AI, ML and Computer Vision Meetup - September 24, 2026
A virtual AI and computer vision meetup featuring responsible automotive AI, coffee-yield estimation, region-based visual representations and consistent image-set generation with diffusion models.
When
Sep 24, 2026
Where
Online event
Attendance
Virtual
Status
scheduled
Event type
Meetup · Published by organizer
Registration
See the organizer for current access, pricing and registration details.
At Mercedes-Benz, our AI Principles guide every step of innovation, emphasizing responsible use, safety and reliability, explainability, and the protection of privacy. These principles go beyond statements and actively shape how we design, test, and deploy AI systems in real-world automotive and enterprise settings.
In this talk, I will present how these principles inspired our recent research on when reusing LoRA (Low-Rank Adaptation) is effective. By combining theoretical analysis with synthetic data as a proxy for enterprise scenarios, we uncovered the strengths and limitations of modular AI components under constrained data access.
Our findings provide practical guidance on when reused LoRAs could deliver high-quality results.
Image collections are humans' primary way of capturing the world, yet advances in generative editing remain largely inapplicable to this modality. We address this gap by introducing Match-and-Fuse - a zero-shot, training-free method for consistent set-to-set generation from image collections that share a common visual element but differ in viewpoint, capture time, and surrounding content.
Our key idea is a unified graph-based framework that combines dense correspondences with an emergent prior in text-to-image diffusion models to generate coherent canvases. We achieve state-of-the-art consistency and visual quality, and unlock new creative capabilities for content generation.
Patch-based tokenization has become the default interface between vision encoders and downstream models, yet patches carry no semantic structure and scale poorly with resolution and temporal extent. This talk presents a research program centered on replacing patch tokens with region-level representations — semantically dense tokens grounded in visual entities rather than arbitrary grid crops.
I will describe RELOCATE, REN, and T-REN, a progression of methods that produce region tokens via pooling, train them with region-level objectives, and extend them to video with temporal coherence. I will then present ongoing work integrating region tokens into VLMs to directly expand visual context capacity, and preliminary results on future region trajectory prediction as a foundation for world modeling.
The broader thesis is that region-level tokens are a more natural unit of visual computation than patches, and their advantage compounds as task complexity, resolution, and temporal horizon increase.
This presentation provides a detailed workflow related to coffee yield estimation in a dense environment. With photos of pre-harvest coffee plants from a couple of coffee estates, details related to pre-processing, annotation to detect regions of interest (ROI), object detection training and inferencing results with various Yolo models and finally segmentation with SAM2 and Yolo*-seg with training and inference results to determine the count of raw, pre-mature, mature and over-mature coffee berries and finally the yield of the entire estate.
All this is based on real world data captured on iPhone and android phones.
partial: All verifiable upcoming-edition names on the inspected page were extracted. This is not a claim that the final event roster is complete. Reviewed 2026-09-11T18:15:44.269Z.
sponsors
not extracted: Not yet extracted from an edition-specific public source. Reviewed 2026-09-11T18:15:44.269Z.
exhibitors
not extracted: Not yet extracted from an edition-specific public source. Reviewed 2026-09-11T18:15:44.269Z.
attendees
not extracted: A public named attendee roster has not been extracted. Speakers and company employment do not imply named attendance. Reviewed 2026-09-11T18:15:44.269Z.
agenda
partial: All verifiable upcoming-edition names on the inspected page were extracted. This is not a claim that the final event roster is complete. Reviewed 2026-09-11T18:15:44.269Z.
Sources
Showing 3 of 3 source records. A source check is not a claim of complete extraction.
Published schedule: 9:00 AM - 11:00 AM PST. Exact time and timezone withheld because organizer abbreviations are not independently reconciled. Full biographies/abstracts retained in immutable HTML receipt. Sponsor, exhibitor and attendee lists not inferred from speaker employers. Session local day: the published single-day event page groups these agenda items/talks on 2026-09-24. Exact times remain unknown where timezone labels are unresolved.