4 citations · 11 across the 22 of their papers we have counts for
26 papers
RhinoNet: Unsupervised Learning for Phenoscaping and Generation of High Dimensional Point Clouds
Siddharth Viswanath, Hiren Madhu, Eddie Cavallin +7
We present RhinoNet, a simplicial complex-based point cloud neural network, that creates a geometry-preserving embedding of high-dimensional point clouds. RhinoNet takes collection…
BrainDyn: A Sheaf Neural ODE for Forecasting and Generating Brain Dynamics
Siddharth Viswanath, Panayiotis Ketonis, Chen Liu +11
Brain activity unfolds as coordinated patterns across regions over time, and modeling these dynamics is a central goal in computational neuroscience. Because activity is distribute…
MIOFlow 2.0: A unified framework for inferring cellular stochastic dynamics from single cell and spatial transcriptomics data
Xingzhi Sun, João Felipe Rocha, Brett Phelan +11
Understanding cellular trajectories via time-resolved single-cell transcriptomics is vital for studying development, regeneration, and disease. A key challenge is inferring continu…
HypRAG: Hyperbolic Dense Retrieval for Retrieval Augmented Generation
Hiren Madhu, Ngoc Bui, Ali Maatouk +6
Embedding geometry plays a fundamental role in retrieval quality, yet dense retrievers for retrieval-augmented generation (RAG) remain largely confined to Euclidean space. However,…
Dispersion Loss Counteracts Embedding Condensation and Improves Generalization in Small Language Models
Chen Liu, Xingzhi Sun, Xi Xiao +8
Large language models (LLMs) achieve remarkable performance through ever-increasing parameter counts, but scaling incurs steep computational costs. To better understand LLM scaling…
Self-Supervised Visual Prompting for Cross-Domain Road Damage Detection
Xi Xiao, Zhuxuanzi Wang, Mingqiao Mo +6
The deployment of automated pavement defect detection is often hindered by poor cross-domain generalization. Supervised detectors achieve strong in-domain accuracy but require cost…
CTR-LoRA: Curvature-Aware and Trust-Region Guided Low-Rank Adaptation for Large Language Models
Zhuxuanzi Wang, Mingqiao Mo, Xi Xiao +6
Parameter-efficient fine-tuning (PEFT) has become the standard approach for adapting large language models under limited compute and memory budgets. Although previous methods impro…
RNAGenScape: Property-Guided, Optimized Generation of mRNA Sequences with Manifold Langevin Dynamics
Danqi Liao, Chen Liu, Xingzhi Sun +8
Generating property-optimized mRNA sequences is central to applications such as vaccine design and protein replacement therapy, but remains challenging due to limited data, complex…
VDW-GNNs: Vector diffusion wavelets for geometric graph neural networks
David R. Johnson, Alexander Sietsema, Rishabh Anand +3
We introduce vector diffusion wavelets (VDWs), a novel family of wavelets inspired by the vector diffusion maps algorithm that was introduced to analyze data lying in the tangent b…
A Graph Laplacian Eigenvector-based Pre-training Method for Graph Neural Networks
Howard Dai, Nyambura Njenga, Hiren Madhu +4
The development of self-supervised graph pre-training methods is a crucial ingredient in recent efforts to design robust graph foundation models (GFMs). Structure-based pre-trainin…
AI Scientists for Building Virtual-Cell Models
Xiangru Tang, Zhuoyun Yu, Jiapeng Chen +12
Autonomous agents, from virtual laboratories to biological data-analysis agents and co-scientists, have begun to turn scientific goals into hypotheses. Whether they can go further…
STAGED: A Multi-Agent Neural Network for Learning Cellular Interaction Dynamics
Joao F. Rocha, Ke Xu, Xingzhi Sun +6
The advent of single-cell technology has significantly improved our understanding of cellular states and subpopulations in various tissues under normal and diseased conditions by e…
SlepNet: Spectral Subgraph Representation Learning for Neural Dynamics
Siddharth Viswanath, Rahul Singh, Yanlei Zhang +3
Graph neural networks have been useful in machine learning on graph-structured data, particularly for node classification and some types of graph classification tasks. However, the…
HEIST: A Graph Foundation Model for Spatial Transcriptomics and Proteomics Data
Hiren Madhu, João Felipe Rocha, Tinglin Huang +3
Single-cell transcriptomics and proteomics have become a great source for data-driven insights into biology, enabling the use of advanced deep learning methods to understand cellul…
HELM: Hyperbolic Large Language Models via Mixture-of-Curvature Experts
Neil He, Rishabh Anand, Hiren Madhu +5
Large language models (LLMs) have shown great success in text modeling tasks across domains. However, natural language exhibits inherent semantic hierarchies and nuanced geometric…
InfoGain Wavelets: Furthering the Design of Graph Diffusion Wavelets
David R. Johnson, Smita Krishnaswamy, Michael Perlmutter
Diffusion wavelets extract information from graph signals at different scales of resolution by utilizing graph diffusion operators raised to various powers, known as diffusion scal…
Principal Curvatures Estimation with Applications to Single Cell Data
Yanlei Zhang, Lydia Mezrag, Xingzhi Sun +6
The rapidly growing field of single-cell transcriptomic sequencing (scRNAseq) presents challenges for data analysis due to its massive datasets. A common method in manifold learnin…
HiPoNet: A Multi-View Simplicial Complex Network for High Dimensional Point-Cloud and Single-Cell Data
Siddharth Viswanath, Hiren Madhu, Dhananjay Bhaskar +7
In this paper, we propose HiPoNet, an end-to-end differentiable neural network for regression, classification, and representation learning on high-dimensional point clouds. Our wor…
Exploring the Manifold of Neural Networks Using Diffusion Geometry
Elliott Abel, Andrew J. Steindl, Selma Mazioud +12
Drawing motivation from the manifold hypothesis, which posits that most high-dimensional data lies on or near low-dimensional manifolds, we apply manifold learning to the space of…
ProtScape: A molecular structure and energy-aware representation for protein conformation generation
Siddharth Viswanath, Dhananjay Bhaskar, Xingzhi Sun +13
Molecular dynamics (MD) simulations are a principled but computationally expensive approach for studying protein conformational variability, making it challenging to generate large…
Convergence of Manifold Filter-Combine Networks
David R. Johnson, Joyce Chew, Siddharth Viswanath +4
In order to better understand manifold neural networks (MNNs), we introduce Manifold Filter-Combine Networks (MFCNs). The filter-combine framework parallels the popular aggregate-c…
Geometry-Aware Generative Autoencoders for Warped Riemannian Metric Learning and Generative Modeling on Data Manifolds
Xingzhi Sun, Danqi Liao, Kincaid MacDonald +7
Rapid growth of high-dimensional datasets in fields such as single-cell RNA sequencing and spatial genomics has led to unprecedented opportunities for scientific discovery, but it…
DiffKillR: Killing and Recreating Diffeomorphisms for Cell Annotation in Dense Microscopy Images
Chen Liu, Danqi Liao, Alejandro Parada-Mayorga +3
The proliferation of digital microscopy images, driven by advances in automated whole slide scanning, presents significant opportunities for biomedical research and clinical diagno…
Hyperedge Representations with Hypergraph Wavelets: Applications to Spatial Transcriptomics
Xingzhi Sun, Charles Xu, João F. Rocha +6
In many data-driven applications, higher-order relationships among multiple objects are essential in capturing complex interactions. Hypergraphs, which generalize graphs by allowin…