arXiv subjects

Hao Zhang

Publications and source records attributed to Hao Zhang.

At least 793 records · Page 44Linked to original sources

arXiv2023

Regularized Data Programming with Automated Bayesian Prior Selection

The cost of manual data labeling can be a significant obstacle in supervised learning. Data programming (DP) offers a weakly supervised solution for training dataset creation, wherein the outputs of user-defined programmatic labeling functions (LFs) are reconciled through unsupervised learning. However, DP can fail to outperform an unweighted majority vote in some scenarios, including low-data contexts. This work introduces a Bayesian extension of classical DP that mitigates failures of unsupervised learning by augmenting the DP objective with regularization terms. Regularized learning is achieved through maximum a posteriori estimation with informative priors. Majority vote is proposed as a proxy signal for automated prior parameter selection. Results suggest that regularized DP improves performance relative to maximum likelihood and majority voting, confers greater interpretability, and bolsters performance in low-data regimes.

cs.LG↗

arXiv2023

Open-NeRF: Towards Open Vocabulary NeRF Decomposition

In this paper, we address the challenge of decomposing Neural Radiance Fields (NeRF) into objects from an open vocabulary, a critical task for object manipulation in 3D reconstruction and view synthesis. Current techniques for NeRF decomposition involve a trade-off between the flexibility of processing open-vocabulary queries and the accuracy of 3D segmentation. We present, Open-vocabulary Embedded Neural Radiance Fields (Open-NeRF), that leverage large-scale, off-the-shelf, segmentation models like the Segment Anything Model (SAM) and introduce an integrate-and-distill paradigm with hierarchical embeddings to achieve both the flexibility of open-vocabulary querying and 3D segmentation accuracy. Open-NeRF first utilizes large-scale foundation models to generate hierarchical 2D mask proposals from varying viewpoints. These proposals are then aligned via tracking approaches and integrated within the 3D space and subsequently distilled into the 3D field. This process ensures consistent recognition and granularity of objects from different viewpoints, even in challenging scenarios involving occlusion and indistinct features. Our experimental results show that the proposed Open-NeRF outperforms state-of-the-art methods such as LERF \cite{lerf} and FFD \cite{ffd} in open-vocabulary scenarios. Open-NeRF offers a promising solution to NeRF decomposition, guided by open-vocabulary queries, enabling novel applications in robotics and vision-language interaction in open-world 3D scenes.

cs.CV↗

arXiv2023

Long-Form Speech Translation through Segmentation with Finite-State Decoding Constraints on Large Language Models

One challenge in speech translation is that plenty of spoken content is long-form, but short units are necessary for obtaining high-quality translations. To address this mismatch, we adapt large language models (LLMs) to split long ASR transcripts into segments that can be independently translated so as to maximize the overall translation quality. We overcome the tendency of hallucination in LLMs by incorporating finite-state constraints during decoding; these eliminate invalid outputs without requiring additional training. We discover that LLMs are adaptable to transcripts containing ASR errors through prompt-tuning or fine-tuning. Relative to a state-of-the-art automatic punctuation baseline, our best LLM improves the average BLEU by 2.9 points for English-German, English-Spanish, and English-Arabic TED talk translation in 9 test sets, just by improving segmentation.

cs.CL↗

arXiv2023

Interaction-Driven Active 3D Reconstruction with Object Interiors

We introduce an active 3D reconstruction method which integrates visual perception, robot-object interaction, and 3D scanning to recover both the exterior and interior, i.e., unexposed, geometries of a target 3D object. Unlike other works in active vision which focus on optimizing camera viewpoints to better investigate the environment, the primary feature of our reconstruction is an analysis of the interactability of various parts of the target object and the ensuing part manipulation by a robot to enable scanning of occluded regions. As a result, an understanding of part articulations of the target object is obtained on top of complete geometry acquisition. Our method operates fully automatically by a Fetch robot with built-in RGBD sensors. It iterates between interaction analysis and interaction-driven reconstruction, scanning and reconstructing detected moveable parts one at a time, where both the articulated part detection and mesh reconstruction are carried out by neural networks. In the final step, all the remaining, non-articulated parts, including all the interior structures that had been exposed by prior part manipulations and subsequently scanned, are reconstructed to complete the acquisition. We demonstrate the performance of our method via qualitative and quantitative evaluation, ablation studies, comparisons to alternatives, as well as experiments in a real environment.

cs.CV↗

arXiv2023

Ultralow lattice thermal transport and considerable wave-like phonon tunneling in chalcogenide perovskite BaZrS$_3$

