arXiv subjects

Yiran Wang

Publications and source records attributed to Yiran Wang.

At least 91 records · Page 5Linked to original sources

arXiv2024

MetaUrban: An Embodied AI Simulation Platform for Urban Micromobility

Public urban spaces like streetscapes and plazas serve residents and accommodate social life in all its vibrant variations. Recent advances in Robotics and Embodied AI make public urban spaces no longer exclusive to humans. Food delivery bots and electric wheelchairs have started sharing sidewalks with pedestrians, while robot dogs and humanoids have recently emerged in the street. Micromobility enabled by AI for short-distance travel in public urban spaces plays a crucial component in the future transportation system. Ensuring the generalizability and safety of AI models maneuvering mobile machines is essential. In this work, we present MetaUrban, a compositional simulation platform for the AI-driven urban micromobility research. MetaUrban can construct an infinite number of interactive urban scenes from compositional elements, covering a vast array of ground plans, object placements, pedestrians, vulnerable road users, and other mobile agents' appearances and dynamics. We design point navigation and social navigation tasks as the pilot study using MetaUrban for urban micromobility research and establish various baselines of Reinforcement Learning and Imitation Learning. We conduct extensive evaluation across mobile machines, demonstrating that heterogeneous mechanical structures significantly influence the learning and execution of AI policies. We perform a thorough ablation study, showing that the compositional nature of the simulated environments can substantially improve the generalizability and safety of the trained mobile agents. MetaUrban will be made publicly available to provide research opportunities and foster safe and trustworthy embodied AI and micromobility in cities. The code and dataset will be publicly available.

cs.CV↗

arXiv2024

On Eliciting Syntax from Language Models via Hashing

Unsupervised parsing, also known as grammar induction, aims to infer syntactic structure from raw text. Recently, binary representation has exhibited remarkable information-preserving capabilities at both lexicon and syntax levels. In this paper, we explore the possibility of leveraging this capability to deduce parsing trees from raw text, relying solely on the implicitly induced grammars within models. To achieve this, we upgrade the bit-level CKY from zero-order to first-order to encode the lexicon and syntax in a unified binary representation space, switch training from supervised to unsupervised under the contrastive hashing framework, and introduce a novel loss function to impose stronger yet balanced alignment signals. Our model shows competitive performance on various datasets, therefore, we claim that our method is effective and efficient enough to acquire high-quality parsing trees from pre-trained language models at a low cost.

cs.CL↗

arXiv2024

NVDS+: Towards Efficient and Versatile Neural Stabilizer for Video Depth Estimation

Video depth estimation aims to infer temporally consistent depth. One approach is to finetune a single-image model on each video with geometry constraints, which proves inefficient and lacks robustness. An alternative is learning to enforce consistency from data, which requires well-designed models and sufficient video depth data. To address both challenges, we introduce NVDS+ that stabilizes inconsistent depth estimated by various single-image models in a plug-and-play manner. We also elaborate a large-scale Video Depth in the Wild (VDW) dataset, which contains 14,203 videos with over two million frames, making it the largest natural-scene video depth dataset. Additionally, a bidirectional inference strategy is designed to improve consistency by adaptively fusing forward and backward predictions. We instantiate a model family ranging from small to large scales for different applications. The method is evaluated on VDW dataset and three public benchmarks. To further prove the versatility, we extend NVDS+ to video semantic segmentation and several downstream applications like bokeh rendering, novel view synthesis, and 3D reconstruction. Experimental results show that our method achieves significant improvements in consistency, accuracy, and efficiency. Our work serves as a solid baseline and data foundation for learning-based video depth estimation. Code and dataset are available at: https://github.com/RaymondWang987/NVDS

cs.CV↗

arXiv2024

BabelBench: An Omni Benchmark for Code-Driven Analysis of Multimodal and Multistructured Data

