Name: Dec 9 - Ann Arbor AI, ML and Computer Vision Meetup
Start: 2025-12-09T22:30:00.000Z
Location: Cahoots

Welcome to the Best of ICCV series, your virtual pass to some of the groundbreaking research, insights, and innovations that defined this year’s conference. Live streaming from the authors to you.

**Date, Time and Location**

Nov 20, 2025
9 AM Pacific
Online. **[Register for the Zoom!](https://voxel51.com/events/best-of-iccv-november-20-2025)**

**SGBD: Sharpness-Aware Mirror Gradient with BLIP-Based Denoising for Robust Multimodal Product Recommendation**

The growing integration of computer vision and machine learning into the retail industry—both online and in physical stores—has driven the adoption of multimodal recommender systems to help users navigate increasingly complex product landscapes. These systems leverage diverse data sources, such as product images, textual descriptions, and user-generated content, to better model user preferences and item characteristics. While the fusion of multimodal data helps address issues like data sparsity and cold-start problems, it also introduces challenges such as information inconsistency, noise, and increased training instability.

In this paper, we analyze these robustness issues through the lens of flat local minima and propose a strategy that incorporates BLIP—a Vision-Language Model with strong denoising capabilities—to mitigate noise in multimodal inputs. Our method, Sharpness-Aware Mirror Gradient with BLIP-Based Denoising (SGBD), is a concise yet effective training strategy that implicitly enhances robustness during optimization. Extensive theoretical and empirical evaluations demonstrate its effectiveness across various multimodal recommendation benchmarks. SGBD offers a scalable solution for improving recommendation performance in real-world retail environments, where noisy, high-dimensional, and fast-evolving product data is the norm, making it a promising paradigm for training robust multi-modal recommender systems in retail industry.

*About the Speaker*

[Kathy Wu](https://www.linkedin.com/in/kathy-wu-phd-a8155563/) holds a Ph.D. in Applied Mathematics and dual M.S. degrees in Computer Science and Quantitative Finance from the University of Southern California (USC), Los Angeles, CA, USA. At USC, she served as a course lecturer, offering ML Foundations and ML for Business Applications in the science school and business school. Her academic research spans high-dimensional statistics, deep learning, and causal inference, etc.

Kathy brings industry experience from Meta, LinkedIn, and Morgan Stanley in the Bay Area and New York City, US, where she focused on AI methodologies and real-world applications. She is currently an Applied Scientist at Amazon, within the Global Store organization, leading projects in E-Commerce Recommendation Systems, Search Engines, Multi-Modal Vision-Language Models (VLMs), and LLM/GenAI in retails.

Her work has been published in top-tier conferences including ICCV, CVPR, ICLR, SIGIR, WACV, etc. At ICCV 2025, she won the Best Paper Award in Retail Vision.

**Spatial Mental Modeling from Limited Views**

Can VLMs imagine the unobservable space from just a few views, like humans do? Humans form spatial mental models, as internal representations of "unseen space" to reason about layout, perspective, and motion. On our proposed MINDCUBE, we see critical gap systematically on VLMs building robust spatial mental models through representing positions (cognitive mapping), orientations (perspective-taking), and dynamics (mental simulation for ''what-if'' movements). We then explore three approaches to help VLMs approximate spatial mental models, including unseen intermediate views, natural language reasoning chains, and cognitive maps.

The significant improvement comes from ''map-then-reason'' that jointly trains the model to first abstract a cognitive map and then reason upon it. By training models to construct and reason over these internal maps, we boosted accuracy from 37.8% to 60.8% (+23.0%). Adding reinforcement learning pushed performance even further to 70.7% (+32.9%). Our key insight is that such scaffolding of spatial mental models, actively constructing and utilizing internal structured spatial representations with flexible reasoning processes, significantly improves understanding of "unobservable space".

We aim to understand why geometric concepts remain challenging for VLMs and outlining promising research directions towards fostering more robust spatial intelligence.

*About the Speaker*

[Manling Li](https://www.linkedin.com/in/manling-li-ai/) is an Assistant Professor at Northwestern University and Amazon Scholar. She was a postdoc at Stanford University, and obtained the PhD degree in Computer Science at University of Illinois Urbana-Champaign in 2023. She works on the intersection of language, vision, and robotics, recognized by the MIT TR 35 Under 35, ACL Inaugural Dissertation Award Honorable Mention, ACL’24 Outstanding Paper Award, ACL'20 Best Demo Paper Award, and NAACL'21 Best Demo Paper Award, Microsoft Research PhD Fellowship, EE CS Rising Star, etc.

