Skip date selector
Skip to beginning of date selector
September 2025
October 2025
November 2025
December 2025
Monday, September 15, 2025
- 9:00 AM1hDS Ph.D. Dissertation Proposal Defense | Ruofan Hu | Monday, Sept. 15 @ 9:00amDATA SCIENCEPhD Dissertation Proposal DefenseRuofan Hu Time: Sep 15, 2025, from 9:00- 10:00 amLocation: Gordon Library Conference Room 303PhD Committee:Prof. Elke A. Rundensteiner, Data Science, WPI. Advisor.Prof. Randy Paffenroth, Mathematical Sciences, WPI.Prof. Fabricio Murai, Data Science, WPI.Prof. Feifan Liu, Population and Quantitative Health Sciences, UMass Chan Medical School. External member. Title: Learning from Weak SupervisionAbstract: Deep learning models often rely on high-quality labeled data, yet such resources are scarce and costly in domains like public health and healthcare. This dissertation addresses the problem of learning from weak supervision, where labels are noisy, incomplete, or coarse. This dissertation focuses on two major regimes: noisy supervision, which involves developing strategies to learn effectively from mixed- and unknown-quality labels, and indirect supervision, which entails designing methods that leverage coarse-grained signals to guide fine-grained tasks, such as rationale extraction and clinical notes summarization. Across four tasks, novel approaches are proposed to reduce dependence on expert annotations, mitigate label noise and imbalance, and exploit existing high-level signals. This work contributes to the development of robust, scalable models that enhance clinical decision support and medical text understanding.
- 9:00 AM1hDS Ph.D. Dissertation Proposal Defense | Ruofan Hu | Monday, Sept. 15 @ 9:00amDATA SCIENCEPhD Dissertation Proposal DefenseRuofan Hu Time: Sep 15, 2025, from 9:00- 10:00 amLocation: Gordon Library Conference Room 303PhD Committee:Prof. Elke A. Rundensteiner, Data Science, WPI. Advisor.Prof. Randy Paffenroth, Mathematical Sciences, WPI.Prof. Fabricio Murai, Data Science, WPI.Prof. Feifan Liu, Population and Quantitative Health Sciences, UMass Chan Medical School. External member. Title: Learning from Weak SupervisionAbstract: Deep learning models often rely on high-quality labeled data, yet such resources are scarce and costly in domains like public health and healthcare. This dissertation addresses the problem of learning from weak supervision, where labels are noisy, incomplete, or coarse. This dissertation focuses on two major regimes: noisy supervision, which involves developing strategies to learn effectively from mixed- and unknown-quality labels, and indirect supervision, which entails designing methods that leverage coarse-grained signals to guide fine-grained tasks, such as rationale extraction and clinical notes summarization. Across four tasks, novel approaches are proposed to reduce dependence on expert annotations, mitigate label noise and imbalance, and exploit existing high-level signals. This work contributes to the development of robust, scalable models that enhance clinical decision support and medical text understanding.
- 9:00 AM1hDS Ph.D. Dissertation Proposal Defense | Ruofan Hu | Monday, Sept. 15 @ 9:00amDATA SCIENCEPhD Dissertation Proposal DefenseRuofan Hu Time: Sep 15, 2025, from 9:00- 10:00 amLocation: Gordon Library Conference Room 303PhD Committee:Prof. Elke A. Rundensteiner, Data Science, WPI. Advisor.Prof. Randy Paffenroth, Mathematical Sciences, WPI.Prof. Fabricio Murai, Data Science, WPI.Prof. Feifan Liu, Population and Quantitative Health Sciences, UMass Chan Medical School. External member. Title: Learning from Weak SupervisionAbstract: Deep learning models often rely on high-quality labeled data, yet such resources are scarce and costly in domains like public health and healthcare. This dissertation addresses the problem of learning from weak supervision, where labels are noisy, incomplete, or coarse. This dissertation focuses on two major regimes: noisy supervision, which involves developing strategies to learn effectively from mixed- and unknown-quality labels, and indirect supervision, which entails designing methods that leverage coarse-grained signals to guide fine-grained tasks, such as rationale extraction and clinical notes summarization. Across four tasks, novel approaches are proposed to reduce dependence on expert annotations, mitigate label noise and imbalance, and exploit existing high-level signals. This work contributes to the development of robust, scalable models that enhance clinical decision support and medical text understanding.
