Joseph Chee Chang
@josephcc
Followers
697
Following
868
Media
42
Statuses
4K
šš»š Research Scientist @ AI2/Semantic Scholar | Artisanal small-batch handcrafted tweets with no added llms. @[email protected] @josephc.bsky.social
Seattle, originally Taiwan
Joined November 2007
RT @mosh_levy: Producing reasoning texts boosts the capabilities of AI models, but do we humans correctly understand these texts? Our latesā¦.
0
27
0
Blazing-fast image creation ā using just your voice. Try Grok Imagine.
284
557
3K
RT @cmalaviya11: People at #ACL2025, come drop by our poster today & chat with me about how context matters for reliable language model evaā¦.
0
6
0
RT @tongshuangwu: @Diyi_Yang @josephcc Thank you all for joining us!! The Q&A were all very insightful šš Here's the link to the slides: htā¦.
docs.google.com
Human-AI Collaboration: How AIs Augment Human Teammates 1 Sherry Wu @ CMU Diyi Yang @ Stanford In collaboration with Marti Hearst @ UC Berkeley and Kyle Lo @ Ai2 July 27 9:00 - 12:30 Hall N, Austria...
0
1
0
RT @arnaik19: In Vienna for #ACL2025NLP this week!. @josephcc, @aps6992 and I will present the Ai2 ScholarQA scientific QA system on Wed. Iā¦.
0
3
0
RT @tongshuangwu: We all agree that AI models/agents should augment humans instead of replace us in many cases. But how do we pick when toā¦.
0
21
0
You can now jump from Scholar QA answers to highlighted evidence in the source paper's pdf : ).
Weāve upgraded ScholarQA, our agent that helps researchers conduct literature reviews efficiently by providing detailed answers. Now, when ScholarQA cites a source, it wonāt just tell you which paper it came fromāyouāll see the exact quote, highlighted in the original PDF. š§µ
0
1
16
RT @ai2_s2research: @allen_ai @SemanticScholar.is hiring an #ml #nlp #ai reasoning researcher for a Research Scientist, Agents for Scienceā¦.
0
11
0
RT @PhilippeLaban: špaper: LLMs Get Lost in Multi-Turn Conversation. In real life, people donāt speak in perfect prompts. So we simulate muā¦.
0
32
0
RT @RuotongWang1: AI agents are entering online social spaces, but often their messages feel generic or intrusive. In our #CHI25 paper, weā¦.
0
21
0
RT @rayrayfok: We are looking for CS researchers to participate in a study exploring how AI can change the way we do literature reviews. šā¦.
docs.google.com
We are researchers from the University of Washington and AI2, and are currently recruiting participants for a user study that explores how AI tools can support scientific literature review. During...
0
11
0
RT @kylelostat: working with PDFs for LMs, errors in extracting content can be soul-crushing. we need not just clean OCR but also correct rā¦.
0
14
0