Lightnews — Scholar-powered news

Yuqicheng Zhu @yuqichengzhu.bsky.social · 28d

🌊 Had an amazing time at NeSy 2025 @nesyconf.org in Santa Cruz! Very well-organized conference, great talks, inspiring discussion and of course enjoying the beautiful beach and Bay Area vibes. 🏖️✨

#NeSy2025 #neurosymbolicAI #SantaCruz

4 7

Reposted by Yuqicheng Zhu

NeSy 2025 Conference @nesyconf.org · 28d

Today, @yuqichengzhu.bsky.social opened the oral session with a beautiful talk on a Neurosymbolic extension of Retrieval Augmented Generation (RAG) with an argumentation framework

1 1 1

Reposted by Yuqicheng Zhu

Daniel Hernández @daniel.mstdn.degu.cl.ap.brid.gy · Aug 2

Yuqicheng Zhu (@yuqichengzhu.bsky.social) presented our paper, Predicate-Conditional Conformalized Answer Sets for Knowledge Graph Embeddings, at #acl2025. This paper studies a key question for the reliability of applications using knowledge graph embeddings […]

[Original post on mstdn.degu.cl]

Yuqicheng is standing in front of his poster. The poster is on a panel with the number 299.

3 3

Reposted by Yuqicheng Zhu

UniStuttgartAI @unistuttgartai.bsky.social · May 28

We are honored to host 𝐃𝐫. 𝐑𝐞𝐢𝐧𝐡𝐚𝐫𝐝 𝐒𝐭𝐨𝐥𝐥𝐞 for his talk, “𝐸𝑛𝑔𝑖𝑛𝑒𝑒𝑟𝑖𝑛𝑔 𝑆𝑎𝑓𝑒 𝑆𝑦𝑠𝑡𝑒𝑚𝑠 𝑤𝑖𝑡ℎ 𝐴𝐼”, on 𝐉𝐮𝐧𝐞 𝟓 𝐚𝐭 𝟏𝟓:𝟒𝟓 in 𝐑𝐨𝐨𝐦 𝐔𝟑𝟐.𝟏𝟎𝟏, 𝐔𝐧𝐢𝐯𝐞𝐫𝐬𝐢𝐭ä𝐭𝐬𝐬𝐭𝐫𝐚ß𝐞 𝟑𝟐. Students, staff, and all interested guests are warmly invited to attend!

#AI #Safety

1 2 3

Reposted by Yuqicheng Zhu

Institute for AI @unistuttgartai.xn--baw-joa.social.ap.brid.gy · Jan 26

Institute researchers propose a new query embedding method to extend the expressiveness of existing query embeddings. The paper will be presented at the Web Conference 2025, in Sidney, Australia, from April 28 to May 2.

Query embedding methods are used to predict the answers to queries by […]

Original post on xn--baw-joa.social

xn--baw-joa.social

1 1

Reposted by Yuqicheng Zhu

UniStuttgartAI @unistuttgartai.bsky.social · Apr 24

Several papers from our institute (AC group) have been accepted at top conferences! 🎉

Our colleagues are attending—feel free to reach out if you’d like to connect! #ICLR2025 #WWW2025 #NAACL2025 #AI #NLP #ML

1 3 4

Reposted by Yuqicheng Zhu

UniStuttgartAI @unistuttgartai.bsky.social · Feb 11

🚀 We’re on Bluesky! 🚀

We are the AI Institute at the University of Stuttgart—researching fundamental questions about AI, reflecting its benefits for society, and promoting the transfer of AI applications to business and society.

Follow us for insights, updates, and discussions on the future of AI!

1 2 3

Yuqicheng Zhu @yuqichengzhu.bsky.social · Jan 28

🤓 In our paper, we tackle this issue by addressing a crucial question:
"How many entities do we need to guarantee coverage of the true answer at a pre-defined confidence level (e.g. 90%)?"
(The more entities we need, the more uncertain the KGE model is about its predictions.)

2

Yuqicheng Zhu @yuqichengzhu.bsky.social · Jan 28

🤔 When can we trust the predictions of Knowledge Graph Embedding (KGE) methods?
😲 Do the plausibility scores they return provide this uncertainty information?
Unfortunately, no—these scores are not calibrated and lack a probabilistic interpretation.

1 2

Yuqicheng Zhu @yuqichengzhu.bsky.social · Jan 28

🚨 New Paper Accepted at #NAACL2025 🚨
"Conformalized Answer Set Prediction for Knowledge Graph Embedding"
@yuqichengzhu.bsky.social, Nico Potyka, Jiarong Pan, @boxiong.bsky.social, Yunjie He, Evgeny Kharlamov, @ststaab.bsky.social
✨Check out our paper: arxiv.org/pdf/2408.082...

1 4 7

Reposted by Yuqicheng Zhu

Blake Richards @tyrellturing.bsky.social · Dec 16

1/ Okay, one thing that has been revealed to me from the replies to this is that many people don't know (or refuse to recognize) the following fact:

The unts in ANN are actually not a terrible approximation of how real neurons work!

A tiny 🧵.

🧠📈 #NeuroAI #MLSky

Blake Richards @tyrellturing.bsky.social · Dec 16

Why does anyone have any issue with this?