- 9:00 AM1hDS Ph.D. Dissertation Proposal Defense | Ruofan Hu | Monday, Sept. 15 @ 9:00amDATA SCIENCEPhD Dissertation Proposal DefenseRuofan Hu Time: Sep 15, 2025, from 9:00- 10:00 amLocation: Gordon Library Conference Room 303PhD Committee:Prof. Elke A. Rundensteiner, Data Science, WPI. Advisor.Prof. Randy Paffenroth, Mathematical Sciences, WPI.Prof. Fabricio Murai, Data Science, WPI.Prof. Feifan Liu, Population and Quantitative Health Sciences, UMass Chan Medical School. External member. Title: Learning from Weak SupervisionAbstract: Deep learning models often rely on high-quality labeled data, yet such resources are scarce and costly in domains like public health and healthcare. This dissertation addresses the problem of learning from weak supervision, where labels are noisy, incomplete, or coarse. This dissertation focuses on two major regimes: noisy supervision, which involves developing strategies to learn effectively from mixed- and unknown-quality labels, and indirect supervision, which entails designing methods that leverage coarse-grained signals to guide fine-grained tasks, such as rationale extraction and clinical notes summarization. Across four tasks, novel approaches are proposed to reduce dependence on expert annotations, mitigate label noise and imbalance, and exploit existing high-level signals. This work contributes to the development of robust, scalable models that enhance clinical decision support and medical text understanding.
- 3:00 PM50mProfessor David Cyganski presents “Unraveling Quantum Mechanics into a Realistic and Ballistic Theory”Ludwig Boltzmann was unsatisfied with fluid theory (Navier-Stokes Eq., etc.) as it lacked a microscopic theory that could explain the irreversibility at the core of thermodynamics. He committed himself to show how the disbelieved notion of atoms could unravel fluid dynamics into a stochastic particle theory. This talk is about my research program to similarly find a microscopic and ballistic theory of “particles” that generates quantum mechanics, while staying within the guard rails of Einstein’s notion of “realism”. We will visit several less traveled areas of quantum theory and mathematics while following a path to this goal and end with a demonstration of a computational demonstration.David Cyganski Professor Emeritus, Electrical and Computer Engineering, RBE - WPIAll Faculty and students are welcome and encouraged to join us! Physics Department Room 218
- 3:00 PM50mProfessor David Cyganski presents “Unraveling Quantum Mechanics into a Realistic and Ballistic Theory”Ludwig Boltzmann was unsatisfied with fluid theory (Navier-Stokes Eq., etc.) as it lacked a microscopic theory that could explain the irreversibility at the core of thermodynamics. He committed himself to show how the disbelieved notion of atoms could unravel fluid dynamics into a stochastic particle theory. This talk is about my research program to similarly find a microscopic and ballistic theory of “particles” that generates quantum mechanics, while staying within the guard rails of Einstein’s notion of “realism”. We will visit several less traveled areas of quantum theory and mathematics while following a path to this goal and end with a demonstration of a computational demonstration.David Cyganski Professor Emeritus, Electrical and Computer Engineering, RBE - WPIAll Faculty and students are welcome and encouraged to join us! Physics Department Room 218
- 3:00 PM50mProfessor David Cyganski presents “Unraveling Quantum Mechanics into a Realistic and Ballistic Theory”Ludwig Boltzmann was unsatisfied with fluid theory (Navier-Stokes Eq., etc.) as it lacked a microscopic theory that could explain the irreversibility at the core of thermodynamics. He committed himself to show how the disbelieved notion of atoms could unravel fluid dynamics into a stochastic particle theory. This talk is about my research program to similarly find a microscopic and ballistic theory of “particles” that generates quantum mechanics, while staying within the guard rails of Einstein’s notion of “realism”. We will visit several less traveled areas of quantum theory and mathematics while following a path to this goal and end with a demonstration of a computational demonstration.David Cyganski Professor Emeritus, Electrical and Computer Engineering, RBE - WPIAll Faculty and students are welcome and encouraged to join us! Physics Department Room 218
- 3:00 PM50mProfessor David Cyganski presents “Unraveling Quantum Mechanics into a Realistic and Ballistic Theory”Ludwig Boltzmann was unsatisfied with fluid theory (Navier-Stokes Eq., etc.) as it lacked a microscopic theory that could explain the irreversibility at the core of thermodynamics. He committed himself to show how the disbelieved notion of atoms could unravel fluid dynamics into a stochastic particle theory. This talk is about my research program to similarly find a microscopic and ballistic theory of “particles” that generates quantum mechanics, while staying within the guard rails of Einstein’s notion of “realism”. We will visit several less traveled areas of quantum theory and mathematics while following a path to this goal and end with a demonstration of a computational demonstration.David Cyganski Professor Emeritus, Electrical and Computer Engineering, RBE - WPIAll Faculty and students are welcome and encouraged to join us! Physics Department Room 218
- 3:00 PM50mProfessor David Cyganski presents “Unraveling Quantum Mechanics into a Realistic and Ballistic Theory”Ludwig Boltzmann was unsatisfied with fluid theory (Navier-Stokes Eq., etc.) as it lacked a microscopic theory that could explain the irreversibility at the core of thermodynamics. He committed himself to show how the disbelieved notion of atoms could unravel fluid dynamics into a stochastic particle theory. This talk is about my research program to similarly find a microscopic and ballistic theory of “particles” that generates quantum mechanics, while staying within the guard rails of Einstein’s notion of “realism”. We will visit several less traveled areas of quantum theory and mathematics while following a path to this goal and end with a demonstration of a computational demonstration.David Cyganski Professor Emeritus, Electrical and Computer Engineering, RBE - WPIAll Faculty and students are welcome and encouraged to join us! Physics Department Room 218