TokenTrace at CVPR 2026: Tracing Creative Influence in Generative AI 

TokenTrace embeds lightweight watermarks into training tokens associated with visual concepts. When the model later generates an image, TokenTrace can recover traces of these watermarked signals, allowing researchers to identify which concepts most strongly contributed to the output. 

Giving Image Editors Adjustable Control Over Editing Instructions: SliderEdit at CVPR 2026 

SliderEdit introduces continuous, adjustable control over individual editing instructions in instruction-based image editing models, turning each instruction into a smooth slider. 

TeamFusion: Using AI Agents to Represent Every Voice in Team Decisions 

TeamFusion is a multi-agent framework that supports team decision-making by creating AI proxy agents grounded in each member’s preferences, so that humans can make better-informed decisions together. 

Agentic Design Review System: Teaching AI to review graphic designs the way experts do 

Our Agentic Design Review System (Agentic-DRS) is an experimental multi-agent framework from Adobe Research for holistic graphic design evaluation. Specialized AI agents assess typography, color harmony, alignment, spacing, composition, and more, coordinated by a meta-agent. 

Adobe Research at Summit 2026: Agentic AI for orchestrating customer experiences 

Adobe Research was behind some of the most exciting announcements, sessions, and sneak previews at Adobe Summit - from the unveiling of new tools that help marketers understand their customers’ behavior and design customer experiences at scale to hands-on agentic AI sessions.

Object-WIPER: A Smarter Way to Erase Objects from Video 

Rather than treating object removal as a simple mask-and-fill task, Object-WIPER recognizes that objects leave visual traces in a scene — shadows on the ground, reflections in glass, translucent overlaps with the background — and that a complete removal means erasing those traces too. 

MotionStream demonstrates real-time control in AI video creation

With the new experimental technology MotionStream, video creators can interact with AI-generated video while it’s being created, directing the movement of objects and changing camera angles in real-time with the simple use of a cursor and sliders.

When the Music Fits: VidTune Helps Video Creators Find the Right Soundtrack 

The experimental technology VidTune generates multiple music tracks from a text prompt and produces visual "contextual thumbnails" for each one, letting creators compare options at a glance.

Vidmento: Filling the gaps in your video story with generative AI 

Vidmento is an experimental AI-assisted video authoring tool from Adobe Research, accepted at CHI 2026, that helps creators build complete video stories by blending their own captured footage with contextually generated clips — preserving narrative continuity and creative intent throughout.