Chalcogenide perovskites provide a promising avenue for non-toxic, stable thermoelectric materials. Here, thermal transport and thermoelectric properties of BaZrS$_3$ as a typical orthorhombic perovskite are investigated. An extremely low lattice thermal conductivity $κ_L$ of 1.84 W/mK at 300 K is revealed for BaZrS$_3$, due to the softening effect of Ba atoms on the lattice and the strong anharmonicity caused by the twisted structure. We demonstrate that coherence contributions to $κ_L$, arising from wave-like phonon tunneling, leading to a 18 \% thermal transport contribution at 300 K. The increasing temperature softens the phonons, thus reducing the group velocity of materials and increasing the scattering phase space. However, it simultaneously reduces the anharmonicity, which is dominant in BaZrS$_3$ and ultimately improves the particle-like thermal transport. Further, by replacing S atom with Se and Ti-alloying strategy, $ZT$ value of BaZrS$_3$ is significantly increased from 0.58 to 0.91 at 500 K, making it an important candidate for thermoelectric applications.

cond-mat.mtrl-sci↗

arXiv2023

Variational quantum circuit learning of entanglement purification in multiple degrees of freedom

Entanglement purification is a crucial technique for promising the effective entanglement channel in noisy large-scale quantum networks, yet complicated in designing protocols in multi-degree of freedom (DoF). To execute the above tasks easily and effectively, developing a learning framework for designing the entanglement purification with multi-DoF is a promising way and still an open research question. Inspired by variational quantum circuit (VQC) with remarkable advantage in learning optimal quantum operations with near-term quantum devices, in this paper we propose an effective VQC framework for the entanglement purification in multi-DoF and exploit it to learn the optimal purification protocols of the objective function which are based on postselection. By properly introducing additional circuit lines for representing each of the ancillary DoFs of all the particles, e.g., space and time, the parametrized quantum circuit can effectively simulate scalable entanglement purification. To verify our framework, the well-known protocols in linear optics are learned well with alternative operations in low-depth quantum circuit. Moreover, we simulate the multipair cases with multi-DoF to show the scalability and discover one-round protocols. Our work provides an effective way for exploring the entanglement purification protocols in multi-DoF and multipair with near-term quantum devices.

quant-ph↗

arXiv2023

Experimental Results of Underwater Sound Speed Profile Inversion by Few-shot Multi-task Learning

Underwater Sound Speed Profile (SSP) distribution has great influence on the propagation mode of acoustic signal, thus the fast and accurate estimation of SSP is of great importance in building underwater observation systems. The state-of-the-art SSP inversion methods include frameworks of matched field processing (MFP), compressive sensing (CS), and feedforeward neural networks (FNN), among which the FNN shows better real-time performance while maintain the same level of accuracy. However, the training of FNN needs quite a lot historical SSP samples, which is diffcult to be satisfied in many ocean areas. This situation is called few-shot learning. To tackle this issue, we propose a multi-task learning (MTL) model with partial parameter sharing among different traning tasks. By MTL, common features could be extracted, thus accelerating the learning process on given tasks, and reducing the demand for reference samples, so as to enhance the generalization ability in few-shot learning. To verify the feasibility and effectiveness of MTL, a deep-ocean experiment was held in April 2023 at the South China Sea. Results shows that MTL outperforms the state-of-the-art methods in terms of accuracy for SSP inversion, while inherits the real-time advantage of FNN during the inversion stage.

eess.AS↗

arXiv2023

Neural Packing: from Visual Sensing to Reinforcement Learning

We present a novel learning framework to solve the transport-and-packing (TAP) problem in 3D. It constitutes a full solution pipeline from partial observations of input objects via RGBD sensing and recognition to final box placement, via robotic motion planning, to arrive at a compact packing in a target container. The technical core of our method is a neural network for TAP, trained via reinforcement learning (RL), to solve the NP-hard combinatorial optimization problem. Our network simultaneously selects an object to pack and determines the final packing location, based on a judicious encoding of the continuously evolving states of partially observed source objects and available spaces in the target container, using separate encoders both enabled with attention mechanisms. The encoded feature vectors are employed to compute the matching scores and feasibility masks of different pairings of box selection and available space configuration for packing strategy optimization. Extensive experiments, including ablation studies and physical packing execution by a real robot (Universal Robot UR5e), are conducted to evaluate our method in terms of its design choices, scalability, generalizability, and comparisons to baselines, including the most recent RL-based TAP solution. We also contribute the first benchmark for TAP which covers a variety of input settings and difficulty levels.

