This is the Twitter handle for CARAML Lab at UTD. CARAML Lab is led by Prof. Rishabh Iyer (https://nitter.cf/t.co/7JfCUsXu1m).
Joined October 2021
- Tweets8
- Following23
- Followers71
- Likes3
Caraml Lab retweeted
Can we talk about how inconvenient it has gotten to get a visa for Chinese students? It’s been 3 weeks since mine was “refused”.
Is there any reason me, in my 2nd yr Stanford PhD, must wait for up to 180 days to be considered safe to be let in the US?
We are happy to announce MILO: Model-agnostic subset selection for Efficient Training and Tuning. MILO achieves an impressive 3x-10x faster training and a whooping 20x-75x faster hyper-parameter tuning.
🚀 (1/6) Exciting News! Introducing MILO, our revolutionary Model Agnostic Subset Selection Framework! It can optimize your model training & tuning, accelerating your #NeuralNetworks training by 3x-10x and supercharging your hyper-parameter tuning by an incredible 20x - 75x.
Caraml Lab retweeted
📢Join us at the #AAAI22 poster session for our paper
A Nested Bi-Level Optimization Framework for Robust Few Shot Learning
Poster Session 5,10@Red 4
📅Fri, Feb 25th, 4:45 PM - 06:30 PM (PST)
📅Sun, Feb 27th, 8:45 AM - 10:30 AM (PST)
🔗Session Link: tinyurl.com/22h3tuu6
1/4
Caraml Lab retweeted
📢Looking for data subset selection functions that can be customized as per your requirements? #AAAI2022
We present PRISM: A Rich Class of Parameterized Submodular Information Measures for Guided Subset Selection
📰Paper : arxiv.org/pdf/2103.00128.pdf
1/N
Caraml Lab retweeted
This is a great initiative! Advanves in NAS, automl, hyoer param tuning is critical these days for large scale ML!
Exciting news: following a series of 8 AutoML workshops at ICML, we will hold the 1st International Conference on AutoML in 2022. Co-located with ICML, 3 days, currently planned in person. Website: automl.cc Submission deadline: Feb 24, 2022 #AutoML #AutoML_Conf 1/
Caraml Lab retweeted
Nice work by my student @surajkothawade and several amazing folks at @NVIDIAAI! Very important problem and a nice clean solution!
📢 Looking for an effective way to mine data similar to a region of interest? #NeurIPS2021
Visit our Spotlight talk titled "Object-Level Targeted Selection via Deep Template Matching" at the NeurIPS 2021 Workshop on Machine Learning for Autonomous Driving!
1/N
Caraml Lab retweeted
Excited to be presenting SIMILAR, our recent work on active learning in imbalance & rare classes, out of distribution data, and redundancy using the Submodular Info Measures at #NeurIPS2021!
Please join us for our poster session in roughly 2 hours!
See the tweet below👇
📢Looking for a one-stop solution for active learning on real-world datasets? #NeurIPS2021
We present SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarios.
📅Poster Session: Fri 10 Dec 8:30 a.m. PST — 10 a.m. PST
1/N
Caraml Lab retweeted
Excited to be presenting our work RETRIEVE at #NeurIPS2021. See details below!
A summary of the paper is in our latest blog post: caraml-lab.medium.com/retrie…
Joint work with @krishnatejakk, Xujiang Zhou and Feng Chen!
📢Join us at the #NeurIPS21 poster session for our paper
*RETRIEVE: Coreset Selection for Efficient and Robust Semi-Supervised Learning*
📅 Poster Session: Wed Dec 08 12:30-02:00 AM (PST)
🎙️ Talk: neurips.cc/virtual/2021/post…
📰 Paper: openreview.net/forum?id=jSz5…
