CLIP
Deconstructing Complex Events through Modeling Uncertainty, States, and Outcomes
Fighting the Global Social Media Infodemic: from Fake News to Harmful Content
Computational models of language acquisition: Lessons from humans for machines and from machines for humans
Curriculum Learning: Scores, Plans, Dynamics, and NLP
Abstract: Curriculum learning is an effective and natural strategy in human learning. It plays an important role in challenging tasks such as language learning. However, current machine learning (ML) paradigms are mostly built upon repeatedly practicing the same training data/tasks with a random order, which is non-adaptive to the learning process. Moreover, they do not plan multiple learning stages in advance as humans.
Following Instructions and Asking Questions
Abstract: As we move towards the creation of embodied agents that understand natural language, several new challenges and complexities arise for grounding (e.g. complex state spaces), planning (e.g. long horizons), and social interaction (e.g. asking for help or clarifications). In this talk, I'll discuss improvements to embodied instruction following within ALFRED and initial steps towards building agents that ask questions or model theory-of-mind.
Zoom link: https://umd.zoom.us/j/98806584197?pwd=SXBWOHE1cU9adFFKUmN2UVlwUEJXdz09 (passcode if needed: clip)
Scaling health care delivery with machine learning
Prof. Riedl will present virtually.
Zoom link: https://umd.zoom.us/j/98806584197?pwd=SXBWOHE1cU9adFFKUmN2UVlwUEJXdz09 (passcode if needed: clip)
The Quest for Automated Story Generation