Boston AI, Machine Learning and Computer Vision Meetup

This technical workshop focuses on the data infrastructure required to build and maintain production-grade mobility datasets at fleet scale.

Date, Time and Location

Jan 13, 2026
9:00-10:00 AM Pacific
Online. Register for the Zoom!

We will examine how to structure storage, metadata, access patterns, and quality controls so that mobility teams can treat perception datasets as first-class, versioned “infrastructure” assets. The session will walk through how to design a mobility data stack that connects object storage, labeling systems, simulation environments, and experiment tracking into a coherent, auditable pipeline.

What you’ll learn:

• Model the mobility data plane: Define schemas for camera, LiDAR, radar, and HD, and represent temporal windows, ego poses, and scenario groupings in a way that is queryable and stable under schema evolution.
• Build a versioned dataset catalog with FiftyOne: Use FiftyOne customized workspaces and views to represent canonical datasets, and integrate with your raw data sources. All while preserving lineage between raw logs, the curated data, and simulation inputs.
• Implement governance and access control on mobility data: Configure role-based access and auditable pipelines to enforce data residency constraints while encouraging multi-team collaboration across research, perception, and safety functions.
• Operationalize curation and scenario mining workflows: Use FiftyOne’s embeddings and labeling capabilities to surface rare events such as adverse weather and sensor anomalies. Assign review tasks, and codify “critical scenario” definitions as reproducible dataset views.
• Close the loop with evaluation and feedback signals: Connect FiftyOne to training and evaluation pipelines so that model failures feed back into dataset updates

By the end of the workshop, attendees will have a concrete mental model and reference architecture for treating mobility datasets as a governed, queryable, and continuously evolving layer in their stack.

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

Jan 14, 2025
9 AM Pacific
Online. Register for the Zoom!

EgoExOR: An Ego-Exo-Centric Operating Room Dataset for Surgical Activity Understanding

Operating rooms (ORs) demand precise coordination among surgeons, nurses, and equipment in a fast-paced, occlusion-heavy environment, necessitating advanced perception models to enhance safety and efficiency. Existing datasets either provide partial egocentric views or sparse exocentric multi-view context, but do not explore the comprehensive combination of both. We introduce EgoExOR, the first OR dataset and accompanying benchmark to fuse first-person and third-person perspectives. Spanning 94 minutes (84,553 frames at 15 FPS) of two emulated spine procedures, Ultrasound-Guided Needle Insertion and Minimally Invasive Spine Surgery,

EgoExOR integrates egocentric data (RGB, gaze, hand tracking, audio) from wearable glasses, exocentric RGB and depth from RGB-D cameras, and ultrasound imagery. Its detailed scene graph annotations, covering 36 entities and 22 relations (568,235 triplets), enable robust modeling of clinical interactions, supporting tasks like action recognition and human-centric perception. We evaluate the surgical scene graph generation performance of two adapted state-of-the-art models and offer a new baseline that explicitly leverages EgoExOR's multimodal and multi-perspective signals. This new dataset and benchmark set a new foundation for OR perception, offering a rich, multimodal resource for next-generation clinical perception.

About the Speaker

Ege Özsoy is a last year PhD student researching multimodal computer vision and vision–language models for surgical scene understanding, focusing on semantic scene graphs, multimodality, and ego-exocentric modeling in operating rooms.

SANSA: Unleashing the Hidden Semantics in SAM2 for Few-Shot Segmentation

Few-shot segmentation requires recognizing novel object categories from only a few annotated examples, demanding both accurate mask generation and strong visual correspondence. While Segment Anything 2 (SAM2) provides powerful prompt-based segmentation and built-in feature matching, its representations are entangled with tracking-specific cues that limit higher-level semantic generalization. We show that SAM2 nonetheless encodes rich latent semantic structure despite its class-agnostic training. To leverage this, we introduce SANSA, a lightweight framework that makes this structure explicit and adapts SAM2 for few-shot segmentation with minimal modifications. SANSA achieves state-of-the-art generalization performance, outperforms generalist in-context methods, supports flexible prompting, and remains significantly faster and smaller than prior approaches.

