Zecheng Zhang
YOU?
Author Swipe
View article: PyG 2.0: Scalable Learning on Real World Graphs
PyG 2.0: Scalable Learning on Real World Graphs Open
PyG (PyTorch Geometric) has evolved significantly since its initial release, establishing itself as a leading framework for Graph Neural Networks. In this paper, we present Pyg 2.0 (and its subsequent minor versions), a comprehensive updat…
View article: Analysis of allohexaploid wheatgrass genome reveals its Y haplome origin in Triticeae and high-altitude adaptation
Analysis of allohexaploid wheatgrass genome reveals its Y haplome origin in Triticeae and high-altitude adaptation Open
Phylogenetic origin of the Y haplome present in allopolyploid Triticeae species remains unknown. Here, we report the 10.47 Gb chromosome-scale genome of allohexaploid Elymus nutans (StStYYHH). Phylogenomic analyses reveal that the Y haplom…
View article: CCS: Controllable and Constrained Sampling with Diffusion Models via Initial Noise Perturbation
CCS: Controllable and Constrained Sampling with Diffusion Models via Initial Noise Perturbation Open
Diffusion models have emerged as powerful tools for generative tasks, producing high-quality outputs across diverse domains. However, how the generated data responds to the initial noise perturbation in diffusion models remains under-explo…
View article: CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents
CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents Open
View article: ContextGNN: Beyond Two-Tower Recommendation Systems
ContextGNN: Beyond Two-Tower Recommendation Systems Open
Recommendation systems predominantly utilize two-tower architectures, which evaluate user-item rankings through the inner product of their respective embeddings. However, one key limitation of two-tower models is that they learn a pair-agn…
View article: Exploring Evolutionary Pathways and Abiotic Stress Responses through Genome-Wide Identification and Analysis of the Alternative Oxidase (AOX) Gene Family in Common Oat (Avena sativa)
Exploring Evolutionary Pathways and Abiotic Stress Responses through Genome-Wide Identification and Analysis of the Alternative Oxidase (AOX) Gene Family in Common Oat (Avena sativa) Open
The alternative oxidase (AOX), a common terminal oxidase in the electron transfer chain (ETC) of plants, plays a crucial role in stress resilience and plant growth and development. Oat (Avena sativa), an important crop with high nutritiona…
View article: LeMON: Learning to Learn Multi-Operator Networks
LeMON: Learning to Learn Multi-Operator Networks Open
Single-operator learning involves training a deep neural network to learn a specific operator, whereas recent work in multi-operator learning uses an operator embedding structure to train a single neural network on data from multiple opera…
View article: Enhancing Visual Question Answering through Ranking-Based Hybrid Training and Multimodal Fusion
Enhancing Visual Question Answering through Ranking-Based Hybrid Training and Multimodal Fusion Open
Visual Question Answering (VQA) is a challenging task that requires systems to provide accurate answers to questions based on image content. Current VQA models struggle with complex questions due to limitations in capturing and integrating…
View article: Optimization of automated garbage recognition model based on ResNet-50 and weakly supervised CNN for sustainable urban development
Optimization of automated garbage recognition model based on ResNet-50 and weakly supervised CNN for sustainable urban development Open
In the context of sustainable urban development, effective garbage management plays a crucial role. However, traditional methods encounter limitations in terms of data quality and quantity. The research on automatic garbage image recogniti…
View article: RelBench: A Benchmark for Deep Learning on Relational Databases
RelBench: A Benchmark for Deep Learning on Relational Databases Open
We present RelBench, a public benchmark for solving predictive tasks over relational databases with graph neural networks. RelBench provides databases and tasks spanning diverse domains and scales, and is intended to be a foundational infr…
View article: CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents
CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents Open
The development of autonomous agents increasingly relies on Multimodal Language Models (MLMs) to perform tasks described in natural language with GUI environments, such as websites, desktop computers, or mobile phones. Existing benchmarks …
View article: Image anomaly detection and prediction scheme based on SSA optimized ResNet50-BiGRU model
Image anomaly detection and prediction scheme based on SSA optimized ResNet50-BiGRU model Open
Image anomaly detection is a popular research direction, with many methods emerging in recent years due to rapid advancements in computing. The use of artificial intelligence for image anomaly detection has been widely studied. By analyzin…
View article: D2NO: Efficient handling of heterogeneous input function spaces with distributed deep neural operators
D2NO: Efficient handling of heterogeneous input function spaces with distributed deep neural operators Open
View article: Out of randomness: How evolution benefits from modularity
Out of randomness: How evolution benefits from modularity Open
Brute force random search, effective in exploring solution spaces, often becomes inefficient or infeasible in real-world scenarios with vast solution spaces. A more effective method, akin to natural evolution, involves recombining existing…
View article: Evolutionary tinkering enriches the hierarchical and nested structures in amino acid sequences
Evolutionary tinkering enriches the hierarchical and nested structures in amino acid sequences Open
Genetic information often exhibits hierarchical and nested relationships, achieved through the reuse of repetitive subsequences such as duplicons and transposable elements, a concept termed “evolutionary tinkering” by François Jacob. Curre…
View article: Theoretical Analysis of Meta Reinforcement Learning: Generalization Bounds and Convergence Guarantees