I've seen people suggesting it's problematic, that neuroscientists won't like it, and so on.

But, I literally don't see why this is problematic...

PessoaBrain @pessoabrain.bsky.social · Dec 15

This would be funny if it weren't sad...
Coming from the "giants" of AI.
Or maybe this was posted out of context? Please clarify.
I can't process this...

21 38 150

Reposted by Yuqicheng Zhu

Andreas Kirsch @blackhc.bsky.social · Dec 17

The slides for my lectures on (Bayesian) Active Learning, Information Theory, and Uncertainty are online now 🥳 They cover quite a bit from basic information theory to some recent papers:

blackhc.github.io/balitu/

and I'll try to add proper course notes over time 🤗

3 28 180

Reposted by Yuqicheng Zhu

NeurIPS Conference @neuripsconf.bsky.social · Dec 14

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. 1/3

11 15 120

Reposted by Yuqicheng Zhu

Mário Figueiredo @marfig.bsky.social · Dec 6

The final version of our survey on conformal prediction for NLP has now been published in TACL: direct.mit.edu/tacl/article...

Conformal Prediction for Natural Language Processing: A Survey

Abstract. The rapid proliferation of large language models and natural language processing (NLP) applications creates a crucial need for uncertainty quantification to mitigate risks such as Hallucinat...

direct.mit.edu

1 4 11

Reposted by Yuqicheng Zhu

Lars van der Laan @larsvanderlaan3.bsky.social · Dec 12

Excited to present "Self-Calibrating Conformal Prediction" at #NeurIPS2024 this afternoon! Join me at the poster session to learn how combining model calibration with predictive inference gives calibrated point predictions and conditionally valid prediction intervals

1 1 4

Reposted by Yuqicheng Zhu

Steffen Staab @ststaab.bsky.social · Dec 4

This position of a doctoral researcher in Machine Learning – Runtime Monitoring of Autonomous Driving Functions is open at Mercedes in collaboration with my team, Analytic Computing at @unistuttgart.bsky.social jobs.mercedes-benz.com/en/phd-docto...

Ph.D. / Doctorate position in Machine Learning – Runtime Monitoring of Autonomous Driving Functions in cooperation with a university starting March 2025

The Mercedes-Benz Group AG, one of the world's most successful automotive companies, is a leading provider of premium and luxury cars and vans. In Corporate Research & Development (RD), we shape futur...

jobs.mercedes-benz.com

3 7

Reposted by Yuqicheng Zhu

logconference.bsky.social @logconference.bsky.social · Nov 29

🏆 Best Paper Award & Honorable Mention 🏆

Congratulations to our outstanding authors for their exceptional contributions to LoG 2024! 🎉

📜 Your work inspires the entire graph and geometric ML community!

1 3 16

Reposted by Yuqicheng Zhu

antonio vergari ⚔️ short-circuiting @nolovedeeplearning.bsky.social · Nov 29

tractability has a precise definition taken from computer science!

So in probabilistic inference, it means solving exactly in polytime a certain query class of interest. In this case compute all possible probabilities for joint assignments.

Shameless plug from a tutorial here 👇👇👇

2 2 14

Reposted by Yuqicheng Zhu

Jiaoyan @jiaoyanchen.bsky.social · Nov 25

Qiang Zhang, me and Zaiqiao Meng will give a 1.5-hour tutorial on Integrating #KnowledgeGraphs and #LLMs for Advancing Scientific Research at @logconference.bsky.social at 2.30pm (UK time / GMT), 26 Nov. #AI4Science. Looking forward to discuss with you.

1 3 10

Reposted by Yuqicheng Zhu

Lars van der Laan @larsvanderlaan3.bsky.social · Nov 14

Excited to share that our paper "Self-Calibrating Conformal Prediction" with Ahmed Alaa is accepted at #NeurIPS2024! 🚀

We combine model calibration and prediction intervals by integrating Venn-Abers into conformal prediction. #conformal #calibration

arxiv.org/pdf/2402.07307

arxiv.org

1 4 19

Reposted by Yuqicheng Zhu

Emile van Krieken @emilevankrieken.com · Nov 11

I made a starter pack with the people doing something related to Neurosymbolic AI that I could find.

Let me know if I missed you!
go.bsky.app/RMJ8q3i

16 36 92

Reposted by Yuqicheng Zhu

Marvin Schmitt @marvin-schmitt.com · Nov 24

You can create your own rule-based feed with @skyfeed.app, or run a completely self-hosted feed server if you want to go fully custom.

For instance, @serge.belongie.com and I just set up an ML Internship feed that collects posts by a keywords-regex and hashtag-MLinternship

bsky.app/profile/did:...

3 13 52

Yuqicheng Zhu @yuqichengzhu.bsky.social · Nov 22

Congratulations Michael!

1

Reposted by Yuqicheng Zhu

Ernesto Jiménez-Ruiz @ejimenez-ruiz.bsky.social · Nov 17

I created a starter pack on KGs! I found others useful as newcomer.

go.bsky.app/EQRCq9R

13 20 53

Reposted by Yuqicheng Zhu

Pasquale Minervini @neuralnoise.com · Nov 16

"LLMs can't reason, look at how their accuracy drops if you change the numbers in the problem!!!"
The accuracy drop (%):

1 1 6