Abstract: Computational pathology has revolutionized cancer diagnosis and research through the analysis of digitized whole slide images (WSIs). However, the giga-pixel size of these images presents profound technical challenges, creating two intertwined bottlenecks: computational inefficiency and label inefficiency. The immense data scale makes standard end-to-end (E2E) training of deep neural networks infeasible due to prohibitive GPU memory requirements, while the reliance on expert pathologists for annotations makes obtaining high-quality labeled data a tedious and expensive process. This proposal confronts these dual challenges by developing a series of novel model architectures, training paradigms, and self-supervised learning methods designed to create a more efficient and effective framework for WSI analysis.
To improve computational efficiency, this proposal first introduces a locally supervised learning paradigm that enables E2E training on entire WSIs by partitioning a network into gradient-isolated modules, circumventing the memory bottleneck of backpropagation. Second, it presents Prompt-MIL, a parameter-efficient fine-tuning framework that reduces the number of trainable parameters, memory consumption, and training time by fine-tuning only few prompts to guide large pre-trained models. Third, this work advances the efficient architecture on WSIs by developing novel State-Space Models (SSMs). It proposes 2DMamba, the first intrinsic Mamba architecture that preserves the crucial 2D spatial structure of images, overcoming the spatial discrepancy inherent in 1D models. Fourth, to address the inefficiency of multi-directional scans in Mamba models, including 2DMamba, it presents Locally Bi-directional Mamba (LBMamba), which introduces a novel, hardware-aware local backward scan that integrates bi-directional scan into a single forward pass, significantly improving throughput performance trade-off. Lastly, it proposes an extension to the LBMamba, warp-level Bi-directional Mamba (WLBMamba) that extends the thread-level bidirectional scan to warp-level bidirectional scan that further improves the throughput performance trade-off.
To improve label efficiency, this proposal proposes a Precise Location-based Matching strategy for self-supervised dense contrastive learning. By allowing a local patch in one augmented view to match multiple overlapping patches in another, creates a more accurate correspondence, leading to superior feature representations for dense prediction tasks like segmentation and detection.
In summary, this proposal presents a holistic investigation into the efficiency bottlenecks in computational pathology. Through these combined contributions in model architecture, training paradigms, and self-supervised learning, this work establishes a more scalable, efficient, and powerful computational framework for analyzing giga-pixel pathology images.
Speaker: Jingwei Zhang
Location: Old Computer Science Room 2114
Zoom: https://stonybrook.zoom.
Meeting ID: 951 8790 3649 | Passcode: 488916
Abstract: Recent advances in Spatial Transcriptomics (ST) pair histology images with spatially resolved gene expression profiles, enabling predictions of gene expression across different tissue locations based on image patches. This opens up new possibilities for enhancing whole slide image (WSI) prediction tasks with localized gene expression. However, existing methods do not fully leverage the interactions between different tissue locations, which are crucial for accurate joint prediction. To address this, we introduce MERGE (Multi-faceted hiErarchical gRaph for Gene Expressions), which combines a multi-faceted hierarchical graph construction strategy with graph neural networks (GNN) to improve gene expression predictions from WSIs. By clustering tissue image patches based on both spatial and morphological features, and incorporating intra- and inter-cluster edges, our approach fosters interactions between distant tissue locations during GNN learning. As an additional contribution, we evaluate different data smoothing techniques that are necessary to mitigate artifacts in ST data, often caused by technical imperfections. We advocate for adopting gene-aware smoothing methods that are more biologically justified. Experimental results on gene expression prediction show that our GNN method outperforms state-of-the-art techniques on multiple metrics such as mean squared error (MSE), mean absolute error (MAE), and pearson correlation coefficient (PCC). Qualitative analysis establishes the effectiveness of MERGE in capturing cancer marker genes, thus consolidating its utility in diagnostics. As an extension of this work, we use MERGE in a setting with an uncertainty calibration branch to perform robust gene expression smoothing. We show that using patch-wise uncertainty from an uncertainty calibration model and the gene expression predictions from MERGE to enrich the ground truth gene expression matrix, results in better alignment with pathologist annotations, thus establishing that the smoothing is biologically informed.
