Auton Lab, Carnegie Mellon

Founded by @awmcmu, Auton Lab, @SCSatCMU is currently lead by Artur Dubrawski & Jeff Schneider. We are interested in all dimensions of Machine Learning and AI.

[Mononito Goswami @MononitoGoswami]

Huge congratulations to my amazing collaborators Yifu Cai, @Arjun_7m, and Dr. Artur Dubrawski at @AutonLab @CMU_Robotics, @SCSatCMU

[Mononito Goswami @MononitoGoswami]

Frontier models like Gemini excel in areas like code and image understanding. But how well do they handle time series reasoning?
(Re-)Introducing TimeSeriesExam, which just won the NeurIPS'24 TSALM Best Paper Honorable Mention🏆

[Arjun Choudhry @Arjun_7m]

Excited to share TimeSeriesExam for systematic evaluation of time series reasoning capabilities of LLMs. Think your LLM can reason on time series concepts? Take it for a spin on the TimeSeriesExam! Now publicly available on HuggingFace :)

[Arjun Choudhry @Arjun_7m]

Heartiest congratulations to our amazing team!
I am applying for PhD positions for Fall 2025. If you see a fit with your lab or interests, or just want to brainstorm on ideas, please DM :)

[Mononito Goswami @MononitoGoswami]

Time Series & Language: A Powerful Pair 📈📉

Loved seeing some recent work time series & text work! It reminded me of our very own work JoLT, one of the first time series and text models !

Want to learn more? Check out JoLT, and our latest paper, on the TimeSeriesExam!

[Ifigeneia Apostolopoulou @ifaposto]

#ICML2024 #ICML

Our new work provides a highly effective and scalable method for enriching deep neural networks to decide whether it has sufficient evidence for reaching a reliable prediction.

Paper 📒 : https://t.co/WGu2dLRUEE
Code 💻: https://t.co/m19mdbrFiD
Poster 📸: https://t.co/OWyvP7JePT

Details Below 🧵

[Deepak Pathak @deepakpathak]

Thrilled to announce @SkildAI! Over the past year, @gupta_abhinav_ and I have been working with our top-tier team to build an AI foundation model grounded in the physical world. Today, we’re taking Skild AI out of stealth with $300M in Series A funding:

https://t.co/1kXo7NrnVr

[Deepak Pathak @deepakpathak]

We’re striving to build the most scalable, robust, and generalizable robotics foundation model. Thank you to our team for all their hard work so far & our investors for believing in our mission. Follow along with us @SkildAI for the latest. Blog: https://t.co/eUwEeVMlTs

[Frank Nielsen @FrnkNlsn]

ICML’24:
“A Rate-Distortion View of Uncertainty Quantification”:
https://t.co/zMwiZfIql4

Distance Aware Bottleneck is a method for enriching deep neural networks to decide whether it has sufficient evidence for reaching a reliable prediction.
@ifaposto @ben_eysenbach Dubrawski

[CMU Robotics Institute @CMU_Robotics]

The Auton Lab has proposed MOMENT: one of the first families of open-source foundation models for time series analysis!

The models serve as a building block for diverse tasks such as forecasting, classification, & anomaly detection.

Learn more: https://t.co/q2rY7FFIi9

[Mononito Goswami @MononitoGoswami]

Exciting news! Just as foundation models revolutionized text and image modeling, it's now time for Time Series Data! Introducing MOMENT, a family of Open Time Series Foundation Models, freshly accepted at @icmlconf 2024! 🎉

[Mononito Goswami @MononitoGoswami]

Excited to present the first day of the @RealAAAI 2024 Spring Symposium on Clinical Foundation Models! 🎊 Today's lineup includes keynotes, a panel discussion, demos, contributed talks, and a poster session!
@clinicalfms

[Valeriy M., PhD, MBA, CQF @predict_addict]

BOOM 💥 The competition in LLM time series space is heating up.

Lag-Llama was making rounds yesterday and some people claimed it was “the first” open source LLM. But it turns out on 6 February before Lag Llama Carnegie Mellon released their own open source LLM “Moment”. 🔥🔥🔥🔥🔥

So MOMENT, not Lag Llama is THE FIRST open source time series LLM. 🚀🚀🚀🚀🚀

“MOMENT: A FAMILY OF OPEN TIME-SERIES FOUNDATION MODELS”

#llm

#timeseries

[Mononito Goswami @MononitoGoswami]

🤖 We have decided to extend the deadline for our @RealAAAI Spring Symposium on Clinical Foundation Models @clinicalfms to Jan 26, 2024 🥳! CfP, timelines, attendance info available at https://t.co/cr4jmfxxmI #ML4H #MLHC

[Mononito Goswami @MononitoGoswami]

🎉Exciting News! Join us for the AAAI-24 Spring Symposium on Clinical Foundation Models! 🚀Explore captivating talks, engaging panels, & cutting-edge demos. All details (CfP, timelines, ...) available at 👉https://t.co/ydKfB8KFF7. Hurry, papers due by Jan 5, 2024 @clinicalfms

[Mononito Goswami @MononitoGoswami]

Tired of reading about Q*?

Want to instead learn about improving the quality of labels in your data?

Then check out our recent NeurIPS D&B paper on benchmarking label error detection tools with AQuA: https://t.co/XWwD19NuNA.

3 reasons why you should check out AQuA: (1/5)

[Auton Lab, Carnegie Mellon @AutonLab]

💻Attention CMU students! 💻

You have one last day to register for the Auton Lab’s 2023 HackAuton!

Please RSVP & join us for a fun weekend of contributing to groundbreaking research while helping shape the future of AI and ML!

https://t.co/T5csGvj9Tu

#hackAuton #AutonLab

[Auton Lab, Carnegie Mellon @AutonLab]

One more week until our Lab’s 30th Anniversary Celebration!

We're excited to celebrate this incredible milestone with you all! Join us to reflect on the Lab's numerous impacts over the years and explore future AI research endeavors.

RSVP @ https://t.co/9OFkDiNY9H

#Auton30 #AI

[Auton Lab, Carnegie Mellon @AutonLab]

We are just 2 WEEKS away from our 30th Anniversary Celebration!

Join us for food & fun while learning about the Lab's impacts so far, current research topics, and future endeavors. Lab Swag will be available at the event for all!

RSVP today @ https://t.co/9OFkDiNqk9

#Auton30

[Auton Lab, Carnegie Mellon @AutonLab]

🎈In light of the Auton Lab’s 30th Birthday coming up, we are also hosting our very own HackAuton the weekend after our 30th Anniversary celebration, from Sept 15th-17th, 2023!🎈
We welcome all CMU students to register!
https://t.co/T5csGviC3W
#Auton30