cs.LG↗

arXiv2023

Non-Hermitian Optical Parametric Systems with Anti-parity-time Symmetry

The continuous advancements in ultrafast lasers, characterized by high pulse energy, great average power, and ultrashort pulse duration, have opened up new frontiers and applications in various fields such as high-energy-density science. In this study, we investigated the implementation of non-Hermitian nonlinear parametric amplification by introducing anti-parity-time (anti-PT) symmetry to three-wave interaction processes. By exploring the parameter space defined by the coupling coefficient, phase mismatch, and absorption, we categorized the behavior of the non-Hermitian optical parametric system into four distinct quadrants, representing unbroken/broken anti-PT symmetry and amplification/attenuation, and amplification-attenuation boundaries and exceptional lines can be observed in such parametric space. Through simulations of the dynamical behavior of the interacting waves, we demonstrated the rich evolutions of the signal and idler waves in systems belonging to the respective quadrants and near exceptional points, revealed by the unique performance of eigenmodes. Our findings provide insights into the evaluation of energy flow direction in optical parametric amplification engineering by the directly linked parameter space, which contribute to a deeper understanding of photonics and laser science, potentially leading to new applications in these fields.

physics.optics↗

arXiv2023

Explaining How a Neural Network Play the Go Game and Let People Learn

The AI model has surpassed human players in the game of Go, and it is widely believed that the AI model has encoded new knowledge about the Go game beyond human players. In this way, explaining the knowledge encoded by the AI model and using it to teach human players represent a promising-yet-challenging issue in explainable AI. To this end, mathematical supports are required to ensure that human players can learn accurate and verifiable knowledge, rather than specious intuitive analysis. Thus, in this paper, we extract interaction primitives between stones encoded by the value network for the Go game, so as to enable people to learn from the value network. Experiments show the effectiveness of our method.

cs.AI↗

arXiv2023

Dynamic Prediction of Full-Ocean Depth SSP by Hierarchical LSTM: An Experimental Result

SSP distribution is an important parameter for underwater positioning, navigation and timing (PNT) because it affects the propagation mode of underwater acoustic signals. To accurate predict future sound speed distribution, we propose a hierarchical long short--term memory (H--LSTM) neural network for future sound speed prediction, which explore the distribution pattern of sound velocity in the time dimension. To verify the feasibility and effectiveness, we conducted both simulations and real experiments. The ocean experiment was held in the South China Sea in April, 2023. Results show that the accuracy of the proposed method outperforms the state--of--the--art methods.

cs.SD↗

arXiv2023

Non-linear magnons and exchange Hamiltonians of delafossite proximate quantum spin liquids

Quantum spin liquids (QSL) are theoretical states of matter with long-range entanglement and exotic quasiparticles. However, they generally elude quantitative theory, rendering their underlying phases mysterious and hampering efforts to identify experimental QSL states. Here we study triangular lattice resonating valence bond QSL candidate materials KYbSe$_2$ and NaYbSe$_2$. We measure the magnon modes in their 1/3 plateau phase, where quantitative theory is tractable, using inelastic neutron scattering and fit them using nonlinear spin wave theory. We also fit the KYbSe$_2$ heat capacity using high temperature series expansion. Both KYbSe$_2$ fits yield the same magnetic Hamiltonian to within uncertainty, confirming previous estimates and showing the Heisenberg $J_2/J_1$ to be an accurate model for these materials. Most importantly, comparing KYbSe$_2$ and NaYbSe$_2$ shows that smaller $A$-site Na$^+$ ion has a larger $J_2/J_1$ ratio. However, hydrostatic pressure applied to KYbSe$_2$ increases the ordering temperature (a result consistent with density functional theory calculations), indicating that pressure decreases $J_2/J_1$. These results show how periodic table and hydrostatic pressure can tune the $A$YbSe$_2$ materials in a controlled way.

cond-mat.str-el↗

arXiv2023

Fast Ray-Tracing-Based Precise Underwater Acoustic Localization without Prior Acknowledgment of Target Depth

Underwater localization is of great importance for marine observation and building positioning, navigation, timing (PNT) systems that could be widely applied in disaster warning, underwater rescues and resources exploration. The uneven distribution of underwater sound velocity poses great challenge for precise underwater positioning. The current soundline correction positioning method mainly aims at scenarios with known target depth. However, for nodes that are non-cooperative nodes or lack of depth information, soundline tracking strategies cannot work well due to nonunique positional solutions. To tackle this issue, we propose an iterative ray tracing 3D underwater localization (IRTUL) method for stratification compensation. To demonstrate the feasibility of fast stratification compensation, we first derive the signal path as a function of glancing angle, and then prove that the signal propagation time and horizontal propagation distance are monotonic functions of the initial grazing angle, so that fast ray tracing can be achieved. Then, we propose an sound velocity profile (SVP) simplification method, which reduces the computational cost of ray tracing. Experimental results show that the IRTUL has the most significant distance correction in the depth direction, and the average accuracy of IRTUL has been improved by about 3 meters compared to localization model with constant sound velocity. Also, the simplified SVP can significantly improve real-time performance with average accuracy loss less than 0.2 m when used for positioning.

