News

Summer 2026 Adobe Research interns, Andrew Shaw, Lisa DiSalvo, and Bryant Bettencourt, worked on projects ranging from human-computer interaction to generative AI to document experiences. But ask them about their summers, and they'll tell you the project was only part of the story.

Meet two generations of Adobe Research interns who’ve accomplished amazing things: created cutting-edge research, published papers, and did Adobe Summit Sneak presentations of their work for thousands of Adobe customers.

Every day, Adobe researchers push the boundaries of technology—a process that’s second nature to Principal Scientist Brian Price. Price has now contributed to his 100th patent at Adobe. We talked with him about his work.

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.

On an exceedingly cold day 30 years ago, Principal Scientist John Nelson decided to leave his job as a Denali mountain guide and head to something warmer. With a background in computer science and fluency in Japanese, Nelson joined Adobe’s After Effects team, first working

GEM Fellows Faith Baca, Christina Chance, and Reuben Luera reflect on how their Adobe Research experience this summer fostered community, mentorship, and hands-on innovation as they advanced research in AI.

At Adobe Research, former interns who are now mentors guide today’s interns through projects that shape both academic research and real products, from tackling bias in AI and advancing content attribution to developing new audio models.

Adobe Research interns took on ambitious projects, worked alongside mentors, and built community— all while shaping the future of tech. Get to know six interns who pushed innovation forward this summer.

This summer, returning Adobe Research interns are taking their projects further — deepening collaborations, publishing new research, and building AI tools with real-world impact. Discover how their experiences shaped their path forward.

This spring, John Collomosse, Sr. Principal Scientist at Adobe Research, joined the Royal Society’s prestigious Pairing Scheme in Westminster to share his expertise in content authenticity with UK policymakers.

Adobe Research Scientist Shruti Agarwal is tackling misinformation by empowering artists and consumers with Content Credentials. Discover how her innovative research, from deepfake detection to invisible watermarking, is restoring trust in the digital world.

Adobe Research scientist Srikrishna Karanam is making visually cohesive branding easier with AI. His work on On-brand Recolor in Adobe Express helps businesses apply brand colors effortlessly with just one click.

Adobe Research has helped build an AI Assistant for Photoshop that lets you edit images by simply describing what you want.

A new feature in Adobe Firefly built in collaboration with Adobe Research is making text-to-image generation more accessible for blind and low-vision (BLV) creators.

Video of Rotate Object by Rob de Winter A new Photoshop feature, built with major contributions from Adobe Research, allows users to turn a 2D layer into a 3D object, rotate the angle and perspective of the object, and then place it seamlessly back into

Adobe Research’s Sound Design AI group shares how Generative Extend brings natural, seamless audio extensions to Premiere Pro, helping creators fix gaps and preserve ambience with ease.

Clip Maker, a collaboration between Adobe Research and Adobe Express, combines cutting-edge AI with intuitive design to help creators craft social-ready clips in seconds. Check out the behind-the-scenes story!

Adobe Express’s new Dynamic Animation feature lets anyone add motion to still images with playful wobbles, wiggles, and bounces—all powered by years of work from Adobe Research and a close collaboration with the Express team. Check out the full story!

Jointly developed by Adobe Research and the Photoshop team, Harmonize uses AI to relight, recolor, and blend objects seamlessly into any scene. First shown as MAX Sneak Project Perfect Blend, this breakthrough is now available in Photoshop! Read the full story.

Firefly’s Generate Sound Effects (GenSFX) was created by Adobe Researchers who envisioned a new approach to audio: one that’s intuitive, expressive, and fun.

First introduced as Project Dub Dub Dub at Adobe MAX 2023, this AI tech now powers the cutting-edge translation tool in Adobe Firefly. It translates videos while matching the speaker’s voice, tone, and cadence. Explore the tech behind the magic!

Project Fast Mask—what began as a research prototype is now powering tools like Roto Brush 3 in After Effects and Remove Video Background in Adobe Express. Discover how this breakthrough in AI-driven object selection is transforming the way we edit videos!

Wondering what’s next for precise, controllable generative AI? Check out the breakthroughs our Adobe researchers are sharing this week at ECCV.

RetouchIQ is an experimental AI editing agent that understands what you mean when you describe how a photo should look and feel, then translates that intent into precise adjustments in professional photo-editing software. 

Adobe Researchers are helping shape the future of AI at the world’s premiere computer vision event, CVPR 2026, the IEEE/CVR Computer Vision and Pattern Recognition Conference. Adobe Researchers are presenting over 75 research papers, including several Oral Papers and award finalists.

SuperFit - presented at CVPR 2026 - converts complex 3D shapes into compact assemblies of simple, interpretable building blocks, called SuperFrusta. 

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. 

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

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. 

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. 

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 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. 

SIGMA-GEN is an experimental unified framework from Adobe Research, presented at ICLR 2026, for multi-identity-preserving image generation — placing multiple subjects into a scene in a single pass, with each subject's appearance faithfully preserved. 

Adobe Research’s NeurIPS 2025 contributions explore new territory in machine learning and AI, including layered image generation, design-aware templates, and subject-driven video models. This teaser highlights a few papers shaping the future of creativity.

On World Photography Day, Adobe Researchers are contributing technologies that give people the information they need to understand where an image comes from, how it’s been changed, and whether its history can be independently verified.

Learn the behind-the-scenes story of Project Face Off - voted the best Summit Sneak of the year. 

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. 

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.

Adobe Researchers have been honored with a Technology and Engineering Emmy for their groundbreaking work on virtual reality (VR) editing tools. The Emmy celebrates Adobe’s “significant contributions to the development of 360-degree consumer video capture, editing, and presentation technologies.”

Rotating a screen with Turntable (Zhiqin Chen, Adobe Stock image) Audiences got their first sneak peek of Adobe Research’s Project Turntable on the Adobe MAX stage. The new tool allows artists to spin their own 2D vector art to different angles, much like artists can

Getting a perfect green-screen cutout is harder than it looks. PolarMatte uses polarized light to capture clearer mattes from just one shot, helping researchers train future AI tools to handle even the trickiest details.

At this year’s Adobe MAX, more than 10,000 creative professionals gathered for a glimpse at the latest Adobe innovations. Here's a look at some of the exciting Adobe Research-powered announcements from Adobe MAX 2025.

35 years of Photoshop! From early masking tools to today’s generative AI, Adobe Research has fueled breakthroughs that push the boundaries of creativity—turning bold ideas into everyday magic for creators worldwide.

What happens when AI doesn’t just respond—but learns and improves from every human interaction? In this story, Principal Research Scientist Branislav Kveton shares his work on reinforcement learning, agentic AI models, and his insights on the evolving relationship between humans and AI.

Editing photos can be tricky, especially if a user isn’t familiar with all their editing tools. Adobe Researchers have developed a new AI model that spots what a user might want to fix, explains each step, and lets users choose which edits to make. Learn more about this new research!

From helping create the Acrobat AI Assistant to the AEP AI Assistant, Adobe Research is pioneering agentic AI to superpower creativity and productivity. See how our latest breakthroughs are shaping what’s next and explore the key initiatives in our work on agentic AI.