I’ve always wanted to write an open-notebook research blog to (i) show the chain of thought behind how we formed hypotheses, designed experiments, and articulated findings, and (ii) lay out all the intermediate results that did not make it into the final paper, including negative
- Excited to share 2 papers from SLED at #COLM2025: - Bootstrapping Visual Assistant Modeling with Situated Interaction Simulation. - Vision-Language Models Are Not Pragmatically Competent in Referring Expression Generation. Come talk to us at the poster sessions!
- We had great discussions today hosting Joyce Chai @mbzuai! Starting new collaborations, expanding our research views
- Replying to @fredahshiFind me at: - Fri Apr 25, 10am-12:30pm Hall 3 + Hall 2B #212, presenting the poster below w/ @Kordjamshidi and @SLED_AI - Fri Apr 25, Oral Session 4c w/ @SLED_AI - All mentorship hours (12:30pm-2pm) on Apr 24-26 - proudly chairing the sessions w/ @savvyRL (2/)
- Language use in embodied AI has been a central focus for us at SLED Lab. We’re excited to welcome you to the @michigan_AI Symposium this year, looking forward to seeing you at the poster session! ❤️




