Chandan Reddy

I'll be at #ICML2025 presenting our LLM-SRBench: A New Benchmark for Scientific Equation Discovery with LLMs (on July 17)! Feel free to stop by or ping me for a chat! Oral (Session 5D) at 10:15 AM and Poster(W-115) at 11 AM. openreview.net/forum?id=SyQPi…

I'll be at #ICLR2025 presenting our work on LLM-SR — symbolic regression with LLMs for scientific discovery (Apr 25)! Feel free to stop by or ping me for a chat! Oral at 4 PM (Session 4B); Poster #617 at 10 AM (Session 3). 🔗 openreview.net/forum?id=m2nmp… #AI #LLM #AIforScience #ML

Thanks to NSF for funding our work on developing machine learning techniques for healthcare. @V_Subbian #NSFfunded #machinelearning #healthcare bit.ly/2FEsSdt

🚨 New paper accepted at COLM 2025! 🚨 Excited to share that "FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning"—a project from my internship at Amazon—has been accepted to #COLM2025! @COLM_conf

🚨 New ICML 2025 Spotlight Paper! 🚨 LLM-SRBench provides a new standard for symbolic regression with LLMs 🧠 📊 239 tasks across physics, chemistry, biology & materials 🔍 Tests true reasoning—not memorization Paper: arxiv.org/pdf/2504.10415 #ICML2025 #AI4Science #LLMs #ML

Can reasoning reduce bias in language models? Turns out — yes. We introduce ReGiFT, a simple yet powerful way to transfer fairness by leveraging reasoning traces. Paper: arxiv.org/abs/2504.05632 #AI #LLM #NLP #Fairness #BiasMitigation

Thrilled that "Self-Supervised Hyperboloid Representations from Logical Queries over Knowledge Graphs" with @nikhilrao86 @sumeetwisc Karthik Subbian @chandankreddy got accepted at The Web Conference. #TheWebConf2021 #www2021 Preprint: arxiv.org/abs/2012.13023

When data annotation is an issue, we should build approaches that leverage unlabeled samples effectively. Check out our work on building semi-supervised deep learning models and their applications to transportation problems #DeepLearning #Transportation dmkd.cs.vt.edu/papers/TKDE19.…

Our survey article on machine learning methods for survival analysis is now published in ACM Computing Surveys. dl.acm.org/citation.cfm?i… #MachineLearning #healthcare Paper: dmkd.cs.vt.edu/papers/CSUR18.… KDD Tutorial website: dmkd.cs.vt.edu/TUTORIAL/Survi… Video: youtube.com/watch?v=GpIk1N…

Our new RSTPP (Recurrent Spatio-Temporal Point Process) model combines the power of point process models and deep learning for spatio-temporal applications. Check out the presentation at #CIKM2018 and the paper dl.acm.org/citation.cfm?i…

Check out our #IJCAI2018 paper on spatio-temporal check-in time prediction models that combine recurrent neural networks with survival analysis @IJCAI_ECAI_18 dmkd.cs.vt.edu/papers/IJCAI18…

Check out our work on summarizing online reviews at #TheWebConf in the session on Web Search and Mining (IV) - "A Sparse Topic Model for Extracting Aspect-Specific Summaries from Online Reviews" dl.acm.org/citation.cfm?i…

Are you interested in analyzing short texts? A Semantics-assisted NMF model will be presented at #TheWebConf "Short-Text Topic Modeling via Non-negative Matrix Factorization Enriched with Local Word-Context Correlations" dl.acm.org/citation.cfm?d…