNM-OLED), fabricated by large-area nanoimprint lithography (NIL). The key component is a nanostructure-patterned substrate embedded with a high-index deep-groove nanomesh and capped with a low-index planarization layer. The high-index and deep-groove nanomesh efficiently releases the tapped photons to achieve significantly enhanced light extraction. And the planarization layer helps to maintain the good charge transport property of the organic active layers deposited on top of it. For a green phosphorescent OLED in our demonstration, with the HDNM-OLED structure, compared to planar conventional ITO-OLED structure, the external quantum efficiency (EQE) was enhanced by 1.85-fold from 26% to 48% and power efficiency was enhanced by 1.86-fold from 42lm/W to 79lm/W. Besides green OELDs, the HDNM-OLED structure was also shown to be able to work for red and blue-emitting OELDs and achieved enhanced light extraction efficiency (1.58-fold for red light, 1.86-fold for blue light) without further structure modification, which demonstrated the light extraction enhancement by the HDNM-OLED is broadband.

physics.optics↗