From awd at cs.cmu.edu  Mon Apr  7 17:11:17 2025
From: awd at cs.cmu.edu (Artur Dubrawski)
Date: Mon, 7 Apr 2025 17:11:17 -0400
Subject: Fwd: RI Ph.D. Thesis Defense: Mononito Goswami
In-Reply-To: <CAPfXyx+8DP9cGNDTBx_hJOJ_wSvKfDBm924LvxprBX7=5CGOtg@mail.gmail.com>
References: <CAPfXyx+8DP9cGNDTBx_hJOJ_wSvKfDBm924LvxprBX7=5CGOtg@mail.gmail.com>
Message-ID: <CAJvAoysRrrb1M1H038v5j4+-1Tq86_TjYM5Zo7t_tWMDOen1yQ@mail.gmail.com>

Please mark your calendars and join Mononito at this big event. It promises
to be an intellectual treat.

Cheers,
Artur

---------- Forwarded message ---------
From: Suzanne Muth <lyonsmuth at cmu.edu>
Date: Mon, Apr 7, 2025, 4:39?PM
Subject: RI Ph.D. Thesis Defense: Mononito Goswami
To: RI People <ri-people at andrew.cmu.edu>


*RI Events Calendar Posting
<https://www.ri.cmu.edu/event/towards-pragmatic-time-series-intelligence-2/>*

*Date:* Thursday, 17 April 2025
*Time:* 4:30 p.m. (ET)
*Location:* CIC LL06 (see attached figure)
*Zoom Link:*
https://cmu.zoom.us/j/91581272900?pwd=DCOr0EFMMTuAncqaeJvNJgw9W8Xsqb.1&jst=2
*Type:* Ph.D. Thesis Defense
*Who:* Mononito Goswami
*Title:* Towards Pragmatic Time Series Intelligence

*Abstract:*
This thesis aims to democratize time series intelligence by making advanced
modeling capabilities accessible to users without specialized machine
learning knowledge. We pursue this goal through three complementary
contributions that build foundation models, improve our understanding of
them, and address challenges emerging in their practical use.

We start by introducing MOMENT, the first family of open source time series
foundation models capable of performing well on a variety of tasks on data
from diverse domains with minimal supervision. We extend these models to
handle long multivariate contexts and integrate multimodal data, enabling
their application to complex real-world scenarios where traditional
approaches fall short.

Next, we examine what these foundation models learn by investigating their
compositional reasoning abilities, representation structures, and encoded
concepts. We identify practical insights that improve both our
understanding of the models and their performance.

Then, we tackle deployment challenges by developing methods to learn from
distributed unlabeled data, assess label quality, and select robust models
when labeled data is scarce. Lastly, we explore how Large Language Model
agents can automate the time series intelligence engineering process, using
open-source tools and tools developed in this thesis.

We demonstrate the utility of our methodology in clinical settings, where
time series data is plentiful and where modeling of it can be impactful. We
conclude that specialized foundation models, combined with practical tools
supporting their real-world deployment, can substantially advance time
series intelligence and yield practical solutions of societal importance.

*Thesis Committee Members:*
Artur Dubrawski (Chair)
Jean Oh
Barnab?s P?czos
Frederic Sala (University of Wisconsin-Madison)
Laurent Callot (Amazon)

Draft of the Thesis Document
<https://drive.google.com/drive/folders/1yzdjxg0Koj92msch3kRxJDemi29E9Snj?usp=sharing>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20250407/17593f5e/attachment-0001.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: CIC Location_LL06 Lower Level.png
Type: image/png
Size: 271016 bytes
Desc: not available
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20250407/17593f5e/attachment-0001.png>

From awd at cs.cmu.edu  Tue Apr 15 19:59:56 2025
From: awd at cs.cmu.edu (Artur Dubrawski)
Date: Tue, 15 Apr 2025 19:59:56 -0400
Subject: Fwd: 5th Year MS thesis Presentation Rohini Banerjee
In-Reply-To: <CAA_yqEpcTprX9o-ofpzuJKxxXb5ZW-Zyz9AMcxJgqmQ0GCkj1g@mail.gmail.com>
References: <CAA_yqEpcTprX9o-ofpzuJKxxXb5ZW-Zyz9AMcxJgqmQ0GCkj1g@mail.gmail.com>
Message-ID: <CAJvAoysJu6nnxP-AAc_gN69W9YmYnV_H8rS=gu7_rHjSeL5YZg@mail.gmail.com>

fysa, Rohini's MS defense is on Tuesday next week.