eess.SP↗

arXiv2023

Underwater Sound Speed Profile Construction: A Review

Real--time and accurate construction of regional sound speed profiles (SSP) is important for building underwater positioning, navigation, and timing (PNT) systems as it greatly affect the signal propagation modes such as trajectory. In this paper, we summarizes and analyzes the current research status in the field of underwater SSP construction, and the mainstream methods include direct SSP measurement and SSP inversion. In the direct measurement method, we compare the performance of popular international commercial temperature, conductivity, and depth profilers (CTD). While for the inversion methods, the framework and basic principles of matched field processing (MFP), compressive sensing (CS), and deep learning (DL) for constructing SSP are introduced, and their advantages and disadvantages are compared. The traditional direct measurement method has good accuracy performance, but it usually takes a long time. The proposal of SSP inversion method greatly improves the convenience and real--time performance, but the accuracy is not as good as the direct measurement method. Currently, the SSP inversion relies on sonar observation data, making it difficult to apply to areas that couldn't be covered by underwater observation systems, and these methods are unable to predict the distribution of sound velocity at future times. How to comprehensively utilize multi-source data and provide elastic sound velocity distribution estimation services with different accuracy and real-time requirements for underwater users without sonar observation data is the mainstream trend in future research on SSP construction.

eess.SP↗

arXiv2023

Hybrid packet switching assisted by classical frame for entanglement-based quantum networks

One of the first problems of studying the quantum internet is how to realize quantum interconnection between users in a quantum network. To address above problem, by referencing the classical Internet, developing the packet switching of quantum networks is a promising way. In this paper, we propose a new hybrid packet switching for entanglement-based quantum networks assisted by classical frame. Different from the previous packet switching for quantum networks based on single photon, the frame used in our scheme is pure classical rather than the classical-quantum structure, and the transmission of classical and quantum signals over physical channels can be independent, which makes our scheme is also valid for quantum networks with heralded entanglement generation. Using our hybrid packet switching, the process of building entanglement channel between end nodes is analogous to the classical packet-switched networks, which provides an effective way to build large-scale packet-switched entanglement-based quantum internet. To verify the feasibility, we perform end-to-end entanglement distribution using our hybrid packet switching in a quantum network and simulate the fidelities of distributed state with respect to the number of hops.

quant-ph↗

arXiv2023

Tuning Large language model for End-to-end Speech Translation

With the emergence of large language models (LLMs), multimodal models based on LLMs have demonstrated significant potential. Models such as LLaSM, X-LLM, and SpeechGPT exhibit an impressive ability to comprehend and generate human instructions. However, their performance often falters when faced with complex tasks like end-to-end speech translation (E2E-ST), a cross-language and cross-modal translation task. In comparison to single-modal models, multimodal models lag behind in these scenarios. This paper introduces LST, a Large multimodal model designed to excel at the E2E-ST task. LST consists of a speech frontend, an adapter, and a LLM backend. The training of LST consists of two stages: (1) Modality adjustment, where the adapter is tuned to align speech representation with text embedding space, and (2) Downstream task fine-tuning, where both the adapter and LLM model are trained to optimize performance on the E2EST task. Experimental results on the MuST-C speech translation benchmark demonstrate that LST-13B achieves BLEU scores of 30.39/41.55/35.33 on En-De/En-Fr/En-Es language pairs, surpassing previous models and establishing a new state-of-the-art. Additionally, we conduct an in-depth analysis of single-modal model selection and the impact of training strategies, which lays the foundation for future research. We will open up our code and models after review.

cs.CL↗

arXiv2023

Generalized spectral characterization of signed trees

Let $T$ be a tree with an irreducible characteristic polynomial $ϕ(x)$ over $\mathbb{Q}$. Let $Δ(T)$ be the discriminant of $ϕ(x)$. It is proved that if $2^{-\frac n2}\sqrt{Δ(T)}$ (which is always an integer) is odd and square free, then every signed tree with underlying graph $T$ is determined by its generalized spectrum.

math.CO↗

arXiv2023

Advancing Acoustic Howling Suppression through Recursive Training of Neural Networks

In this paper, we introduce a novel training framework designed to comprehensively address the acoustic howling issue by examining its fundamental formation process. This framework integrates a neural network (NN) module into the closed-loop system during training with signals generated recursively on the fly to closely mimic the streaming process of acoustic howling suppression (AHS). The proposed recursive training strategy bridges the gap between training and real-world inference scenarios, marking a departure from previous NN-based methods that typically approach AHS as either noise suppression or acoustic echo cancellation. Within this framework, we explore two methodologies: one exclusively relying on NN and the other combining NN with the traditional Kalman filter. Additionally, we propose strategies, including howling detection and initialization using pre-trained offline models, to bolster trainability and expedite the training process. Experimental results validate that this framework offers a substantial improvement over previous methodologies for acoustic howling suppression.

eess.AS↗