Large language models (LLMs) have become increasingly pivotal across various domains, especially in handling complex data types. This includes structured data processing, as exemplified by ChartQA and ChatGPT-Ada, and multimodal unstructured data processing as seen in Visual Question Answering (VQA). These areas have attracted significant attention from both industry and academia. Despite this, there remains a lack of unified evaluation methodologies for these diverse data handling scenarios. In response, we introduce BabelBench, an innovative benchmark framework that evaluates the proficiency of LLMs in managing multimodal multistructured data with code execution. BabelBench incorporates a dataset comprising 247 meticulously curated problems that challenge the models with tasks in perception, commonsense reasoning, logical reasoning, and so on. Besides the basic capabilities of multimodal understanding, structured data processing as well as code generation, these tasks demand advanced capabilities in exploration, planning, reasoning and debugging. Our experimental findings on BabelBench indicate that even cutting-edge models like ChatGPT 4 exhibit substantial room for improvement. The insights derived from our comprehensive analysis offer valuable guidance for future research within the community. The benchmark data can be found at https://github.com/FFD8FFE/babelbench.

cs.AI↗

arXiv2024

Motion Avatar: Generate Human and Animal Avatars with Arbitrary Motion

In recent years, there has been significant interest in creating 3D avatars and motions, driven by their diverse applications in areas like film-making, video games, AR/VR, and human-robot interaction. However, current efforts primarily concentrate on either generating the 3D avatar mesh alone or producing motion sequences, with integrating these two aspects proving to be a persistent challenge. Additionally, while avatar and motion generation predominantly target humans, extending these techniques to animals remains a significant challenge due to inadequate training data and methods. To bridge these gaps, our paper presents three key contributions. Firstly, we proposed a novel agent-based approach named Motion Avatar, which allows for the automatic generation of high-quality customizable human and animal avatars with motions through text queries. The method significantly advanced the progress in dynamic 3D character generation. Secondly, we introduced a LLM planner that coordinates both motion and avatar generation, which transforms a discriminative planning into a customizable Q&A fashion. Lastly, we presented an animal motion dataset named Zoo-300K, comprising approximately 300,000 text-motion pairs across 65 animal categories and its building pipeline ZooGen, which serves as a valuable resource for the community. See project website https://steve-zeyu-zhang.github.io/MotionAvatar/

cs.CV↗

arXiv2024

To be Continuous, or to be Discrete, Those are Bits of Questions

Recently, binary representation has been proposed as a novel representation that lies between continuous and discrete representations. It exhibits considerable information-preserving capability when being used to replace continuous input vectors. In this paper, we investigate the feasibility of further introducing it to the output side, aiming to allow models to output binary labels instead. To preserve the structural information on the output side along with label information, we extend the previous contrastive hashing method as structured contrastive hashing. More specifically, we upgrade CKY from label-level to bit-level, define a new similarity function with span marginal probabilities, and introduce a novel contrastive loss function with a carefully designed instance selection strategy. Our model achieves competitive performance on various structured prediction tasks, and demonstrates that binary representation can be considered a novel representation that further bridges the gap between the continuous nature of deep learning and the discrete intrinsic property of natural languages.

cs.CL↗

arXiv2024

Nuclear mass table in deformed relativistic Hartree-Bogoliubov theory in continuum, II: Even-$Z$ nuclei

The mass table in the deformed relativistic Hartree-Bogoliubov theory in continuum (DRHBc) with the PC-PK1 density functional has been established for even-$Z$ nuclei with $8\le Z\le120$, extended from the previous work for even-even nuclei [Zhang $\it{et.~al.}$ (DRHBc Mass Table Collaboration), At. Data Nucl. Data Tables 144, 101488 (2022)]. The calculated binding energies, two-nucleon and one-neutron separation energies, root-mean-square (rms) radii of neutron, proton, matter, and charge distributions, quadrupole deformations, and neutron and proton Fermi surfaces are tabulated and compared with available experimental data. A total of 4829 even-$Z$ nuclei are predicted to be bound, with an rms deviation of 1.477 MeV from the 1244 mass data. Good agreement with the available experimental odd-even mass differences, $α$ decay energies, and charge radii is also achieved. The description accuracy for nuclear masses and nucleon separation energies as well as the prediction for drip lines is compared with the results obtained from other relativistic and nonrelativistic density functional. The comparison shows that the DRHBc theory with PC-PK1 provides an excellent microscopic description for the masses of even-$Z$ nuclei. The systematics of the nucleon separation energies, odd-even mass differences, pairing energies, two-nucleon gaps, $α$ decay energies, rms radii, quadrupole deformations, potential energy curves, neutron density distributions, and neutron mean-field potentials are discussed.

