bigdata_ugent's profile picture. Big Data Hadoop, HDFS, Spark, ML Flow initiative at Ghent University

BigData_UGent

@bigdata_ugent

Big Data Hadoop, HDFS, Spark, ML Flow initiative at Ghent University

Repost di BigData_UGent

In Today’s Session of my #BigDataAnalytics Class Dylan talks about the latest developments in the transformer architecture (#LLMs, large-language models, #NLP). He discusses how to implement them in #Python notebooks. #DataEngineering #DataScience #DataAnalytics #OpenSource #orms

dirkvandenpoel's tweet image. In Today’s Session of my #BigDataAnalytics Class Dylan talks about the latest developments in the transformer architecture (#LLMs, large-language models, #NLP). He discusses how to implement them in #Python notebooks. #DataEngineering #DataScience #DataAnalytics #OpenSource #orms

Repost di BigData_UGent

Even in the era of NVIDIA‘s Grace Blackwell distributed computing is still a big thing. Some speedups are even superlinear. Talk by Mark Ostroot (principal solutions engineer at Simplerose) at the 2025 INFORMS Annual Meeting in Atlanta, GA. #INFORMS2025

dirkvandenpoel's tweet image. Even in the era of NVIDIA‘s Grace Blackwell distributed computing is still a big thing. Some speedups are even superlinear. Talk by Mark Ostroot (principal solutions engineer at Simplerose) at the 2025 INFORMS Annual Meeting in Atlanta, GA. #INFORMS2025
dirkvandenpoel's tweet image. Even in the era of NVIDIA‘s Grace Blackwell distributed computing is still a big thing. Some speedups are even superlinear. Talk by Mark Ostroot (principal solutions engineer at Simplerose) at the 2025 INFORMS Annual Meeting in Atlanta, GA. #INFORMS2025

Repost di BigData_UGent

We have lift-off at the 2025 INFORMS Annual Meeting in Atlanta, GA @INFORMS2025 @INFORMS #ORMS #AI #Analytics #LLMs

dirkvandenpoel's tweet image. We have lift-off at the 2025 INFORMS Annual Meeting in Atlanta, GA @INFORMS2025 @INFORMS #ORMS #AI #Analytics #LLMs
dirkvandenpoel's tweet image. We have lift-off at the 2025 INFORMS Annual Meeting in Atlanta, GA @INFORMS2025 @INFORMS #ORMS #AI #Analytics #LLMs
dirkvandenpoel's tweet image. We have lift-off at the 2025 INFORMS Annual Meeting in Atlanta, GA @INFORMS2025 @INFORMS #ORMS #AI #Analytics #LLMs

Repost di BigData_UGent

On my way to the 2025 INFORMS Annual Meeting in Atlanta, GA to present our innovative LLM research on uncovering service quality of airports using ModernBERT and LLaMa 3.3 70B. I’ll apply our new methodology to the ATL Airport. @INFORMS @INFORMS2025 #INFORMS2025 #ORMS #GenAI #LLM


Repost di BigData_UGent

Great talk by Sumit Gulwani (@SumitGulwani, Microsoft) on improving AI reasoning by using intent, interaction, inspection, and memory (see last picture) at #KDD2025 in Toronto, Canada. #AI #LLM #CodeGeneration

dirkvandenpoel's tweet image. Great talk by Sumit Gulwani (@SumitGulwani, Microsoft) on improving AI reasoning by using intent, interaction, inspection, and memory (see last picture) at #KDD2025 in Toronto, Canada. #AI #LLM #CodeGeneration
dirkvandenpoel's tweet image. Great talk by Sumit Gulwani (@SumitGulwani, Microsoft) on improving AI reasoning by using intent, interaction, inspection, and memory (see last picture) at #KDD2025 in Toronto, Canada. #AI #LLM #CodeGeneration
dirkvandenpoel's tweet image. Great talk by Sumit Gulwani (@SumitGulwani, Microsoft) on improving AI reasoning by using intent, interaction, inspection, and memory (see last picture) at #KDD2025 in Toronto, Canada. #AI #LLM #CodeGeneration
dirkvandenpoel's tweet image. Great talk by Sumit Gulwani (@SumitGulwani, Microsoft) on improving AI reasoning by using intent, interaction, inspection, and memory (see last picture) at #KDD2025 in Toronto, Canada. #AI #LLM #CodeGeneration

Repost di BigData_UGent

Great talk by Dan Roth on the limitations of using LLMs for reasoning at the #KDD2025 Conference in Toronto. Being linguistically coherent is much easier than we thought (that’s what LLMs have taught us). Use LLMs to generate (Python) code to solve hard problems. #AI #LLMs #ORMS

dirkvandenpoel's tweet image. Great talk by Dan Roth on the limitations of using LLMs for reasoning at the #KDD2025 Conference in Toronto. Being linguistically coherent is much easier than we thought (that’s what LLMs have taught us). Use LLMs to generate (Python) code to solve hard problems. #AI #LLMs #ORMS
dirkvandenpoel's tweet image. Great talk by Dan Roth on the limitations of using LLMs for reasoning at the #KDD2025 Conference in Toronto. Being linguistically coherent is much easier than we thought (that’s what LLMs have taught us). Use LLMs to generate (Python) code to solve hard problems. #AI #LLMs #ORMS
dirkvandenpoel's tweet image. Great talk by Dan Roth on the limitations of using LLMs for reasoning at the #KDD2025 Conference in Toronto. Being linguistically coherent is much easier than we thought (that’s what LLMs have taught us). Use LLMs to generate (Python) code to solve hard problems. #AI #LLMs #ORMS
dirkvandenpoel's tweet image. Great talk by Dan Roth on the limitations of using LLMs for reasoning at the #KDD2025 Conference in Toronto. Being linguistically coherent is much easier than we thought (that’s what LLMs have taught us). Use LLMs to generate (Python) code to solve hard problems. #AI #LLMs #ORMS

