Region Tokens as the Visual Primitive: From Recognition to World Modeling

AI, ML and Computer Vision Meetup - September 24, 2026

Sep 24, 2026 · Time to be announced

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.

Session status: scheduled

Official session / agenda

Saving a session is not registration. Check the official agenda for availability, eligibility and any additional fees.

Speakers and their event affiliations

Parent event

Virtual · Online event

This describes the parent event. Confirm the session’s attendance requirements with the organizer.

Companies participating in the parent event

These are event-level relationships, not confirmed sponsorship of this session.