nucl-th↗

arXiv2024

Iterative Reconstruction Methods for Cosmological X-Ray Tomography

We consider the imaging of cosmic strings by using Cosmic Microwave Background (CMB) data. Mathematically, we study the inversion of an X-ray transform in Lorentzian geometry, called the light ray transform. The inverse problem is highly ill-posed, with additional complexities of being large-scale and dynamic, with unknown parameters that represent multidimensional objects. This presents significant computational challenges for the numerical reconstruction of images that have high spatial and temporal resolution. In this paper, we begin with a microlocal stability analysis for inverting the light ray transform using the Landweber iteration. Next, we discretize the spatiotemporal object and light ray transform and consider iterative computational methods for solving the resulting inverse problem. We provide a numerical investigation and comparison of some advanced iterative methods for regularization including Tikhonov and sparsity-promoting regularizers for various example scalar functions with conormal type singularities.

math.NA↗

arXiv2024

SAMDA: Leveraging SAM on Few-Shot Domain Adaptation for Electronic Microscopy Segmentation

It has been shown that traditional deep learning methods for electronic microscopy segmentation usually suffer from low transferability when samples and annotations are limited, while large-scale vision foundation models are more robust when transferring between different domains but facing sub-optimal improvement under fine-tuning. In this work, we present a new few-shot domain adaptation framework SAMDA, which combines the Segment Anything Model(SAM) with nnUNet in the embedding space to achieve high transferability and accuracy. Specifically, we choose the Unet-based network as the "expert" component to learn segmentation features efficiently and design a SAM-based adaptation module as the "generic" component for domain transfer. By amalgamating the "generic" and "expert" components, we mitigate the modality imbalance in the complex pre-training knowledge inherent to large-scale Vision Foundation models and the challenge of transferability inherent to traditional neural networks. The effectiveness of our model is evaluated on two electron microscopic image datasets with different modalities for mitochondria segmentation, which improves the dice coefficient on the target domain by 6.7%. Also, the SAM-based adaptor performs significantly better with only a single annotated image than the 10-shot domain adaptation on nnUNet. We further verify our model on four MRI datasets from different sources to prove its generalization ability.

eess.IV↗

arXiv2024

Plant-Capture Methods for Estimating Population Size from Uncertain Plant Captures

Plant-capture is a variant of classical capture-recapture methods used to estimate the size of a population. In this method, decoys referred to as "plants" are introduced into the population in order to estimate the capture probability. The method has shown considerable success in estimating population sizes from limited samples in many epidemiological, ecological, and demographic studies. However, previous plant-recapture studies have not systematically accounted for uncertainty in the capture status of each individual plant. In this work, we propose various approaches to formally incorporate uncertainty into the plant-capture model arising from (i) the capture status of plants and (ii) the heterogeneity between multiple survey sites. We present two inference methods and compare their performance in simulation studies. We then apply our methods to estimate the size of the homeless population in several US cities using the large-scale "S-night" study conducted by the US Census Bureau.

stat.ME↗

arXiv2023

An Extreme Learning Machine-Based Method for Computational PDEs in Higher Dimensions