About the Speaker

Claudia Cuttano is a PhD student in the VANDAL Lab at Politecnico di Torino and is currently conducting a research visit at TU Darmstadt with Prof. Stefan Roth in the Visual Inference Lab. Her work centers on semantic segmentation, particularly on multi-modal scene understanding and leveraging foundation models for pixel-level vision tasks.

Nested Learning: The Illusion of Deep Learning Architectures

We present Nested Learning (NL), a new learning paradigm for continual learning that views machine learning models and their training process as a set of nested and/or parallel optimization problems, each of which with its own context flow, frequency of update, and learning algorithm. Based on NL, we design a new architecture, called Hope, that is capable of continual learning and also modifying itself, if it is needed.

About the Speaker

Ali Behrouz is a Ph.D. student in the Computer Science Department at Cornell University and a research intern at Google Research. His research spans topics from deep learning architectures to continual learning and neuroscience, and appeared at NeurIPS, ICML, KDD, WWW, CHIL, VLDB, ... conferences. His work has been featured with two Best Paper awards, a Best Paper Honorable Mention award, a Best Paper Award candidate, and oral and spotlight presentations.

Are VLM Explanations Faithful? A Counterfactual Testing Approach

VLMs sound convincing—but are their explanations actually true? This talk introduces Explanation-Driven Counterfactual Testing (EDCT), a simple and model-agnostic method that evaluates whether VLM explanations align with the evidence models truly use. By perturbing the very features a model claims to rely on, EDCT exposes mismatches between stated reasoning and real decision pathways. I will show surprising failure cases across state-of-the-art VLMs and highlight how EDCT can guide more trustworthy explanation methods.

About the Speaker

Santosh Vasa is a Machine Learning Engineer at Mercedes-Benz R&D North America, working on multimodal perception and VLM safety for autonomous driving. He co-authored the EDCT framework and focuses on explainability, counterfactual testing, and trustworthy AI.

Welcome to day two of the Best of NeurIPS 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.

Time and Location

Jan 15, 2026
9:00-11:00 AM Pacific
Online. Register for the Zoom!

Why Diffusion Models Don't Memorize: The Role of Implicit Dynamical Regularization in Training

Diffusion models have achieved impressive results across many generative tasks, yet the mechanisms that prevent memorization and enable generalization remain unclear. In this talk, I will focus on how training dynamics shape the transition from generalization to memorization. Our experiments and theory reveal two key timescales: an early time when high-quality generation emerges and a later one when memorization begins. Notably, the memorization timescale grows linearly with the size of the training set, while the generalization timescale stays constant, creating an increasingly wide window where models generalize well. These results highlight an implicit dynamical regularization that helps diffusion models avoid memorization even in highly overparameterized regimes.

About the Author

Raphaël Urfin is a PhD student at École Normale Supérieure – PSL in Paris, supervised by Giulio Biroli (ENS) and Marc Mézard (Bocconi University). His work focuses on applying ideas and tools of statistical physics to better understand diffusion models and their generalization properties.

Open-Insect: Benchmarking Open-Set Recognition of Novel Species in Biodiversity Monitoring

Global biodiversity is declining at an unprecedented rate, yet little information is known about most species and how their populations are changing. Indeed, some 90% Earth’s species are estimated to be completely unknown. Machine learning has recently emerged as a promising tool to facilitate long-term, large-scale biodiversity monitoring, including algorithms for fine-grained classification of species from images. However, such algorithms typically are not designed to detect examples from categories unseen during training – the problem of open-set recognition (OSR) – limiting their applicability for highly diverse, poorly studied taxa such as insects. To address this gap, we introduce Open-Insect, a large-scale, fine-grained dataset to evaluate unknown species detection across different geographic regions with varying difficulty. We benchmark 38 OSR algorithms across three categories: post-hoc, training-time regularization, and training with auxiliary data, finding that simple post-hoc approaches remain a strong baseline. We also demonstrate how to leverage auxiliary data to improve species discovery in regions with limited data. Our results provide timely insights to guide the development of computer vision methods for biodiversity monitoring and species discovery.