Cheers,
Artur

---------- Forwarded message ---------
From: Tracy Farbacher <tt1b at andrew.cmu.edu>
Date: Tue, Apr 15, 2025 at 7:18?PM
Subject: 5th Year MS thesis Presentation Rohini Banerjee





*Rohini BanerjeeTuesday, April 22, 20253:00 PMNewell Simon Hall (NSH)
3001Uncertainty-Aware AI for Clinical Decision Support*

*Abstract:*
Building interpretable-by-design AI models that intuitively communicate
model uncertainty is vital to engendering physician and patient trust. We
develop uncertainty-guided deep learning systems for two pertinent
healthcare settings. Efficient intravascular access in trauma and critical
care is a high-stakes intervention affording minimal tolerance for error.
Autonomous needle insertion systems can be useful in austere environments
due to the lack of skilled medical personnel. However, inaccuracies in
vessel segmentation modeling can result in vessel damage and hemorrhage.
The risk can be mitigated via predictive uncertainty estimation to assess
model reliability. Thus, we introduce MSU-Net, a novel multistage approach
to semantic vessel segmentation in ultrasound images that combines the
predictive power of Monte Carlo networks and deep ensembles. We demonstrate
significant improvements, 27.7% over the state-of-the-art, while enhancing
model reliability through a 20.9% stronger discrimination in epistemic
uncertainty between correct and incorrect predictions.

Next, we investigate the robustness of predictive modeling in quantifying
the severity of rash manifestations associated with Cutaneous
Dermatomyositis (CDM), a rare and currently incurable autoimmune disorder.
Given the importance of telemedicine for remote disease monitoring and
timely intervention, we address challenges of data scarcity and patient
diversity by integrating a novel BERT-style self-supervised learning (SSL)
framework to image-based models. Pretrained via masked image modeling on
demographically diverse images, our model achieves over a 40% improvement
in fine-tuning performance on high-resolution in-clinic hand images from a
limited cohort of 23 CDM patients. We achieve 83% accuracy on a held-out
patient set, surpassing the clinical benchmark of 70?75% accuracy. To our
knowledge, this is the first work to integrate uncertainty estimation into
such architectures, enabling robustness under distributional shift in skin
tone unseen during fine-tuning.

Our contributions lay the groundwork for developing accurate, statistically
rigorous, clinically actionable deep learning models. Future work aims to
improve the interpretability of models for equitable clinical decision
support.

*Thesis Document:*
https://drive.google.com/file/d/1TnC6IcyDmTD6IzBpaSKsIsQX1f8Bkl0K/view?usp=sharing

*Thesis Committee:*
Artur W. Dubrawski (Chair)
L?szl? A. Jeni
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20250415/cfdec8c5/attachment-0001.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: Rohini Banerjee Thesis.pdf
Type: application/pdf
Size: 144502 bytes
Desc: not available
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20250415/cfdec8c5/attachment-0001.pdf>

From awd at cs.cmu.edu  Wed Apr 16 10:30:42 2025
From: awd at cs.cmu.edu (Artur Dubrawski)
Date: Wed, 16 Apr 2025 10:30:42 -0400
Subject: Fwd: [Location Change to NSH 4305] RI Ph.D. Thesis Defense: Mononito
 Goswami
In-Reply-To: <CAPfXyxJBNn5H2p53N9mZk+ikmsR+rHx7p45Z9JKstQw6p4uUZw@mail.gmail.com>
References: <CAPfXyx+8DP9cGNDTBx_hJOJ_wSvKfDBm924LvxprBX7=5CGOtg@mail.gmail.com>
 <CAPfXyxJBNn5H2p53N9mZk+ikmsR+rHx7p45Z9JKstQw6p4uUZw@mail.gmail.com>
Message-ID: <CAJvAoysTGBAsaLK+VrXTFrt9Z2JkPLZhvDq1ALpaiqx7L3d-Yw@mail.gmail.com>

Mono's defense will happen closer to the Auton Wing.