We present two effective methods for solving high-dimensional partial differential equations (PDE) based on randomized neural networks. Motivated by the universal approximation property of this type of networks, both methods extend the extreme learning machine (ELM) approach from low to high dimensions. With the first method the unknown solution field in $d$ dimensions is represented by a randomized feed-forward neural network, in which the hidden-layer parameters are randomly assigned and fixed while the output-layer parameters are trained. The PDE and the boundary/initial conditions, as well as the continuity conditions (for the local variant of the method), are enforced on a set of random interior/boundary collocation points. The resultant linear or nonlinear algebraic system, through its least squares solution, provides the trained values for the network parameters. With the second method the high-dimensional PDE problem is reformulated through a constrained expression based on an Approximate variant of the Theory of Functional Connections (A-TFC), which avoids the exponential growth in the number of terms of TFC as the dimension increases. The free field function in the A-TFC constrained expression is represented by a randomized neural network and is trained by a procedure analogous to the first method. We present ample numerical simulations for a number of high-dimensional linear/nonlinear stationary/dynamic PDEs to demonstrate their performance. These methods can produce accurate solutions to high-dimensional PDEs, in particular with their errors reaching levels not far from the machine accuracy for relatively lower dimensions. Compared with the physics-informed neural network (PINN) method, the current method is both cost-effective and more accurate for high-dimensional PDEs.

math.NA↗

arXiv2023

Block-Level Interference Exploitation Precoding for MU-MISO: An ADMM Approach

We study constructive interference based block-level precoding (CI-BLP) in the downlink of multi-user multiple-input single-output (MU-MISO) systems. Specifically, our aim is to extend the analysis on CI-BLP to the case where the considered number of symbol slots is smaller than that of the users. To this end, we mathematically prove the feasibility of using the pseudo-inverse to obtain the optimal CI-BLP precoding matrix in a closed form. Similar to the case when the number of users is small, we show that a quadratic programming (QP) optimization on simplex can be constructed. We also design a low-complexity algorithm based on the alternating direction method of multipliers (ADMM) framework, which can efficiently solve large-scale QP problems. We further analyze the convergence and complexity of the proposed algorithm. Numerical results validate our analysis and the optimality of the proposed algorithm, and further show that the proposed algorithm offers a flexible performance-complexity tradeoff by limiting the maximum number of iterations, which motivates the use of CI-BLP in practical wireless systems.

cs.IT↗

arXiv2023

A Projection-Based Approach for Distributed Energy Resources Aggregation

Aggregating distributed energy resources (DERs) is of great significance to improve the overall operational efficiency of smart grid. The aggregation model needs to consider various factors such as network constraints, operational constraints, and economic characteristics of the DERs. This paper constructs a multi-slot DER aggregation model that considers the above factors using feasible region projection approach, which achieved the protection of DERs data information and the elimination of internal variables. A system economic dispatch (ED) model is established for the operators to make full use of the DER clusters. We calculate the feasible regions with temporal coupling by extending the Progressive Vertex Enumeration (PVE) algorithm to high dimension by the Quickhull algorithm. Finally, an IEEE 39-bus distribution network is simulated with DERs to verify the effectiveness of the proposed model. Results show that the two-step ED derives the same results as the centralized ED.

eess.SY↗

arXiv2023

A clever neural network in solving inverse problems of Schrödinger equation

In this work, we solve inverse problems of nonlinear Schrödinger equations that can be formulated as a learning process of a special convolutional neural network. Instead of attempting to approximate functions in the inverse problems, we embed a library as a low dimensional manifold in the network such that unknowns can be reduced to some scalars. The nonlinear Schrödinger equation (NLSE) is $i\frac{\partial ψ}{\partial t}-β\frac{\partial^2 ψ}{\partial x^2}+γ|ψ|^2ψ+V(x)ψ=0,$ where the wave function $ψ(x,t)$ is the solution to the forward problem and the potential $V(x)$ is the quantity of interest of the inverse problem. The main contributions of this work come from two aspects. First, we construct a special neural network directly from the Schrödinger equation, which is motivated by a splitting method. The physics behind the construction enhances explainability of the neural network. The other part is using a library-search algorithm to project the solution space of the inverse problem to a lower-dimensional space. The way to seek the solution in a reduced approximation space can be traced back to the compressed sensing theory. The motivation of this part is to alleviate the training burden in estimating functions. Instead, with a well-chosen library, one can greatly simplify the training process. A brief analysis is given, which focuses on well-possedness of some mentioned inverse problems and convergence of the neural network approximation. To show the effectiveness of the proposed method, we explore in some representative problems including simple equations and a couple equation. The results can well verify the theory part. In the future, we can further explore manifold learning to enhance the approximation effect of the library-search algorithm.