**Forecasting and Visualizing Air Pollution via Sky Images and VLM-Guided Generative Models**

Air pollution monitoring is traditionally limited by costly sensors and sparse data coverage. Our research introduces a vision-language model framework that predicts air quality directly from real-world sky images and also simulates skies under varying pollution levels to enhance interpretability and robustness. We further develop visualization techniques to make predictions more understandable for policymakers and the public. This talk will present our methodology, key findings, and implications for sustainable urban environments.

*About the Speaker*

[Mohammad Saleh Vahdatpour](https://www.linkedin.com/in/msvahdatpour/) is a PhD candidate in Computer Science at Georgia State University specializing in deep learning, vision–language models, and sustainable AI systems. His research bridges generative AI, environmental monitoring, and motion perception, focusing on scalable and energy-efficient models that connect scientific innovation with real-world impact.

**Sari Sandbox: A Virtual Retail Store Environment for Embodied AI Agents**

We present Sari Sandbox, a high-fidelity, photorealistic 3D retail store simulation for benchmarking embodied agents against human performance in shopping tasks. Addressing a gap in retail-specific sim environments for embodied agent training, Sari Sandbox features over 250 interactive grocery items across three store configurations, controlled via an API. It supports both virtual reality (VR) for human interaction and a vision language model (VLM)-powered embodied agent.

We also introduce SariBench, a dataset of annotated human demonstrations across varied task difficulties. Our sandbox enables embodied agents to navigate, inspect, and manipulate retail items, providing baselines against human performance. We conclude with benchmarks, performance analysis, and recommendations for enhancing realism and scalability.

*About the Speakers*

[Emmanuel G. Maminta](https://www.linkedin.com/in/egmaminta) is a fourth-year Artificial Intelligence Ph.D. student at the Ubiquitous Computing Laboratory (UCL) in the University of the Philippines Diliman, advised by Prof. Rowel O. Atienza.

Janika Deborah B.Gajo is an undergraduate student studying for a Bachelor of Science in Computer Engineering at the University of the Philippines, Diliman.

London Computer Vision Meetup

Farzam

Nov 20 - Best of ICCV (Day 2)

Online event

San Francisco Augmented Reality and Computer Vision Meetup

Jimmy Guerrero - Voxel51

TEST

Welcome to the Best of ICCV series, your virtual pass to some of the groundbreaking research, insights, and innovations that defined this year’s conference. Live streaming from the authors to you.

**Date, Time and Location**

Nov 21, 2025
9 AM Pacific
Online. **[Register for the Zoom!](https://voxel51.com/events/best-of-iccv-november-21-2025)**

**GECO: Geometrically Consistent Embedding with Lightspeed Inference**

Recent advances in feature learning have shown that self-supervised vision foundation models can capture semantic correspondences but often lack awareness of underlying 3D geometry. GECO addresses this gap by producing geometrically coherent features that semantically distinguish parts based on geometry (e.g., left/right eyes, front/back legs).
We propose a training framework based on optimal transport, enabling supervision beyond keypoints, even under occlusions and disocclusions. With a lightweight architecture, GECO runs at 30 fps, 98.2% faster than prior methods, while achieving state-of-the-art performance on PFPascal, APK, and CUB, improving PCK by 6.0%, 6.2%, and 4.1%, respectively. Finally, we show that PCK alone is insufficient to capture geometric quality and introduce new metrics and insights for more geometry-aware feature learning

*About the Speaker*

[Regine Hartwig](https://www.linkedin.com/in/regine-hartwig-862469187/) is a PHD Graduate Student at the Technical University of Munich

**Proactive Comorbidity Prediction in HIV: Towards Fair and Trustworthy Care**

HIV is a chronic infection that weakens the immune system and exposes patients to a high burden of comorbidities. While antiretroviral therapy has improved life expectancy, comorbidities remain a major challenge, and traditional screening protocols often fail to capture subtle risk patterns early enough. To address this, we develop a novel method trained on lab tests and demographic data from 2,200 patients in SE London. The method integrates feature interaction modeling, attention mechanisms, residual fusion and label-specific attention heads, outperforming TabNet, MLPs and classical machine learning models.

Our experiments show that incorporating demographic information improves predictive performance, though demographic recoverability analyses reveal that age and gender can still be inferred from lab data alone, raising fairness concerns. Finally, robustness checks confirm stable feature importance across cross-validation folds, reinforcing the trustworthiness of our approach.

*About the Speaker*

[Dimitrios Kollias](https://www.linkedin.com/in/dimitrios-kollias-5b19771b5) is an Associate Professor in Multimodal AI at Queen Mary University of London, specializing in machine/deep learning, trustworthy AI, computer vision, medical imaging & healthcare, behavior analysis, HMI. I have published 80+ papers (h-index 39; 6100+ citations) in top venues (e.g., CVPR, ICCV, ECCV, AAAI, IJCV, ECAI), invented a patent in behavior analysis (Huawei) and my research is widely adopted by academia and industry. I also serve as AI consultant and advisor to global companies, and have played leading roles in major international AI workshops and competitions.

