Celian Ringwald
@ringwald_c
Followers
335
Following
2K
Media
87
Statuses
880
Datartisan working with knowledge, graphs and texts - Phd Student at INRIA, 3IA, CNRS, I3S, UCA
Joined March 2015
We're happy to share our latest research accepted at #KCAP2025: “Overcoming the Generalization Limits of SLM Finetuning for Shape-Based Extraction of Datatype and Object Properties” 📄 https://t.co/e8czkDEVmr 👨💻 https://t.co/yMyzlJCVJh
0
0
3
-Echos from the room of text, triples & constraints- Really excited to visit the KCL Knowledge Graphs Lab over the next two weeks! A stay that sounds like a hyperbolic time chamber, to discuss and join forces on LLM/Constraints RQs, before writing the last pages of my PhD
0
0
1
Really sad to see the PaperWithCode shutting down too, for the moment https://t.co/YquDVIg9rR do not entirely do the same job...
huggingface.co
0
0
0
#ESWC2025 kicks off! Join us in the next days for two sessions on LLM-driven ontology generation: 🔹 ELMKE workshop: Assessing LLMs to generate domain ontologies https://t.co/Rx5LxfUQaC 🔹 Research track: Ontology generation with LLMs https://t.co/JYAYNvGoBo
@eswc_conf
arxiv.org
The ontology engineering process is complex, time-consuming, and error-prone, even for experienced ontology engineers. In this work, we investigate the potential of Large Language Models (LLMs) to...
0
4
6
Ever more confirmation language models are behaving as latent knowledge graphs.
Our interpretability team recently released research that traced the thoughts of a large language model. Now we’re open-sourcing the method. Researchers can generate “attribution graphs” like those in our study, and explore them interactively.
9
40
408
I am looking forward #ESWC2025 in Portorož next week ! The occasion to present our last work: Kastor - 🦫 A framework that includes Human-in-the-loop and combines #KG and #SLMs to produce #RDF and shape-based relation extractors. > Author version: https://t.co/B2QUZfTsYk
0
2
11
Just received my #LookingForAPostDoc tshirt :) See you soon for talking about shapes, rdf based relation extraction and Kastor (beavers) in a wood of knowledge.
0
1
8
When working with LLMs I am used to starting "New Conversation" for each request. But there is also the polar opposite approach of keeping one giant conversation going forever. The standard approach can still choose to use a Memory tool to write things down in between
672
567
7K
Still a source of inspiration :)
An introductory talk by Christopher Manning @chrmanning on “Large Language Models in 2025 – How much understanding and intelligence?” at the Workshop on a Public AI Assistant to Worldwide Knowledge at @Stanford, covering 3 eras of LLMs, RAG, Agents, DeepSeek-R1, using LLMs, ….
1
1
6
An introductory talk by Christopher Manning @chrmanning on “Large Language Models in 2025 – How much understanding and intelligence?” at the Workshop on a Public AI Assistant to Worldwide Knowledge at @Stanford, covering 3 eras of LLMs, RAG, Agents, DeepSeek-R1, using LLMs, ….
8
162
845
📢 5 Associate Professor positions @Laboratoire_I3S @Univ_CotedAzur The recruitment campaign will start the 4th March 2025. One position is on "Artificial Intelligence methods for the life cycle of a knowledge graphs" 👉 https://t.co/p4aL7DUmUh
#Jobs #Emploi
0
2
3
🎓#PhD👏 Félicitations à Benjamin MOLINET 👨🎓 doctorant @Univ_CotedAzur au sein de l'équipe Wimmics @inria_sophia pour son travail de thèse et sa soutenance ! 📚#Medical En savoir ➕ sur lui➡️ https://t.co/roZtK5AxTz ➡️ https://t.co/9omzI0H8El
0
3
5
First day of the plenary meeting of the GOBLIN COST Action! Great Knowledge Graph Science team in Action! #goblincost #KnowledgeGraphs
0
14
25
[#Média] 📰 sur https://t.co/MTCRJ9XYCF un entretien avec @fabien_gandon @Inria et @franck_michel2 @CNRS qui ont écrit "PAY ATTENTION" 📔 un appel à réguler le marché de l'attention. Les plateformes numériques affectent nos émotions et notre bien être.
creativeprocess.info
AI competes for our attention because our attention has been commodified. As our entire lives revolve more and more around the attention economy, what can we do to restore our autonomy, reclaim our...
0
7
6
📃 Prêtez Attention : quand « prêter » est « données » (épisode 1), un billet sur le blog Binaire de Le Monde 🔗 https://t.co/2ptZB83BjT 🔑 #attention #IA #Web 📢 @Blog_Binaire @lemondefr @SocInfoFr @inria @Univ_CotedAzur @CNRS_DR20 @Laboratoire_I3S @Cluster_IA @franck_michel2
lemonde.fr
A l'heure où Elon Musk fait un peu n'importe quoi au nom de la liberté d'expression, quand des grands patrons du numérique lui emboîtent le pas sans doute pour pousser leurs intérêts économiques, il...
0
5
6