😉💻🔄 Research Scientist @ AI2/Semantic Scholar | Artisanal small-batch handcrafted tweets with no added llms. @joseph@hci.social @josephc.bsky.social

Seattle, originally Taiwan
Joined November 2007
Joseph Chee Chang retweeted
Had a fun summer working @allen_ai on simulated reasoning (as a diagnostic lens) with @josephcc, @amyxzh, @Siangliulue, @mbodhisattwa! Sharing new results at the poster on Fri! (full preprint coming soon 🙏🏻)
Upcoming travel and papers: Not officially at #colm2026 but stopping by tmrw to the Ai2 event! And we have a paper in the Social Simulation with LLMs workshop: openreview.net/forum?id=81iy… Sat-Tues I'll be at #cscw2026, first on a panel at the COMPASS workshop sites.google.com/view/worksh…
3
9
414
We’re also hiring for multiple positions and will have researchers across teams and recruiters at the event to answer questions if you’re interested 🙂
174
Hello friends, who's also going to COLM? : )
8
27
1,994
Looking for study participants (3 hr $150) to build theories from 100 papers. For example, "How does different AI attribution affects reader perceptions?" "How does XAI techniques affect performance?" If that sounds interesting please sign up here : ) forms.gle/8Qgxkz31TRfoDDtj8
3
6
954
Joseph Chee Chang retweeted
Excited to share MyScholarQA - a personalized deep research tool that learns from your papers and lets you customize reports! 🧑‍🔬🖌️ Our #ACL2026 paper built and evaluated it, showing simulated users (LLMs) couldn't mimic what real users wanted 🙅 Spicy results + a live demo 👇🧵
1
33
2
92
12,547
Joseph Chee Chang retweeted
Are you a researcher in CS or a CS-adjacent field curious about how an AI agent can help you with your research project? Want to try a new tool for your research support in a paid user study ($100, 2 hr)? Limited spot numbers. See details and sign up here: forms.gle/JzLtkAhe7TtvuiwQ8
2
22
98
9,790
Joseph Chee Chang retweeted
Cocoa is accepted to #chi2026 as a 🏆best paper (top 1% of submissions)! See you in Barcelona 🎉🇪🇸
🤔Giving complex tasks to AI agents is easy—getting them to do exactly what you want isn’t. How can human-AI collaboration give us more reliable & steerable agents? 🍫Introducing Cocoa, our new interaction paradigm to balance human & AI agency in complex human-AI workflows. 🧵
4
8
2
67
8,267
Joseph Chee Chang retweeted
We analyzed 250K+ queries & 430K+ clickstream interactions from Asta, our AI-powered research assistant—and today we're releasing the full dataset. How do researchers actually use AI science tools? Here's what we found. 🧵
6
15
2
104
11,151
Submission deadline ending soon - Come hangout with us at CHI : )
What is future of reading? 📗 Announcing the 1st Science & Technology of Augmented Reading (STAR) workshop at #CHI2026! We want your takes on: 🤖 AI & Agents for reading 👁️ Visual Interactions 🗺️ Domains (Code, Law, Ed, etc.) 👇 Submit a 2-4 pg paper: chi-star-workshop.github.io/
2
262
Joseph Chee Chang retweeted
What is future of reading? 📗 Announcing the 1st Science & Technology of Augmented Reading (STAR) workshop at #CHI2026! We want your takes on: 🤖 AI & Agents for reading 👁️ Visual Interactions 🗺️ Domains (Code, Law, Ed, etc.) 👇 Submit a 2-4 pg paper: chi-star-workshop.github.io/
4
2
13
2,062
Joseph Chee Chang retweeted
Deadline for submission in just under 10 days! Reach out if you have any questions.
What is future of reading? 📗 Announcing the 1st Science & Technology of Augmented Reading (STAR) workshop at #CHI2026! We want your takes on: 🤖 AI & Agents for reading 👁️ Visual Interactions 🗺️ Domains (Code, Law, Ed, etc.) 👇 Submit a 2-4 pg paper: chi-star-workshop.github.io/
1
2
8
570
Joseph Chee Chang retweeted
Introducing Theorizer: Turning thousands of papers into scientific laws 📚➡️📜 Most automated discovery systems focus on experimentation. Theorizer tackles the other half of science: theory building—compressing scattered findings into structured, testable claims. 🧵
14
88
15
587
55,705
Joseph Chee Chang retweeted
🆕 New in Asta: multi-turn report generation. You can now have back-and-forth conversations with Asta, our agentic platform for scientific research, to refine long-form, fully cited reports instead of relying on single-shot prompts.
1
10
3
70
6,705
Joseph Chee Chang retweeted
Ever want to ask questions about a paper, including its figures & tables? 📊📈 Want smoother interactions w/papers on desktop & mobile? Try Paper+Figure QA, a new tool from @allen_ai that answers with the original figures, tables, and excerpts from papers: paperfigureqa.allen.ai
1
3
1
5
1,286
Joseph Chee Chang retweeted
Update: DataVoyager, which we launched in Preview early this fall, is now available in Asta. 🎉 You can upload real datasets, ask complex research questions in natural language, & get back reproducible answers + visualizations. 🔍📊
6
16
4
64
13,143
Ai2 is hiring Summer interns to work on: - human-AI interaction and intelligent UIs - research support systems e.g., lit reviews, ideation - and more! We encourage publishing and public deployments. Apply with link below before Dec 15 for the first reviews cycle : ) #chi2026
7
26
2
254
18,407
Joseph Chee Chang retweeted
Last year I worked at @Adobe @AdobeResearch and @allen_ai, exploring how we can help users read, organize and understand long documents. This piece covers what we learned on modelling user intent and combining LLMs with principled tools when building complex pipelines for it!
2
6
1
51
10,469
Joseph Chee Chang retweeted
Introducing Asta—our bold initiative to accelerate science with trustworthy, capable agents, benchmarks, & developer resources that bring clarity to the landscape of scientific AI + agents. 🧵
10
47
8
219
296,603