DIM leverages spatial representations and direct manipulation to unlock deep human–AI collaboration in intent generation, evaluation, and integration. In this work, we apply DIM in evaluating and refining research directions.

🚨 When people are worried about language models’ linguistic intelligence surpassing humans, we should instead harness other human strengths such as spatial reasoning. 💡Thrilled to share our research concept accepted by UIST'25: Direct Intent Manipulation (DIM).

Generate videos in just a few seconds. Try Grok Imagine, free for a limited time.

RT @YuanchenB36202: 🚨 Do stronger reasoning models guarantee better real-world coordination and performance? .Not always. 🔔 Sharing our ne….

🎉 Officially ABD! My dissertation proposal "From Automation to Augmentation: Scaffolding and Structuring Human-AI Collaboration through Intent-oriented Interaction Paradigms" is approved by my committee. Time to hit the job market 🚀

As agents increasingly operate UIs, users can express intents instead of stepwise GUI manipulation. We've been exploring how to combine the strengths of intent-based interaction and direct manipulation and proposing Direct Intent Manipulation (DIM), accepted as a UIST'25 poster!

Not sure which career path to take in the age of AI automation—PhD, dev, ML, or startup? Introduce CareerPooler 🎱: turn career planning into a pool game—pocket milestones, skills & surprises to simulate multiple career paths! 🚀Try it out—join our study:

RT @gliu0329: 🎓💰🔬 Want to learn machine learning, win a cash prize (USD 50K in total!!), and help drive real progress in discovering new po….

Seeing other researchers adopt, apply, and cite a concept I contributed to is a truly rewarding moment:

RT @haofeiyu44: 🧪 Want an AI-generated paper draft in just 1 minute? Or dreaming of building auto-research apps but frustrated with setups?….

Try out the interactive demo at and check out the open-source repository at :).

Forecasting tech advancements has always been challenging. Yet, historical parallels can offer insights into the patterns of innovation. We present the concept of an analogical timeline—a method of using LLM and one tech trajectory to predict the future evolution of another.

"History doesn't repeat itself, but it often rhymes.". We introduce the Analogical Timeline for the Hype Cycle as an initial approach to tackling a question that captivates everyone yet remains elusive: What will the future be like?

Excited to share that the full paper version of my intern work on GenAI hypothesis exploration @MITIBMLab has been accepted by @acm_cc, with an acceptance rate of 21.8%. This year was especially competitive—I deeply felt it as a PC member.

@ACMIUI @MITIBMLab Read our paper ↓

Next week at @ACMIUI, we’ll present my internship work at @MITIBMLab: "Structuring GenAI-Assisted Hypothesis Exploration with an Interactive Shared Representation." We applied Intent-AI Interaction to data analysis, allowing analysts to collaborate with AI at a conceptual level.

To ride tech waves, we must understand not just what will happen, but also when and how. Yet, the wave vs. bubble debate persists. Our best practice is to draw analogies from history—introducing "Analogical Timeline for GenAI & Robot": It'll stay updated!

@Figure_robot Yet, when we look back at the history of GenAI, things becomes much clearer. Let’s discuss together the trial and error in GenAI back in 2022 to better ride the robot wave in 2025! More information will be announced later.

Over the past year, we witnessed many AI advancements: VLM, open-source reasoning models, and multi-agent frameworks. All of these point towards robotics as a key application, as reflected in @Figure_robot valuation surge from $2.6B (Feb 2024) to $39.5B (Feb 2025).

Glad to introduce our colloquium "Robot in 2025 as GenAI in 2022: Riding the robot wave with lessons learned from GenAI boom" in Atlanta on May 18, 2025! Don't regret missing the GenAI boom—we are about to embrace an even bigger robotics wave soon.

Over the past year, we witnessed many AI: advancements: VLM, open-source reasoning models, and multi-agent frameworks. All of these point towards robotics as a key application, as reflected in @Figure_robot valuation surge from $2.6B (Feb 2024) to $39.5B (Feb 2025).