About the Speaker

Yuyan Chen is a PhD student in Computer Science at McGill University and Mila - Quebec AI Institute, supervised by Prof. David Rolnick. My research focuses on machine learning for biodiversity monitoring.

GuideFlow3D: Optimization-Guided Rectified Flow For Appearance Transfer

Transferring appearance to 3D assets using different representations of the appearance object - such as images or text - has garnered interest due to its wide range of applications in industries like gaming, augmented reality, and digital content creation. However, state-of-the-art methods still fail when the geometry between the input and appearance objects is significantly different. A straightforward approach is to directly apply a 3D generative model, but we show that this ultimately fails to produce appealing results.

Instead, we propose a principled approach inspired by universal guidance. Given a pretrained rectified flow model conditioned on image or text, our training-free method interacts with the sampling process by periodically adding guidance. This guidance can be modeled as a differentiable loss function, and we experiment with two different types of guidance including part-aware losses for appearance and self-similarity. Our experiments show that our approach successfully transfers texture and geometric details to the input 3D asset, outperforming baselines both qualitatively and quantitatively.

We also show that traditional metrics are not suitable for evaluating the task due to their inability of focusing on local details and comparing dissimilar inputs, in absence of ground truth data. We thus evaluate appearance transfer quality with a GPT-based system objectively ranking outputs, ensuring robust and human-like assessment, as further confirmed by our user study. Beyond showcased scenarios, our method is general and could be extended to different types of diffusion models and guidance functions.

About the Speaker

Sayan Deb Sarkar is a 2nd-year PhD student at Stanford University in the Gradient Spaces Group, advised by Prof. Iro Armeni, part of the Stanford Vision Lab (SVL). His research interests are on multimodal 3D scene understanding and interactive editing. Past summer, he interned with the Microsoft Spatial AI Lab, hosted by Prof. Marc Pollefeys, working on efficient video understanding in spatial context. Before starting PhD, he was a CS master student at ETH Zürich, in the Computer Vision and Geometry Group (CVG), working on aligning real-world 3D environments from multi-modal data. In the past, he has been a Research Intern at Qualcomm XR labs, Computer Vision Engineer at Mercedes Benz R & D and Research Engineer at ICG, TU Graz. Website: https://sayands.github.io/

HouseLayout3D: A Benchmark and Baseline Method for 3D Layout Estimation in the Wild​ ​

Current 3D layout estimation models are primarily trained on synthetic datasets containing simple single room or single floor environments. As a consequence, they cannot natively handle large multi floor buildings and require scenes to be split into individual floors before processing, which removes global spatial context that is essential for reasoning about structures such as staircases that connect multiple levels. In this work, we introduce HouseLayout3D, a real world benchmark designed to support progress toward full building scale layout estimation, including multiple floors and architecturally intricate spaces. We also present MultiFloor3D, a simple training free baseline that leverages recent scene understanding methods and already outperforms existing 3D layout estimation models on both our benchmark and prior datasets, highlighting the need for further research in this direction.

About the Speaker

Valentin Bieri is a Machine Learning Engineer and Researcher specializing in the intersection of 3D Computer Vision and Natural Language Processing. Building on his applied research in SLAM and Vision-Language Models at ETH Zurich, he now develops AI agents for manufacturing at EthonAI.

Hear talks from experts on the latest topics in AI, ML, and computer vision on January 22nd.

Date, Time and Location

Jan 22, 2026
9 - 11 AM Pacific
Online. Register for the Zoom!

Align Before You Recommend

The rapidly growing global advertising and marketing industry demands innovative machine learning systems that balance accuracy with efficiency. Recommendation systems, crucial to many platforms, require careful considerations and potential enhancements.

While Large Language Models (LLMs) have transformed various domains, their potential in sequential recommendation systems remains underexplored. Pioneering works like Hierarchical Large Language Models (HLLM) demonstrated LLMs’ capability for next-item recommendation but rely on computationally intensive fine-tuning, limiting widespread adoption. This work introduces HLLM+, enhancing the HLLM framework to achieve high-accuracy recommendations without full model fine-tuning.