**Toward Trustworthy Embodied Agents: From Individuals to Teams**

Modern intelligent embodied agents, such as service robots and autonomous vehicles, interact frequently with humans in dynamic, uncertain environments. They may also collaborate with each other as a team through effective communication to enhance task success, safety, and efficiency. These brings a few significant challenges. First, building reliable agents that safely navigate multi-agent scenarios requires scalable and generalizable prediction of surrounding agents’ behaviors and robust decision making under environmental uncertainty in out-of-distribution (OOD) scenarios. Second, effective cooperation between agents requires efficient communication and information fusion strategies and reliable task planning for complex long-horizon tasks.

In this talk, I will introduce a series of our recent work that addresses these challenges to enable safe and trustworthy embodied agents and their application to autonomous driving and service robots. Specifically, I will first demonstrate principled uncertainty quantification techniques and how they enable generalizable prediction and planning in out-of-distribution scenarios. Then, I will talk about effective approaches to enable efficient multi-agent communication and cooperation in centralized and decentralized settings.

*About the Speaker*

[Dr. Jiachen Li](https://www.linkedin.com/in/jiachen-li/) is an Assistant Professor in the Department of Electrical and Computer Engineering (ECE) and a cooperating faculty in the Department of Computer Science and Engineering (CSE) at the University of California, Riverside. He is the Director of the Trustworthy Autonomous Systems Laboratory and is affiliated with the Riverside Artificial Intelligence Research Institute (RAISE), the Center for Robotics and Intelligent Systems (CRIS), and the Center for Environmental Research and Technology (CE-CERT).

**DRaM-LHM: A Quaternion Framework for Iterative Camera Pose Estimation**

We explore a quaternion adjugate matrix-based representation for rotational motion in the Perspective-n-Point (PnP) problem. Leveraging quadratic quaternion terms within a Determinant Ratio Matrix (DRaM) estimation framework, we extend its application to perspective scenarios, providing a robust and efficient initialization for iterative PnP pose estimation. Notably, by solving the orthographic projection least-squares problem, DRaM provides a reliable initialization that enhances the accuracy and stability of iterative PnP solvers. Experiments on synthetic and real data demonstrate its efficiency, accuracy, and robustness, particularly under high noise conditions. Furthermore, our nonminimal formulation ensures numerical stability, making it effective for real-world applications.

*About the Speaker*

[Chen Lin](https://www.linkedin.com/in/chen-lin-38062495/) was a Research Fellow at the Simons Foundation, where she specialized in 3D computer vision and visual(-inertial) SLAM. Her research spans from classical multiview geometry to learning-based pose estimation and scene understanding. Her ICCV 2025 paper introduces a new framework for rotation and pose estimation built on advanced algebraic paradigms.

PRIYANKA KAMILA

Victor Escorcia

Matthew P

Nov 21 - Best of ICCV (Day 3)

Join our in-person meetup to hear talks from experts on cutting-edge topics across AI, ML, and computer vision.

**Date, Time and Location**

Dec 9, 2025
5:30 - 8:30 PM

**[Preregister to reserve your spot](https://voxel51.com/events/ann-arbor-ai-ml-and-computer-vision-meetup-december-9-2025)**

[Cahoots Coworking Space](https://cahoots.com/)
206 E Huron St,
Ann Arbor, MI 48104

*Stay tuned! More speakers to be announced shortly.*

**Challenges and Opportunities for AI in Marine Robotics**

Underwater robots are essential tools for ocean exploration. This presentation will explore new technology in robotics and artificial intelligence that can enable automated detection of shipwreck sites from sonar data collected from autonomous underwater vehicles (AUVs). We will also discuss our recent work on underwater mapping and 3D reconstruction towards real-time dense mapping of shipwreck sites from sonar and camera imagery. Results will be demonstrated on data from field trials in Thunder Bay National Marine Sanctuary in Lake Huron.

*About the Speaker*

[Katie Skinner](https://www.linkedin.com/in/katherine-a-skinner-073ab779/) is an Assistant Professor in the Department of Robotics at the University of Michigan. She received an M.S. and Ph.D. from the Robotics Institute at the University of Michigan, and a B.S.E. in Mechanical and Aerospace Engineering with a Certificate in Applications of Computing from Princeton University. She is a recipient of the NSF CAREER Award, ONR Young Investigator Award, and IEEE Robotics and Automation Letters Best Paper Award.

