Starting my Ph.D. journey at UT Austin! I am excited to work with @amypavel on HCI+A11y research🙂

RT @yoonchangsung: I’m hiring multiple PhD students and one postdoc at NTU Singapore, starting in Spring or Fall 2026, to push the frontier….

RT @fangcong_y10593: Solving complex problems with CoT requires combining different skills. We can do this by:.🧩Modify the CoT data format….

For more details, check out our paper: . If you’re interested in collaborating, please reach out!.

It was exciting to collaborate with students and teachers at TSBVI and explore AI's impact on accessible video editing. We look forward to expanding access further.

At CHI 2023, we introduced AVscript, a text-based video editing tool that lets blind creators edit videos using a screen reader. It provides a narration transcript with scene descriptions and highlights visual errors (e.g., blur, bad lighting).

Last week, we visited the Texas School for the Blind and Visually Impaired (TSBVI) and introduced AVscript to their Film and Media class. 🎥🎬 Students tried editing videos with our tool!

RT @jayhersk: I’m so happy to share that I’ll be joining @TuftsUniversity @TuftsCS as an Assistant Professor in January 2026! 🥳 I’ll be rec….

RT @dingzeyuli: Come to Mina's talk today afternoon at 2:10pm @ G303!. VideoDiff is about the future of video authoring shifting from editi….

RT @LiyanTang4: Check out my work at @bespokelabsai We release Bespoke-MiniChart-7B, a new SOTA in chart understanding of its size. Chart u….

RT @ManyaWadhwa1: Evaluating language model responses on open-ended tasks is hard! 🤔. We introduce EvalAgent, a framework that identifies n….

RT @kevpjk: 🤖👩🏻‍💻Proactive AI tools like @GitHubCopilot @cursor_ai @allhands_ai promise to assist developers by anticipating their needs a….

📄This is a work done during my internship @AdobeResearch with awesome @dingzeyuli @kpimmel Hijung Valentina Shin @amypavel Mira Dontcheva.

Users can also narrow down the options by sorting and further customize them by refining and regenerating AI suggestions. For each new version, VideoDiff provides a diff summary highlighting how it differs from the original.

VideoDiff generates diverse AI recommendations for making rough cuts, inserting B-roll, and adding text effects. It supports easy comparison by aligning videos and highlighting differences using Timeline and Transcript views.

Recent AI models can suggest endless video edits, offering many alternatives to video creators. But how can we easily sift through them all? . In our #CHI2025 paper, we propose VideoDiff, an AI video editing tool designed for editing with alternatives.

RT @anuj_diwan: If you'd like an open-source text-to-speech model that follows your style instructions, consider using our ParaSpeechCaps-b….

RT @john_jyc: #CHI2025 paper from Midjourney Storytelling Lab.🫱🧸 🦖🫲What if we can tell a story by playing with toys?.🫱🧸 🦖🤖What if we can co….

Following inquiries, we are extending the deadline to the 20th. We look forward to your submission!.

and awesome team of organizers @hcikate @jazette_j @amypavel & Jennifer Mankoff.

We have awesome panelists including @svaleval @dj_hci @ArianaAboulafia @ChanceyFleet.