See you all there tomorrow!
(4:30pm, NSH 4305)

Cheers
Artur

---------- Forwarded message ---------
From: Suzanne Muth <lyonsmuth at cmu.edu>
Date: Wed, Apr 16, 2025 at 9:45?AM
Subject: [Location Change to NSH 4305] RI Ph.D. Thesis Defense: Mononito
Goswami
To: RI People <ri-people at andrew.cmu.edu>


This talk will take place in *NSH 4305* on April 17th beginning at 4:30pm.


> *RI Events Calendar Posting
> <https://www.ri.cmu.edu/event/towards-pragmatic-time-series-intelligence-2/>*
>
> *Date:* Thursday, 17 April 2025
> *Time:* 4:30 p.m. (ET)
> *Location:* NSH 4305
> *Zoom: Link
> <https://cmu.zoom.us/j/91581272900?pwd=DCOr0EFMMTuAncqaeJvNJgw9W8Xsqb.1&jst=2>*
>
> *Type:* Ph.D. Thesis Defense
> *Who:* Mononito Goswami
> *Title:* Towards Pragmatic Time Series Intelligence
>
> *Abstract:*
> This thesis aims to democratize time series intelligence by making
> advanced modeling capabilities accessible to users without specialized
> machine learning knowledge. We pursue this goal through three complementary
> contributions that build foundation models, improve our understanding of
> them, and address challenges emerging in their practical use.
>
> We start by introducing MOMENT, the first family of open source time
> series foundation models capable of performing well on a variety of tasks
> on data from diverse domains with minimal supervision. We extend these
> models to handle long multivariate contexts and integrate multimodal data,
> enabling their application to complex real-world scenarios where
> traditional approaches fall short.
>
> Next, we examine what these foundation models learn by investigating their
> compositional reasoning abilities, representation structures, and encoded
> concepts. We identify practical insights that improve both our
> understanding of the models and their performance.
>
> Then, we tackle deployment challenges by developing methods to learn from
> distributed unlabeled data, assess label quality, and select robust models
> when labeled data is scarce. Lastly, we explore how Large Language Model
> agents can automate the time series intelligence engineering process, using
> open-source tools and tools developed in this thesis.
>
> We demonstrate the utility of our methodology in clinical settings, where
> time series data is plentiful and where modeling of it can be impactful. We
> conclude that specialized foundation models, combined with practical tools
> supporting their real-world deployment, can substantially advance time
> series intelligence and yield practical solutions of societal importance.
>
> *Thesis Committee Members:*
> Artur Dubrawski (Chair)
> Jean Oh
> Barnab?s P?czos
> Frederic Sala (University of Wisconsin-Madison)
> Laurent Callot (Amazon)
>
> Draft of the Thesis Document
> <https://drive.google.com/drive/folders/1yzdjxg0Koj92msch3kRxJDemi29E9Snj?usp=sharing>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20250416/61fa3cc5/attachment.html>

From youngsec at andrew.cmu.edu  Mon Apr 21 11:31:26 2025
From: youngsec at andrew.cmu.edu (Youngseog Chung)
Date: Mon, 21 Apr 2025 11:31:26 -0400
Subject: Full scratch on GPU16
Message-ID: <CAAyLgL53x3hjxdk+kie6bz0gkHgP51Qn0+ROPUWVxbD+hr+L=g@mail.gmail.com>

Hi everyone,

The scratch space on GPU16 is 100% full.

Please help clearing out any large files you don't need.


Best,
Youngseog
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20250421/da332a86/attachment.html>