Speaker: Aniruddha Ganguly
Location: Virtual Zoom Meeting
https://stonybrook.zoom.us/j/
Meeting ID: 547 484 7973
Passcode: 206739
Speaker: Aniruddha Ganguly
Location: Virtual Zoom Meeting
https://stonybrook.zoom.us/j/
Meeting ID: 547 484 7973
Passcode: 206739
University Libraries Present: Qualitative data can be challenging to analyze and interpret effectively. In this workshop, SBU Libraries' Data Literacies Lead, Ahmad Pratama will show you how to extract meaningful insights from textual data, including understanding sentiment trends. Learn to explore qualitative data with Python using word clouds, basic natural language processing (NLP) techniques, and lexicon-based sentiment analysis with VADER.
https://stonybrook.zoom.us/meeting/register/k0r6mPYCRayk2AOGmyd0qw#/registration
https://stonybrook.zoom.us/meeting/register/k0r6mPYCRayk2AOGmyd0qw#/registration
You are cordially invited to attend the biweekly Brookhaven AI Mixer (BAM). BAM includes one short talk on AI research happening at BNL, followed by an open mixer over coffee and snacks for everyone to network and discuss all things AI. The first half hour will consist of presentations that will be available via ZOOM, and the second half hour will be for in person only networking.
Join us every other Tuesday at noon in CDSD's Training Room (building 725, 2nd floor) to learn about interesting AI methods and applications, engage with potential collaborators, prepare for pending FASST funding calls, and build a community of AI for Science at BNL.
Learning Generalizable Program and Architecture Representations for Performance Modeling
Abstract: Performance modeling is an essential tool in many areas of computer science and engineering. However, existing performance modeling approaches have limitations, such as high computational cost, narrow flexibility, or restricted accuracy/generality. To address these limitations, this talk introduces PerfVec, a novel deep learning-based performance modeling framework that learns high-dimensional and independent/orthogonal program and microarchitecture representations. Once learned, a program representation can be used to predict its performance on any microarchitecture, and likewise, a microarchitecture representation can be applied in the performance prediction of any program. Additionally, PerfVec yields a foundation model that captures the performance essence of instructions, which can be directly used by developers in numerous performance modeling-related tasks without incurring its training cost. The evaluation demonstrates that PerfVec is more general and efficient than previous approaches. This talk will also introduce how PerfVec's design principles can benefit broader research areas.
Biography: Lingda Li is a computer scientist at Brookhaven National Laboratory. He is generally interested in computer architecture and programming model research, with focus on simulation/modeling, memory systems, and machine learning. Before joining BNL, he worked at the Department of Computer Science of Rutgers University as a postdoc to carry out GPGPU research. He obtained a PhD in computer architecture from the Microprocessor Research and Development Center at Peking University.
Location: CDS, Bldg. 725, Training Room
Join ZoomGov Meeting: https://bnl.zoomgov.com/j/1605837856?pwd=kYqJs4bVBt4E0cMCWR6GXH3wxzOoiw.1
Meeting ID: 160 583 7856
Passcode: 161580
The Provost's Spotlight Talks feature eminent visitors to the university as well as Stony Brook faculty members who have recently been recognized for outstanding contributions in their field.
Transmedia artist Stephanie Dinkins, Kusama endowed chair in art in the College of Arts and Sciences at Stony Brook University, brings her expertise in AI to the next Spotlight Talk with The Stories We Encode: AI, Love and the Future of Algorithmic Care on Tuesday, October 22, at 3:30 pm in the Charles B. Wang Center Theatre.
Working at the intersection of emerging technologies and social collaboration, Dinkins was named a 2023 TIME 100 Most Influential People in AI. She was recognized for her work with Not the Only One, an ongoing project in which she trained an AI on three generations of Black women to give it cultural roots, a deep history, and a perspective that existing systems do not offer.
The event is free and open to the public, and the discussion will be followed by a reception in the Wang Theatre lobby, hosted by the College of Arts and Sciences for new and promoted faculty.
