Thrilled to announce that as of today, I am an assistant professor at @UMontreal, affiliated with @Mila_Quebec and @IVADO_Qc 🎉 I am very thankful to my advisors and colleagues for all their support and guidance throughout this journey. I am very excited for this new chapter.

Our work lays the foundation for writing support, not just through words, but also visuals. 📝Paper: https://t.co/GUHmEsHIuz 🎥Video: https://t.co/TyxPAibAPl 🖥️Code: https://t.co/brhHEQJiTI 🕹️Demo: https://t.co/eEducI6ucm (8/8)

Of course, many more visualizations could help writers. That is why we propose a framework to help inform the design of visual representations that support the visual story-writing workflow. 👇 (7/8)

In two user studies with inexperienced and experienced creative writers, we found that the generated visualizations supported participants in planning high-level revisions, tracking story elements, and exploring story variations in ways that encourage creativity. (6/8)

Creating new characters or new interactions between characters is as simple as creating a new node and connecting it. 👇 (5/8)

Changing the order of scenes is as simple as moving them around in the timeline. 👇 (4/8)

Reviewing characters’ movements becomes a visual task. And changing a character's location in a scene is as simple as dragging them from one location to another on a map. 👇 (3/8)

We developed an intelligent word processor that offers three automatically generated views to review the interaction and relationships between characters, their locations, and the order of the scenes. This helps review and edit the story.👇

Visual Story-Writing. While you write, our word processor visualizes the timeline, world map, and character relationships. Editing these visuals updates the story (e.g. drag a character on the map to move them). This summarizes our #UIST2025 paper. #HCI #LLMs #AI Thread 🧵 (1/8)

🚨 How can we enable exploration & iteration in the design process — across personas, problem statements, solution ideas, and scenarios? Our #UIST2025 paper tackles this with AI and propagation-based mechanisms ⤵️/⤴️. 🌐 https://t.co/jD2h8urLFE 🎥 https://t.co/fGQ3i22D8d 🧵👇

Super excited that our paper, co-authored with @junkato, on parameter-tuning widgets for creative software has been accepted to #UIST2025. It’s my first academic paper ever, which makes it way more special. #tweeqjs https://t.co/pjwcjumLmF

Huge congratulations to my coauthors @farwest1138 @jsquare & LiYi on receiving the @acm_dis best paper award 🏆 for Narrative Motion Blocks. This paper is very close to my heart, as it combines direct manipulation affordances with textual prompts for animation creation.

How should we update AI memory of user intent as intent evolves? 🤖💭 How can we auto-update memory docs like Cursor rules as a user interacts with an AI agent over time? Check out our pre-print: Semantic Commit: Helping users update intent specifications for AI memory at scale!

Are we really designing the tools writers want? Find out in this great work. Tons of great ideas emerged from it. This might inspire your next project!

This work was done during my postdoc with @fanny_uoft in collaboration with @YounghoHCI. I will present this work at CHI2025 on Tuesday, 29, April at 2:10PM in the session “Text Entry”. Come find me in Yokohama if you want to chat! (10/10)

Textoshop reimagines text editing. We encourage others to use interaction analogies to revisit existing workflows when designing software. 📝Paper: https://t.co/KCmvBwpPYN 🎥Video: https://t.co/i8QwXgs8Lq 🖥️Code: https://t.co/0H4oqUHVmA 🕹️Demo: https://t.co/iTmemvnb3o (9/10)

In a user study with both guided and free-form tasks, we found participants transferred their knowledge of drawing software onto Textoshop to the point where they guessed how to use its features and followed new workflows, although it was not always a good thing. (8/10)

And just like images are organized in layers, in Textoshop, “text layers” do not simply overlay text but also cause a reflow of the whole document. This makes them powerful to organize the text and manage different versions. 👇 (7/10)

Just like shapes can be combined using boolean operations, in Textoshop, two passages of text can be “united” to merge ideas, “intersected” to keep common ideas, “subtracted” to remove ideas, or “excluded” to keep unshared ideas. 👇 (6/10)

But this analogy goes beyond tools and also extends to workflows. Just like only what is on the canvas is part of the final image, in Textoshop, text can be moved so that the margin becomes an experimentation zone that can also store text for inspiration or future use. 👇 (5/10)

Just like colours are explored in a colour wheel, in Textoshop, tones are explored in a tone picker which offers a 3D space to browse thousands of tone variations for a single passage of text. 👇 (4/10)