Assistant Professor@Iowa State, Postdoc @Stanford, PhD@IMPRS-IS
Joined November 2021
- Tweets52
- Following148
- Followers150
- Likes250
Bo Xiong retweeted
🎓 #SWSA Distinguished Dissertation Award 2025 goes to @BoXiongs !
Recognized for his brilliant thesis: “Geometric Relational Embeddings” 🧠
👏 Congrats Bo - see you at #ISWC2025 in #Japan!
#DistinguishedDissertationAward #SemanticWeb #KnowledgeGraphs #AI #ResearchExcellence
Bo Xiong retweeted
SEMMA (transliteration of செம்ம - meaning awesome), my first PhD work, is accepted to #EMNLP2025 Main!
I also found out today that SEMMA has the (tied) highest average reviewer score in this ARR cycle 💪
📜: arxiv.org/abs/2505.20422
Bo Xiong retweeted
Does text help KG Foundation Models generalize better? 🤔
Yes (and no)! ☯️
Bootstrapped by LLMs improving KG relation labels, we show that textual similarity between relations can act as an invariance - helping generalization across datasets! 🧵👇
Bo Xiong retweeted
hi, we found problematic benchmarks in complex query answering as well! arxiv.org/abs/2410.12537 @tetraduzione @Mniepert @c_gregucci @chrsmrrs @michael_galkin
Bo Xiong retweeted
Goodbye ChatGPT
It’s only been 5 days since Deepseek R1 dropped, and the World is already blown away by its potential.
13 examples that will blow your mind (Don't miss the 5th one):
Bo Xiong retweeted
NeurIPS acknowledges that the cultural generalization made by the keynote speaker today reinforces implicit biases by making generalisations about Chinese scholars. This is not what NeurIPS stands for. NeurIPS is dedicated to being a safe space for all of us. We want to address the comment made during the invited talk this afternoon, as it is something that NeurIPS does not condone and it doesn't align with our code of conduct. We are addressing this issue with the speaker directly.
NeurIPS is dedicated to being a diverse and inclusive place where everyone is treated equally.
Bo Xiong retweeted
🚨Is complex query answering really complex?🚨
unfortunately not!
the current benchmarks boil down to link prediction 98% of the time...
how to fix this???
👇👇👇
📜arxiv.org/abs/2410.12537
with @c_gregucci @BoXiongs @loreloc_ @PMinervini @ststaab
Bo Xiong retweeted
can you guess what are the numbers in this table about? and what is the message?
I will incrementally reveal the header and the row ids in the next days, and ultimately its caption.
if you figure it out first, you will win a coffee with @PMinervini!
3 of 3 submissions of my research will be presented by my co-authors and/or me at EMNLP 2024, Miami, USA. 😀
The topics include #KG and #reasoning with #Uncertainty, #Temporal, #LargeLanguageModels, and #RAG.
Congratuations to all the co-authors.
Bo Xiong retweeted
Congrats to Dr. @andreasgrv who just defended his #PhD thesis on unargmaxability and constraints in deep learning, examined by Vlad Niculae and @driainmurray 🎉
A pity you could not (yet) see Andreas' beautifully designed thesis!
In the meantime, some pics from the pre-viva 👇
Bo Xiong retweeted
Exciting job opportunity! 🧑🔬 We at the School of Informatics, University of Edinburgh (@InfAtEd, @EdinburghNLP) are looking for a Research Associate (~postdoc) in NLP and ML for a 3-year project fully funded by @Huawei via the Huawei-Edinburgh Joint Lab initiative!
The project focuses on improving the robustness and trustworthiness of LLMs when answering complex questions and solving complex tasks 🚀
📅 Apply by 15th July 2024
🔗 Link to apply: elxw.fa.em3.oraclecloud.com/…
#NLP #MachineLearning #ResearchJobs #AcademicTwitter
Bo Xiong retweeted
Sometimes it’s truly hard to find as passionate and enthusiastic researchers as Pasquale 😃 you should really consider to apply to this job position 🚀 Plus, Edinburgh and @InfAtEd are just amazing 🤩
Exciting job opportunity! 🧑🔬 We at the School of Informatics, University of Edinburgh (@InfAtEd, @EdinburghNLP) are looking for a Research Associate (~postdoc) in NLP and ML for a 3-year project fully funded by @Huawei via the Huawei-Edinburgh Joint Lab initiative!
The project focuses on improving the robustness and trustworthiness of LLMs when answering complex questions and solving complex tasks 🚀
📅 Apply by 15th July 2024
🔗 Link to apply: elxw.fa.em3.oraclecloud.com/…
#NLP #MachineLearning #ResearchJobs #AcademicTwitter
Glad to visit the April Lab at Edinburgh. I learned a lot from many people here. Thank you for the hosting😊
last week we had @BoXiongs from @ELLISforEurope Stuttgart give a nice talk at @InfAtEd in the joint @HuaweiUK lab at @BayesCentre on
imposing #structure and #knowledge in #geometric #deep #learning
#ML #AI
Bo Xiong retweeted
Interested in constraints in Neural Networks? Come to poster 489 and I will explain how bottlenecked layers are constraining what you can and cannot predict! #AAAAI24 #AAAI2024
How expressive is your deep multi-label classifier?
Can it represent all outputs of interest? 🤔
SPOILER🚨: Your model can have *test set* outputs that are impossible to predict! 🚫
Check out our paper! arxiv.org/abs/2310.10443
🧵(1/7)
🎉 In our recent paper accepted at #AAAI24! we propose NestE, a knowledge graph embedding method that encodes nested facts represented by quoted triples (h,r,t) in which the subject and object are triples themselves.
Arxiv: arxiv.org/abs/2312.09219
Code: github.com/xiongbo010/NestE
Bo Xiong retweeted
We convert popular knowledge graph embedding (KGE) models such as ComplEx into generative models of triples that
1️⃣ better scale training to very large knowledge graphs
2️⃣ make reliable predictions with logical constraints
3️⃣ support sampling
in our #NeurIPS2023 oral!
Bo Xiong retweeted
And the fifth ongoing #CIKM2023 tutorial is Reasoning beyond Triples: Recent Advances in Knowledge Graph Embeddings by @BoXiongs, Mojtaba Nayyeri, @danieldazac, and @michaelcochez 🧵6/6
Site: kg-beyond-triple.github.io/
Thrilled to announce that we will be giving a tutorial with @danieldazac @michaelcochez and Mojtaba on "Reasoning beyond Triples: Recent Advances in Knowledge Graph Embeddings", at #cikm2023.
Slides will be available on the tutorial website kg-beyond-triple.github.io/. Stay tuned!