math.NA↗

arXiv2023

Diffusion-Augmented Depth Prediction with Sparse Annotations

Depth estimation aims to predict dense depth maps. In autonomous driving scenes, sparsity of annotations makes the task challenging. Supervised models produce concave objects due to insufficient structural information. They overfit to valid pixels and fail to restore spatial structures. Self-supervised methods are proposed for the problem. Their robustness is limited by pose estimation, leading to erroneous results in natural scenes. In this paper, we propose a supervised framework termed Diffusion-Augmented Depth Prediction (DADP). We leverage the structural characteristics of diffusion model to enforce depth structures of depth models in a plug-and-play manner. An object-guided integrality loss is also proposed to further enhance regional structure integrality by fetching objective information. We evaluate DADP on three driving benchmarks and achieve significant improvements in depth structures and robustness. Our work provides a new perspective on depth estimation with sparse annotations in autonomous driving scenes.

cs.CV↗

arXiv2023

Low-Switching Policy Gradient with Exploration via Online Sensitivity Sampling

Policy optimization methods are powerful algorithms in Reinforcement Learning (RL) for their flexibility to deal with policy parameterization and ability to handle model misspecification. However, these methods usually suffer from slow convergence rates and poor sample complexity. Hence it is important to design provably sample efficient algorithms for policy optimization. Yet, recent advances for this problems have only been successful in tabular and linear setting, whose benign structures cannot be generalized to non-linearly parameterized policies. In this paper, we address this problem by leveraging recent advances in value-based algorithms, including bounded eluder-dimension and online sensitivity sampling, to design a low-switching sample-efficient policy optimization algorithm, LPO, with general non-linear function approximation. We show that, our algorithm obtains an $\varepsilon$-optimal policy with only $\widetilde{O}(\frac{\text{poly}(d)}{\varepsilon^3})$ samples, where $\varepsilon$ is the suboptimality gap and $d$ is a complexity measure of the function class approximating the policy. This drastically improves previously best-known sample bound for policy optimization algorithms, $\widetilde{O}(\frac{\text{poly}(d)}{\varepsilon^8})$. Moreover, we empirically test our theory with deep neural nets to show the benefits of the theoretical inspiration.

cs.LG↗

arXiv2023

Inverse source problem for the Boltzmann equation in cosmology

We study the inverse problem of recovering primordial perturbations from anisotropies of Cosmic Microwave Background (CMB) using the kinetic model. Mathematically, the problem in concern is the inverse source problem for the linear Boltzmann equation with measurements on some Cauchy surface. We obtain two stable determination results for generic absorption coefficients and scattering kernels.

math.AP↗

arXiv2023

Heteroanionic Stabilization of Ni$^{1+}$ with Nonplanar Coordination in Layered Nickelates

We present electronic structure calculations on layered nickelate oxyfluorides derived from the Ruddlesden-Popper arisotype structure in search of unidentified materials that may host nickelate superconductivity. By performing anion exchange of oxygen with fluorine, we create two heteroanionic La$_2$NiO$_3$F polymorphs and stabilize Ni$^{1+}$ in 4-coordinate and 5-coordinate square planar and square pyramidal geometries, respectively. We further predict chemical reactions with high thermodynamic driving forces to guide their synthesis. These oxyfluorides are weakly correlated antiferromagnetic insulators and their nonmagnetic phases exhibit quasi-2D Fermi surfaces dominated by Ni $d_{x^2-y^2}$ states, which strikingly resemble undoped cuprate superconductors. We discuss how the oxyfluoride anion chemistry promotes Ni-O covalency and single-band character that is more similar to the cuprates than homoanionic infinite-layer nickelates. We use our understanding to propose doping strategies and layered LaSrNiO$_2$F$_2$ and La$_3$Ni$_2$O$_4$F$_3$ nickelate oxyfluorides with tunable electronic and magnetic structures for experimentation.

cond-mat.mtrl-sci↗