About the Talk
AI's impact on society necessitates addressing longstanding human rights issues and prejudices. To ensure AI benefits humanity, we must confront institutional biases, rethink our relationship with other beings and emerging technologies, and reconcile ideals with actual power structures. This involves recognizing systemic inequalities, redefining human identity, and equitably distributing resources. AI, if developed and used ethically, offers an opportunity to reimagine a more equitable world for all inhabitants.
The International Neuroethics Society (INS) Speaker Series on AI & Consciousness
AI has existed as a tool for a long time, performing simple tasks such as sorting documents, suggesting music, and so on. But with the development of new generations of AI, the perception of its value to society has been increasing, as it can bring potential and promising benefits in many areas of human life. AI is known to have errors or biases that result in strange or even dangerous responses, but what happens when in AI-human interaction, the latter have errors or biases? cultural errors or biases? And what could be the implications for human relationships?
Speaker Bio
Dr. Karen Herrera-Ferrá is an independent and global consultant on ethical, medical, psychological, legal, social, cultural, policy-making, human rights and political issues and concerns on the development and use of neuroscience, neurotechnology and AI. She is a former member of the Board of Directors of the International Neuroethics Society.
Register here
https://umaryland.zoom.us/
Discover how U.S. Census Bureau Tools can help you find free data for your research projects, community, and more. See how to access the latest American Community Survey and 2020 Census data for various geographies including New York City and Long Island at data.census.gov. Learn about Community Resilience Estimates and how to navigate My Community Explorer; an interactive map-based tool which highlights demographic and socioeconomic data that measure inequality. This session will involve live demonstrations and hands-on exercises for participants. Registrants will receive the Zoom link one day prior to the event.
Please Register for SBU Libraries' AI Club: Exploring Census Data here.
Please Register for SBU Libraries' AI Club: Exploring Census Data here.
What comes after today's large language models and deep neural networks? Join the Computing Community Consortium (CCC) for a virtual 30-min community chat led by David Jensen, CCC Council Member and lead author of the new CCC whitepaper, Envisioning Possible Futures for AI Research. Jensen will explore paradigm-shifting AI Research Futures like Neuro-Symbolic, Embodied, Multi-Agent, and Quantum AI, and then open the floor to the audience for an engaging Q&A discussion.
Register here.
Register here.
Abstract: The development of embodied AI has largely focused on scaling data and computational power, often at the cost of energy efficiency. In contrast, biological intelligence achieves remarkable adaptability with minimal resources, inspiring a shift toward neuromorphic AI, an approach that mimics the structure and dynamics of biological neural systems. In this talk, I will explore the promises and challenges of neuromorphic computer vision from three key perspectives: algorithms, robot actions, and data. First, I will discuss algorithmic advances, including continuous visual hull reconstruction, continuous-time human motion field estimation, and unsupervised independent motion segmentation. Next, I will illustrate how neuromorphic vision enables agile robotic actions by leveraging event-based perception for real-time decision-making. Finally, I will address challenges in training data-driven models with event data, highlighting strategies to enhance data availability and efficiency. By integrating these elements, neuromorphic AI paves the way for energy-efficient, high-performance embodied intelligence in dynamic real-world environments.
Speaker Bio: Ziyun (Claude) Wang is a fifth-year Ph.D. student in the General Robotics, Automation, Sensing & Perception (GRASP) Lab at the University of Pennsylvania, advised by Professor Kostas Daniilidis. His research focuses on developing algorithms for neuromorphic computer vision and integrating them with real hardware to enable agile perception in embodied AI systems. Prior to his Ph.D., he worked at the Samsung AI Center New York, where he developed 3D reconstruction techniques for robotic applications and earned three patents. He also contributed to the Apple Vision Pro team, enhancing user comfort for AR glasses. His research work has been recognized at major computer vision, robotics, and machine learning venues including the AAAI Conference on Artificial Intelligence (AAAI), European Conference on Computer Vision (ECCV), International Conference on Learning Representations (ICLR), Conference on Computer Vision and Pattern Recognition (CVPR) workshops, and IEEE Robotics and Automation Letters (R-AL), with an oral presentation at ECCV placing in the top 2.7%. His research aims to drive the development of next-generation bio-inspired AI systems, enabling more efficient, adaptive, and intelligent embodied perception.