Optimization and Trustworthy Machine Learning (OPTML) @ MSU Director: Dr. Sijia Liu Direction: optimization theory, trustworthy and scalable machine learning
East Lansing, MI
- Tweets 6
- Following 5
- Followers 17
- Likes 2
OPTML @MSU retweeted
📢We're thrilled to present our #CVPR23 work during the poster session #253 Thu morning. Come and see the interpretability and advancement in visual prompting! @sijialiu17 @OptML_MSU @pinyuchenTW @MITIBMLab
What is the challenge of (visual) prompting (a kind of parameter-efficient fine-tuning) in the vision domain? Our new #CVPR23 paper "Understanding and Improving Visual Prompting: A Label-Mapping Perspective" makes an effort to resolve the existing label mapping issue.
4
6
2,139
💡Excited for a deep dive into the remarkable synergy of text-visual prompting enhancing 2D temporal video grounding 🖼️, presented by @damon19950223 @sijialiu17 @IntelAI See you tomorrow afternoon at session #233!
📢We're thrilled to present our #CVPR23 work during the poster session #233 Wed afternoon. Curious about how to enhance 2D temporal video grounding performance? Discover the power of text-visual prompting! 🚀 Project page: optml-group.com/posts/2dtvp_…. @sijialiu17 @OptML_MSU @IntelAI
1
64
OPTML @MSU retweeted
🚀Unveil & tackle IRM challenges at #ICLR2023! We address long-overlooked challenges in IRM training and evaluation & unlock IRM with the consensus-constrained bi-level optimization! Don't miss our poster session📌MH1-2-3-4 #20, Wed, 4:30-6:30 pm CAT🌟 arxiv.org/abs/2303.02343
2
2
4
1,549
OPTML @MSU retweeted
Is 5-min slideslive video too short to know our work? Check out this video (piped.video/eeKITiOOTaE) and find more details on our Bi-Level Pruning algorithm! #NeurIPS2022
Paper: arxiv.org/abs/2210.04092
Code: github.com/OPTML-Group/BiP
Look forward to meeting you in New Orleans.
Excited to share our work accepted by #NeurIPS2022 @NeurIPSConf! This is an amazing attempt to advance pruning through bi-level optimization with 2~7× speedup over IMP for the same level of model accuracy and sparsity.
Paper: arxiv.org/pdf/2210.04092.pdf
Code: github.com/OPTML-Group/BiP
1
2
OPTML @MSU retweeted
Excited to share our work accepted by #NeurIPS2022 @NeurIPSConf! This is an amazing attempt to advance pruning through bi-level optimization with 2~7× speedup over IMP for the same level of model accuracy and sparsity.
Paper: arxiv.org/pdf/2210.04092.pdf
Code: github.com/OPTML-Group/BiP
2
1
5
OPTML @MSU retweeted
So happy to receive the NeurIPS 2022 Scholar Award and Top Reviewer! Thanks for the acknowledgement from @NeurIPSConf, which would be a great encouragement to my research.
Look forward to seeing you in New Orleans and I will share two papers at the poster session!
#NeurIPS2022
2
1
7