Lingkai Kong
@konglingkai_AI
Postdoc @Harvard. Ph.D. @GeorgiaTech. Generative AI, Uncertainty Quantification, AI4Social Good.
You may already be amazed by diffusion models for generating images and videos—but did you know they can also help wildlife conservation🐘? We propose DiffOracle, combining diffusion models & game theory to stop poaching! Arxiv: arxiv.org/abs/2503.05730
Unfortunately, I cannot make NeurIPS this year, but I will be around Seattle starting later this week! So if anyone stops by Seattle before or after NeurIPS, ping me to catch up! My excellent collaborators will also present three papers (includ. one spotlight) @NeurIPSConf!
Excited to present our paper at #UAI2025 on Thursday 🇧🇷 Can we predict which datasets transfer best when downstream decisions, not just predictions, matter? Can we know this before learning? We introduce OTD³, a new dataset distance for PtO tasks arxiv.org/pdf/2409.06997
Absolutely thrilled to be able host this alumni dinner for our Teamcore research group at #AAAI2025. It was (and it continues to be) an honor to have mentored so many professors! And it is fantastic to see everyone's progress in their careers.
Afterall, DiffOPT is accepted in @aistats_conf 2025! Generative priors are natural for optimization esp. formulated as sampling! We also extend to derivative-free settings. Great work with @konglingkai_AI and Wenhao!
🧵1/6 Introducing Diffusion Constrained Samplers 🥳🥳🥳 arxiv.org/abs/2402.18012 Interested in optimization problems where (partial) constraints are unknown (protein/molecule design)? We show diffusion models learn it implicitly and optimize feasible solutions thru sampling!
📢📢📢 Happy to introduce Graph Generative Pre-trained Transformers (G2PT): Can we tokenize graphs and train an autoregressive (AR) model with generative pre-trained transformers to generate graphs? A new work led by @XiaohuiC16528, @YinkaiW, @jacksonleihao. A thread 🧵1/6
So fantastic to have @konglingkai_AI as a postdoc with us at @hseas. Excited for all our research collaboration!
The Ph.D. ceremony for Fall Commencement is only hours away! 🎓🥳 Meet one of our graduates, Lingkai Kong, who is now a postdoc at @Harvard where uses his CSE degree to help counter poaching in Africa and improve healthcare access in India! 📰🔗👇 cc.gatech.edu/news/alumnus-u…
The interdisciplinary environment at @GTCSE has profoundly shaped my research philosophy. I am deeply grateful to my postdoc advisor @MilindTambe_AI for providing me with the opportunity to work on these amazing projects that contribute to society!
The Ph.D. ceremony for Fall Commencement is only hours away! 🎓🥳 Meet one of our graduates, Lingkai Kong, who is now a postdoc at @Harvard where uses his CSE degree to help counter poaching in Africa and improve healthcare access in India! 📰🔗👇 cc.gatech.edu/news/alumnus-u…
#NeurIPS I’m on the 2024-25 job market, seeking faculty positions and postdoc opportunities! My research focuses on Bayesian Deep Learning, Spatiotemporal Modeling, and Scientific ML, with applications in public health, climate science, and drug discovery. dongxiaw.github.io/online-cv/
Happy to share RE-Control is accepted to #NeurIPS2024!
1/n Want to align your LLM with human objectives but lack the computing resources for fine-tuning?😭😭 We propose RE-Control, which aligns LLMs through representation editing (RE) from a control perspective!🤩🤩 Arxiv: arxiv.org/pdf/2406.05954 Code: github.com/Lingkai-Kong/R…
🧵1/6 Happy to introduce ChemFlow: Navigating Chemical Space with Latent Flows arXiv: arxiv.org/abs/2405.03987 Demos are available at: colab.research.google.com/drive/1QAy_QoE… Flows can uncover meaningful structures of latent spaces learned by generative models!