Mumbai AI, Machine Learning and Computer Vision Meetup

Nov 13, 2025
9 AM Pacific
Online. Register for the Zoom!

Copy, Paste, Customize! The Template Approach to AI Engineering

Most AI implementations fail because teams treat prompt engineering as ad-hoc experimentation rather than systematic software engineering, leading to unreliable systems that don't scale beyond proof-of-concepts. This talk demonstrates engineering practices that enable reliable AI deployment through standardized prompt templates, systematic validation frameworks, and production observability.

Drawing from experience developing fillable prompt templates currently being validated in production environments processing thousands of submissions, I'll share how Infrastructure as Code principles apply to LLM workflows, why evaluation metrics like BLEU scores are critical for production reliability, and how systematic failure analysis prevents costly deployment issues. Attendees will walk away with understanding of practical frameworks for improving AI system reliability and specific strategies for building more consistent, scalable AI implementations.

About the Speaker

Jeanne McClure is a postdoctoral scholar at NC State's Data Science and AI Academy with expertise in systematic AI implementation and validation. Her research transforms experimental AI tools into reliable production systems through standardized prompt templates, rigorous testing frameworks, and systematic failure analysis. She holds a PhD in Learning, Design and Technology with additional graduate work in data science.

Multimodality with Biases: Understand and Evaluate VLMs for Autonomous Driving with FiftyOne

Do your VLMs really see danger? With FiftyOne, I’ll show you how to understand and evaluate vision-language models for autonomous driving — making risk and bias visible in seconds. We’ll compare models on the same scenes, reveal failures and edge cases, and you’ll see a simple dashboard to decide which data to curate and what to adjust. You’ll leave with a clear, practical, and replicable method to raise the bar for safety.

About the Speaker

Paula Ramos has a PhD in Computer Vision and Machine Learning, with more than 20 years of experience in the technological field. She has been developing novel integrated engineering technologies, mainly in Computer Vision, robotics, and Machine Learning applied to agriculture, since the early 2000s in Colombia.

The Heart of Innovation: Women, AI, and the Future of Healthcare

This session explores how Artificial Intelligence is transforming healthcare by enhancing diagnosis, treatment, and patient outcomes. It highlights the importance of diverse and female perspectives in shaping AI solutions that are ethical, empathetic, and human-centered. We will discuss key applications, current challenges, and the future potential of AI in medicine. It’s a forward-looking conversation about how innovation can build a healthier world.

About the Speaker

Karen Sanchez is a Postdoctoral Researcher at the Center of Excellence for Generative AI at King Abdullah University of Science and Technology (KAUST), Saudi Arabia. Her research focuses on AI for Science, spanning computer vision, video understanding, and privacy-preserving machine learning. She is also an active advocate for diversity and outreach in AI, contributing to global initiatives that connect researchers and amplify underrepresented voices in technology.

Language Diffusion Models

Autoregressive models (ARMs) are widely regarded as the cornerstone of large language models (LLMs). Challenge this notion by introducing LLaDA, a diffusion model trained from scratch under the pre-training and supervised fine-tuning (SFT) paradigm. LLaDA models distributions through a forward data masking process and a reverse process, parameterized by a vanilla Transformer to predict masked tokens.

Optimizing a likelihood bound provides a principled generative approach for probabilistic inference. Across extensive benchmarks, LLaDA demonstrates strong scalability, outperforming self-constructed ARM baselines. Remarkably, LLaDA 8B is competitive with strong LLMs like LLaMA3 8B in in-context learning and, after SFT, exhibits impressive instruction-following abilities in case studies such as multi-turn dialogue.

About the Speaker

Jayita Bhattacharyya is an AI/ML Nerd with a blend of technical speaking & hackathon wizardry! Applying tech to solve real-world problems. The work focus these days is on generative AI. Helping software teams incorporate AI into transforming software engineering.

This hands-on workshop introduces you to document visual AI workflows using FiftyOne, the leading open-source toolkit for computer vision datasets.

Date and Location

Nov 14, 2025
9:00-10:30 AM Pacific
Online. Register for the Zoom

In document understanding, a pixel is worth a thousand tokens. While traditional text-extraction pipelines tokenize and process documents sequentially, modern visual AI approaches can understand document structure, layout, and content directly from images—making them more efficient, accurate, and robust to diverse document formats.

In this workshop you'll learn how to:

• Load and organize document datasets in FiftyOne for visual exploration and analysis
• Compute visual embeddings using state-of-the-art document retrieval models to enable semantic search and similarity analysis
• Leverage FiftyOne workflows including similarity search, clustering, and quality assessment to gain insights from your document collections
• Deploy modern vision-language models for OCR and document understanding tasks that go beyond simple text extraction
• Evaluate and compare different OCR models to select the best approach for your specific use case

Whether you're working with invoices, receipts, forms, scientific papers, or mixed document types, this workshop will equip you with practical skills to build robust document AI pipelines that harness the power of visual understanding. Walk away with reproducible notebooks and best practices for tackling real-world document intelligence challenges.

Nov 19, 2025
9 AM Pacific
Online. Register for the Zoom!