**Building Smarter AV Simulation with Neural Reconstruction and World Models**

This talk explores how neural reconstruction and world models are coming together to create richer, more dynamic simulation for scalable autonomous vehicle development. We’ll look at the latest releases in 3D Gaussian splatting techniques and world reasoning and generation, as well as discuss how these technologies are advancing the deployment of autonomous driving stacks that can generalize to any environment. We’ll also cover NVIDIA open models, frameworks, and data to help kickstart your own development pipelines.

*About the Speaker*

[Katie Washabaugh](https://www.linkedin.com/in/katie-burke-washabaugh-1984994b/) is NVIDIA’s Product Marketing Manager for Autonomous Vehicle Simulation, focusing on virtual solutions for real world mobility. A former journalist at publications such as Automotive News and MarketWatch, she joined the NVIDIA team in 2018 as Automotive Content Marketing Manager. Katie holds a B.A. in public policy from the University of Michigan and lives in Detroit.

**In-Cabin Intelligence: AI's Vision for Predictive Cabin Safety**

Current in-cabin monitoring systems react to distractions and drowsiness after they occur. Cabin AI: Predictive Safety introduces a paradigm shift using multi-modal sensor fusion and deep learning to anticipate dangerous states before they manifest. By analyzing driver gaze, occupant behavior, and physiological signals, these systems predict impairment, distraction, and risky activities with over 95% accuracy, meeting stringent Euro NCAP 2025 requirements. This proactive approach not only prevents accidents but builds passenger trust in autonomous vehicles. Discover how predictive algorithms are transforming cabin sensing from a compliance checkbox into a core safety differentiator.

*About the Speaker*

[Vijayachandar Sanikal,](https://www.linkedin.com/in/vijaysanikal) IEEE Senior Member, is a visionary automotive leader with 20+ years pioneering AI-driven thermal optimization and cloud-based simulation for electric and autonomous vehicles. He builds intelligent mobility solutions at the intersection of digital twins, software-defined vehicles, and sustainable innovation.

**From Raw Sensor Data to Reliable Datasets: Physical AI in Practice**

Modern mobility systems rely on massive, high-quality multimodal datasets — yet real-world data is messy. Misaligned sensors, inconsistent metadata, and uneven scenario coverage can slow development and lead to costly model failures. The Physical AI Workbench, built in collaboration between Voxel51 and NVIDIA, provides an automated and scalable pipeline for auditing, reconstructing, and enriching autonomous driving datasets.

In this talk, we’ll show how FiftyOne serves as the central interface for inspecting and validating sensor alignment, scene structure, and scenario diversity, while NVIDIA Neural Reconstruction (NuRec) enables physics-aware reconstruction directly from real-world captures. We’ll highlight how these capabilities support automated dataset quality checks, reduce manual review overhead, and streamline the creation of richer datasets for model training and evaluation.

Attendees will gain insight into how Physical AI workflows help mobility teams scale, improve dataset reliability, and accelerate iteration from data capture to model deployment — without rewriting their infrastructure.

*About the Speaker*

[Daniel Gural](https://www.linkedin.com/in/daniel-gural/) leads technical partnerships at Voxel51, where he’s building the Physical AI Workbench, a platform that connects real-world sensor data with realistic simulation to help engineers better understand, validate, and improve their perception systems. With a background in developer relations and computer vision engineering,

Ann Arbor AI, Machine Learning and Computer Vision Meetup

Apoorv Mahajan

Suibhne Ó Foighil

Vijay Sanikal

malones169

surratta

Malek Aburaddaha

Dec 9 - Ann Arbor AI, ML and Computer Vision Meetup

Cahoots

Computer Vision Meetups

Sponsor

Gruppi

{PRO_NETWORK_NAME} fa parte di Meetup Pro con più di {PRO_MEMBER_COUNT} iscritti in {PRO_GROUP_COUNT} Meetup in tutto il mondo. Meetup Pro è lo strumento professionale per organizzare e comunicare in un network di utenti, partner, contributori e partecipanti.

This virtual Meetup Network is for data scientists, machine learning engineers, and open source enthusiasts who want to expand their knowledge of computer vision and complementary technologies. Every month we’ll bring you two diverse speakers working at the cutting edge of computer vision.

What’s computer vision? It's how systems can derive meaningful information from digital images, videos and other visual inputs — and how they can take actions or make recommendations based on that information.

Use cases for computer vision include: autonomous vehicles, facial recognition, inventory management, medical imaging and more.

This network is sponsored by Voxel51, maintainers of the open source FiftyOne computer vision toolset. Learn more: https://github.com/voxel51/fiftyone

Jimmy Guerrero

Administration, promotion, giveaways and charitable contributions.

Computer Vision Meetups

Chi siamo

Sponsor

Voxel51

Prossimi eventi

Chi siamo

Sponsor

Voxel51

Gruppi