
Joseph Chee Chang
3.9K posts

Joseph Chee Chang
@josephcc
😉💻🔄 Research Scientist @ AI2/Semantic Scholar | Artisanal small-batch handcrafted tweets with no added llms. @[email protected] @josephc.bsky.social


🤔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. 🧵

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



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






CDS PhD alum Vishakh Padmakumar (@vishakh_pk), now at @Stanford, tackled the hard part of summarization — deciding what matters. At @Adobe, he built diversity-aware summarizers; at AI2 (@allen_ai), intent-based tools for literature review tables. nyudatascience.medium.com/supercharged-i…






Excited to share ✨ Contextualized Evaluations ✨! Benchmarks like Chatbot Arena contain underspecified queries, which can lead to arbitrary eval judgments. What happens if we provide evaluators with context (e.g who's the user, what's their intent) when judging LM outputs? 🧵↓