Theoretical Analysis of Meta Reinforcement Learning: Generalization Bounds and Convergence Guarantees Open
This research delves deeply into Meta Reinforcement Learning (Meta RL) through a exploration focusing on defining generalization limits and ensuring convergence. By employing a approach this article introduces an innovative theoretical fra…
View article: Automatic News Generation and Fact-Checking System Based on Language Processing
Automatic News Generation and Fact-Checking System Based on Language Processing Open
This paper explores an automatic news generation and fact-checking system based on language processing, aimed at enhancing the efficiency and quality of news production while ensuring the authenticity and reliability of the news content. W…
View article: MODNO: Multi Operator Learning With Distributed Neural Operators
MODNO: Multi Operator Learning With Distributed Neural Operators Open
The study of operator learning involves the utilization of neural networks to approximate operators. Traditionally, the focus has been on single-operator learning (SOL). However, recent advances have rapidly expanded this to include the ap…
View article: PyTorch Frame: A Modular Framework for Multi-Modal Tabular Learning
PyTorch Frame: A Modular Framework for Multi-Modal Tabular Learning Open
We present PyTorch Frame, a PyTorch-based framework for deep learning over multi-modal tabular data. PyTorch Frame makes tabular deep learning easy by providing a PyTorch-based data structure to handle complex tabular data, introducing a m…
View article: Conformalized-DeepONet: A Distribution-Free Framework for Uncertainty Quantification in Deep Operator Networks
Conformalized-DeepONet: A Distribution-Free Framework for Uncertainty Quantification in Deep Operator Networks Open
In this paper, we adopt conformal prediction, a distribution-free uncertainty quantification (UQ) framework, to obtain confidence prediction intervals with coverage guarantees for Deep Operator Network (DeepONet) regression. Initially, we …
View article: Restoring the discontinuous heat equation source using sparse boundary data and dynamic sensors
Restoring the discontinuous heat equation source using sparse boundary data and dynamic sensors Open
This study focuses on addressing the inverse source problem associated with the parabolic equation. We rely on sparse boundary flux data as our measurements, which are acquired from a restricted section of the boundary. While it has been e…
View article: Evolutionary Tinkering Enriches the Hierarchical and Nested Structures in Amino Acid Sequences
Evolutionary Tinkering Enriches the Hierarchical and Nested Structures in Amino Acid Sequences Open
Genetic information often exhibits hierarchical and nested relationships, achieved through the reuse of repetitive subsequences such as duplicons and transposable elements, a concept termed ``evolutionary tinkering'' by Fran\c{c}ois Jacob.…
View article: Theoretical perspective on synthetic man‐made life: Learning from the origin of life
Theoretical perspective on synthetic man‐made life: Learning from the origin of life Open
Creating a man‐made life in the laboratory is one of life science’s most intriguing yet challenging problems. Advances in synthetic biology and related theories, particularly those related to the origin of life, have laid the groundwork fo…
View article: Evolutionary Tinkering Enriches the Hierarchical and Interlaced Structures in Amino Acid Sequences
Evolutionary Tinkering Enriches the Hierarchical and Interlaced Structures in Amino Acid Sequences Open
Background : In bioinformatics, tools like multiple sequence alignment and entropy methods probe sequence information and evolutionary relationships between species. Although powerful, they might miss crucial hierarchical relationships for…
View article: Restoring the Discontinuous Heat Equation Source Using Sparse Boundary Data and Dynamic Sensors
Restoring the Discontinuous Heat Equation Source Using Sparse Boundary Data and Dynamic Sensors Open
This study focuses on addressing the inverse source problem associated with the parabolic equation. We rely on sparse boundary flux data as our measurements, which are acquired from a restricted section of the boundary. While it has been e…
View article: Bayesian deep operator learning for homogenized to fine-scale maps for multiscale PDE
Bayesian deep operator learning for homogenized to fine-scale maps for multiscale PDE Open
We present a new framework for computing fine-scale solutions of multiscale Partial Differential Equations (PDEs) using operator learning tools. Obtaining fine-scale solutions of multiscale PDEs can be challenging, but there are many inexp…
View article: A discretization-invariant extension and analysis of some deep operator networks
A discretization-invariant extension and analysis of some deep operator networks Open
We present a generalized version of the discretization-invariant neural operator and prove that the network is a universal approximation in the operator sense. Moreover, by incorporating additional terms in the architecture, we establish a…
View article: Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency
Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency Open
Diffusion models have recently emerged as powerful generative priors for solving inverse problems. However, training diffusion models in the pixel space are both data-intensive and computationally demanding, which restricts their applicabi…
View article: Learning the dynamical response of nonlinear non-autonomous dynamical systems with deep operator neural networks
Learning the dynamical response of nonlinear non-autonomous dynamical systems with deep operator neural networks Open
View article: Fast Replica Exchange Stochastic Gradient Langevin Dynamics
Fast Replica Exchange Stochastic Gradient Langevin Dynamics Open
Application of the replica exchange (i.e., parallel tempering) technique to Langevin Monte Carlo algorithms, especially stochastic gradient Langevin dynamics (SGLD), has scored great success in non-convex learning problems, but one potenti…