AnimalClue: Recognizing Animals by their Traces

Wildlife observation plays an important role in biodiversity conservation, necessitating robust methodologies for monitoring wildlife populations and interspecies interactions. Recent advances in computer vision have significantly contributed to automating fundamental wildlife observation tasks, such as animal detection and species identification. However, accurately identifying species from indirect evidence like footprints and feces remains relatively underexplored, despite its importance in contributing to wildlife monitoring.

To bridge this gap, we introduce AnimalClue, the first large-scale dataset for species identification from images of indirect evidence. Our dataset consists of 159,605 bounding boxes encompassing five categories of indirect clues: footprints, feces, eggs, bones, and feathers. It covers 968 species, 200 families, and 65 orders. Each image is annotated with species-level labels, bounding boxes or segmentation masks, and fine-grained trait information, including activity patterns and habitat preferences. Unlike existing datasets primarily focused on direct visual features (e.g., animal appearances), AnimalClue presents unique challenges for classification, detection, and instance segmentation tasks due to the need for recognizing more detailed and subtle visual features. In our experiments, we extensively evaluate representative vision models and identify key challenges in animal identification from their traces.

About the Speaker

Risa Shinoda received her M.S. and Ph.D. in Agricultural Science from Kyoto University in 2022 and 2025. Since April 2025, she has been serving as a Specially Appointed Assistant Professor at the Graduate School of Information Science and Technology, the University of Osaka. She is engaged in research on the application of image recognition to plants and animals, as well as vision-language models.

LOTS of Fashion! Multi-Conditioning for Image Generation via Sketch-Text Pairing

Fashion design is a complex creative process that blends visual and textual expressions. Designers convey ideas through sketches, which define spatial structure and design elements, and textual descriptions, capturing material, texture, and stylistic details. In this paper, we present LOcalized Text and Sketch for fashion image generation (LOTS), an approach for compositional sketch-text based generation of complete fashion outlooks. LOTS leverages a global description with paired localized sketch + text information for conditioning and introduces a novel step-based merging strategy for diffusion adaptation.

First, a Modularized Pair-Centric representation encodes sketches and text into a shared latent space while preserving independent localized features; then, a Diffusion Pair Guidance phase integrates both local and global conditioning via attention-based guidance within the diffusion model’s multi-step denoising process. To validate our method, we build on Fashionpedia to release Sketchy, the first fashion dataset where multiple text-sketch pairs are provided per image. Quantitative results show LOTS achieves state-of-the-art image generation performance on both global and localized metrics, while qualitative examples and a human evaluation study highlight its unprecedented level of design customization.

About the Speaker

Federico Girella is a third-year Ph.D. student at the University of Verona (Italy), supervised by Prof. Marco Cristani, with expected graduation in May 2026. His research involves joint representations in the Image and Language multi-modal domain, working with deep neural networks such as (Large) Vision and Language Models and Text-to-Image Generative Models. His main body of work focuses on Text-to-Image Retrieval and Generation in the Fashion domain.

ProtoMedX: Explainable Multi-Modal Prototype Learning for Bone Health Assessment

Early detection of osteoporosis and osteopenia is critical, yet most AI models for bone health rely solely on imaging and offer little transparency into their decisions. In this talk, I will present ProtoMedX, the first prototype-based framework that combines lumbar spine DEXA scans with patient clinical records to deliver accurate and inherently explainable predictions.

Unlike black-box deep networks, ProtoMedX classifies patients by comparing them to learned case-based prototypes, mirroring how clinicians reason in practice. Our method not only achieves state-of-the-art accuracy on a real NHS dataset of 4,160 patients but also provides clear, interpretable explanations aligned with the upcoming EU AI Act requirements for high-risk medical AI. Beyond bone health, this work illustrates how prototype learning can make multi-modal AI both powerful and transparent, offering a blueprint for other safety-critical domains.

About the Speaker

Alvaro Lopez is a PhD candidate in Explainable AI at Lancaster University and an AI Research Associate at J.P. Morgan in London. His research focuses on prototype-based learning, multi-modal AI, and AI security. He has led projects on medical AI, fraud detection, and adversarial robustness, with applications ranging from healthcare to financial systems.

CLASP: Adaptive Spectral Clustering for Unsupervised Per-Image Segmentation

We introduce CLASP (Clustering via Adaptive Spectral Processing), a lightweight framework for unsupervised image segmentation that operates without any labeled data or fine-tuning. CLASP first extracts per-patch features using a self-supervised ViT encoder (DINO); then, it builds an affinity matrix and applies spectral clustering. To avoid manual tuning, we select the segment count automatically with a eigengap-silhouette search, and we sharpen the boundaries with a fully connected DenseCRF. Despite its simplicity and training-free nature, CLASP attains competitive mIoU and pixel-accuracy on COCO-Stuff and ADE20K, matching recent unsupervised baselines. The zero-training design makes CLASP a strong, easily reproducible baseline for large unannotated corpora—especially common in digital advertising and marketing workflows such as brand-safety screening, creative asset curation, and social-media content moderation.

About the Speaker

Max Curie is a Research Scientist at Integral Ad Science, building fast, lightweight solutions for brand safety, multi-media classification, and recommendation systems. As a former nuclear physicist at Princeton University, he brings rigorous analytical thinking and modeling discipline from his physics background to advance ad tech.

Nov 20, 2025
9 AM Pacific
Online. Register for the Zoom!

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 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 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 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 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.