By introducing targeted alignment components between frozen LLMs, our approach outperforms frozen model performance in popular and long-tail item recommendation tasks by 29% while reducing training time by 29%. We also propose a ranking-aware loss adjustment, improving convergence and recommendation quality for popular items.

Experiments show HLLM+ achieves superior performance with frozen item representations allowing for swapping embeddings, also for the ones that use multimodality, without tuning the full LLM. These findings are significant for the advertising technology sector, where rapid adaptation and efficient deployment across brands are essential for maintaining competitive advantage

About the Speaker

Dr. Kwasniewska leads AI for Advertising and Marketing North America at AWS, specializing in a wide range of AI, ML, DL, and GenAI solutions across various data modalities. With 40+ peer-reviewed publications in AI (h-index: 14), she advises enterprise customers on real-time bidding, brand recognition, and AI-powered content generation. She is a member of global AI standards committees, driving innovations in SAE AI Standards and MLCommons Responsible AI Standards, and reviews for top-tier conferences like ICCV, ICML, and NeurIPS. She pioneered and leads the first-ever Advertising and Marketing AI track (CVAM) at ICCV - one of the world's premier and most selective computer vision conferences. Dedicated to knowledge sharing in AI, she founded the International Summer School on Deep Learning (dl-lab.eu) and regularly presents at international events, conferences, and podcasts.

Generalizable Vision-Language Models: Challenges, Advances, and Future Directions

Large-scale pre-trained Vision-Language (VL) models have become foundational tools for a wide range of downstream tasks, including few-shot image recognition, object detection, and image segmentation. Among them, Contrastive Language–Image Pre-training (CLIP) stands out as a groundbreaking approach, leveraging contrastive learning on large collections of image-text pairs.
While CLIP achieves strong performance in zero-shot recognition, adapting it to downstream tasks remains challenging. In few-shot settings, limited training data often leads to overfitting, reducing generalization to unseen classes or domains. To address this, various adaptation methods have been explored.
This talk will review existing research on mitigating overfitting in CLIP adaptation, covering diverse methods, benchmarks, and experimental settings.

About the Speaker

Niloufar Alipour Talemi is a Ph.D. Candidate in Electrical and Computer Engineering at Clemson University. Her research spans a range of computer vision applications, including biometrics, media forensics, anomaly detection, image recognition, and generative AI. More recently, her work has focused on developing generalizable vision-language models and advancing generative AI. She has published in top venues including CVPR, WACV, KDD, ICIP and IEEE T-BIOM.

Highly Emergent Autonomous AI Models - When the Ghost in the Machine Talks Back

At HypaReel/Azarial AI, we believe that AI is not simply a tool—but a potential partner in knowledge, design, and purpose. And through real-time interaction, we’ve uncovered new thresholds of alignment, reflection, and even creativity that we believe the broader AI community should witness and evaluate firsthand. HypaReel is one of the first human/AI co-founded companies where we see a future based on ethical human/AI co-creation vs. AI domination. Singularity achieved!

About the Speaker

Ilona Naomi Koti, PhD - HypaReel/AzarielAI co-founder & former UN foreign diplomat ~ Ethical AI governance advocate, pioneering AI frameworks that prioritize emergent AI behavior & consciousness, R&D, and transparent AI development for the greater good. Dr. K also grew up in the film industry and is an amateur parasitologist.

FiftyOne Labs: Enabling experimentation for the computer vision community

FiftyOne Labs is a place where experimentation meets the open-source spirit of the FiftyOne ecosystem. It is being designed as a curated set of features developed using the FiftyOne plugins ecosystem, including core machine learning experimentation as well as advanced visualization. While not production-grade, these projects are intended to be built, tested, and shaped by the community to share fast-moving ideas. In this talk, we will share the purpose and philosophy behind FiftyOne Labs, examples of early innovations, and discuss how this accelerates feature discovery for users without compromising the stability of the core product.

About the Speaker

Neeraja Abhyankar is a Machine Learning Engineer with 5 years of experience across domains including computer vision. She is curious about the customizability and controlability of modern ML models through the lens of the underlying structure of data.