ML@RPTU

We are the Machine Learning group at RPTU!

[ML@RPTU @mlrptu]

We also thank everyone who attended the workshop and submitted their papers. Check out all the accepted papers and details here: https://t.co/XXy9q45Fe1 📚👨‍🔬

#ML4CCE #ECML2024 #AI #MachineLearning #ChemicalEngineering #Innovation #Research #TechTalks

[ML@RPTU @mlrptu]

🚀 We had an incredible time hosting the ML4CCE Workshop at @ECMLPKDD 2024! 💡🔬 Experts from machine learning and chemical engineering came together to explore exciting topics like molecular design, process control, and anomaly detection, among others. 🎓✨

[ML@RPTU @mlrptu]

Special thanks to our Keynote speakers: Venkat Venkatasubramanian (@ProfVenkat7), Dominik Grimm (@dg_grimm), and Felix Strieth-Kalthoff (@felix_s_k) for their incredible talks and insights! 🎤👏 Their contributions made the event truly memorable.

[ML@RPTU @mlrptu]

@Saurabh37965589 @purvanshi_mehta @waleedamustafa Authors: S. Varshneya (@SaurabVarshneya), A. Ledent, P. Liznerski, A. Balinskyy, P. Mehta (@purvanshi_mehta), W. Mustafa (@waleedamustafa), and M. Kloft.

[ML@RPTU @mlrptu]

🎉 Excited to announce our two papers accepted at IJCAI 2024 (@IJCAIconf):

The papers tackle crucial challenges in language understanding and multimodal learning.

We will be presenting them at the conference.
#IJCAI2024 #AI #NLP #MultimodalLearning

[ML@RPTU @mlrptu]

Authors:
C. James, M. Nagda (@MayankNagda35), N. Ghassemi, M. Kloft, and S. Fellenz (@sophieImWeb2_0)

[ML@RPTU @mlrptu]

🎉 Thrilled to announce that our paper is accepted at ACL 2024 @aclmeeting @aclanthology #acl2024 #NLProc:

[ML@RPTU @mlrptu]

"Evaluating Dynamic Topic Models"

📝 We propose a novel evaluation measure for DTMs analyzing topic quality changes over time. This extension combines topic quality with temporal consistency, aiding in identifying changing topics and guiding future research.

[ML@RPTU @mlrptu]

2. "Numerically Tight Generalization Bounds for Adversarial Risk in Stochastic Neural Networks" by W. Mustafa et al.

📝 Our novel generalization bounds predict model performance and robustness on unseen data in adversarial settings.

[ML@RPTU @mlrptu]

🎉 Excited to share our two papers that were presented at AISTATS 2024 (@aistats_conf):

#AISTATS2024 #AI #ML #RL

[ML@RPTU @mlrptu]

📝 In this paper, we dynamically adapt RL agents' behavior for moral decision-making by incorporating moral scores into the training objective. Findings highlight trade-offs between immoral behavior and performance.

[ML@RPTU @mlrptu]

📝 "Interpretable Tensor Fusion" introduces InTense, a multimodal learning method providing interpretability by disentangling data representations and their fusion.

[ML@RPTU @mlrptu]

2. "Interpretable Tensor Fusion"

Authors: S. Varshneya, A. Ledent, P. Liznerski, A. Balinskyy, P. Mehta, W. Mustafa, and M. Kloft.

[ML@RPTU @mlrptu]

checkout our full work: https://t.co/ABTrlQgZvw.
Authors: Phil Ostheimer (@PhilOstheimer), Mayank Nagda (@MayankNagda35), Marius Kloft, Sophie Fellenz (@sophieImWeb2_0)

[ML@RPTU @mlrptu]

📝 Text Style Transfer Evaluation Using Large Language Models. Presenting findings at #LREC-#COLING 2024. Our study explores LLMs' potential in TST assessment, revealing promising correlations with human evaluations. A new avenue for TST assessment emerges. #NLProc #AI

[ML@RPTU @mlrptu]

#ML #ECMLPKDD2024 @ECMLPKDD

[Sophie Burkhardt @sophieImWeb2_0]

We are excited to present the 1st Workshop on Machine Learning for Chemistry and Chemical Engineering @ECMLPKDD
in Vilnius on September 9th. Submit papers until June 15th! https://t.co/Bi5CqpUzAa @GloriusFrank @StephanMandt @P_Friederich @AlexanderMitsos

[ML@RPTU @mlrptu]

🎮Check out the paper "Ordinal Regression for Difficulty Estimation of StepMania Levels": https://t.co/ev2Y2SfFrD📄Explore the code here: https://t.co/ZmEM5D2fpe 💻 and see a practical use case in action: https://t.co/C98pS7lqYr 🚀 #MachineLearning #Gaming #AI #DDR

[ML@RPTU @mlrptu]

🕺 Ready to groove to the perfect beat? Our research tackles the challenge of predicting difficulty levels in StepMania levels as an ordinal regression task with neural network-based models, outperforming the rest! The work will be presented at #ECML . #ECML_2023