Repost di BigData_UGent

Today, I started with the Test of Time Award talk at the #KDD2025 Conference in Toronto. Superb talk by Hao Wang on Deep Recommender Systems (RECSYS). He gave a great overview of how the field evolved over time, and the next steps. #AI #RecSys

dirkvandenpoel's tweet image. Today, I started with the Test of Time Award talk at the #KDD2025 Conference in Toronto. Superb talk by Hao Wang on Deep Recommender Systems (RECSYS). He gave a great overview of how the field evolved over time, and the next steps. #AI #RecSys
dirkvandenpoel's tweet image. Today, I started with the Test of Time Award talk at the #KDD2025 Conference in Toronto. Superb talk by Hao Wang on Deep Recommender Systems (RECSYS). He gave a great overview of how the field evolved over time, and the next steps. #AI #RecSys
dirkvandenpoel's tweet image. Today, I started with the Test of Time Award talk at the #KDD2025 Conference in Toronto. Superb talk by Hao Wang on Deep Recommender Systems (RECSYS). He gave a great overview of how the field evolved over time, and the next steps. #AI #RecSys
dirkvandenpoel's tweet image. Today, I started with the Test of Time Award talk at the #KDD2025 Conference in Toronto. Superb talk by Hao Wang on Deep Recommender Systems (RECSYS). He gave a great overview of how the field evolved over time, and the next steps. #AI #RecSys

Repost di BigData_UGent

Great tutorial on efficient and effective search-agent training at #KDD2025 in Toronto. One does not need a lot of data to train a search agent via RL (using S3 compared to R1). #LLM #RAG #RL #R1 #S3

dirkvandenpoel's tweet image. Great tutorial on efficient and effective search-agent training at #KDD2025 in Toronto. One does not need a lot of data to train a search agent via RL (using S3 compared to R1). #LLM #RAG #RL #R1 #S3
dirkvandenpoel's tweet image. Great tutorial on efficient and effective search-agent training at #KDD2025 in Toronto. One does not need a lot of data to train a search agent via RL (using S3 compared to R1). #LLM #RAG #RL #R1 #S3

Repost di BigData_UGent

My personal #KDD2025 Day 2 is all about #finance ranging from using AI to enhance safety, AI in credit, and data-driven pricing #AI #llm #timeseries #finetuning #dataleakage

dirkvandenpoel's tweet image. My personal #KDD2025 Day 2 is all about #finance ranging from using AI to enhance safety, AI in credit, and data-driven pricing #AI #llm #timeseries #finetuning #dataleakage
dirkvandenpoel's tweet image. My personal #KDD2025 Day 2 is all about #finance ranging from using AI to enhance safety, AI in credit, and data-driven pricing #AI #llm #timeseries #finetuning #dataleakage
dirkvandenpoel's tweet image. My personal #KDD2025 Day 2 is all about #finance ranging from using AI to enhance safety, AI in credit, and data-driven pricing #AI #llm #timeseries #finetuning #dataleakage
dirkvandenpoel's tweet image. My personal #KDD2025 Day 2 is all about #finance ranging from using AI to enhance safety, AI in credit, and data-driven pricing #AI #llm #timeseries #finetuning #dataleakage

Repost di BigData_UGent

Building scenario planning solutions for supply chain optimization using LLMs (large language models) at the #KDD2025 Workshop AI for Supply Chain. #FlandersMake #REMASC #AI See example on the slides in the pictures.

dirkvandenpoel's tweet image. Building scenario planning solutions for supply chain optimization using LLMs (large language models) at the #KDD2025 Workshop AI for Supply Chain. #FlandersMake #REMASC #AI See example on the slides in the pictures.
dirkvandenpoel's tweet image. Building scenario planning solutions for supply chain optimization using LLMs (large language models) at the #KDD2025 Workshop AI for Supply Chain. #FlandersMake #REMASC #AI See example on the slides in the pictures.

Repost di BigData_UGent

We have liftoff at the 2025 KDD Conference in Toronto, ON. #KDD2025 I’m attending the Workshop on AI for Supply Chain relevant to our REMASC. Supply chain planning faces two sources of complexity: radical uncertainty (e.g., use scenario planning) and need for good predictions.

dirkvandenpoel's tweet image. We have liftoff at the 2025 KDD Conference in Toronto, ON. #KDD2025  I’m attending the Workshop on AI for Supply Chain relevant to our REMASC. Supply chain planning faces two sources of complexity: radical uncertainty (e.g., use scenario planning) and need for good predictions.

Repost di BigData_UGent

Naive RAG vs. Graph RAG, clearly explained:


Repost di BigData_UGent

Today marks the start of presentations of the “Data Science for Business” (@UGent) projects. This particular project is for #FlandersMake using #RAG (Retrieval-Augmented Generation) #LLM technology to build a #chatbot. mma.ugent.be #orms #DataScience

dirkvandenpoel's tweet image. Today marks the start of presentations of the “Data Science for Business” (@UGent) projects. This particular project is for #FlandersMake using #RAG (Retrieval-Augmented Generation) #LLM technology to build a #chatbot. mma.ugent.be #orms #DataScience

Repost di BigData_UGent

We have lift-off at the 2025 @INFORMS Marketing Science Conference in Washington, DC. Hot topics include #GenAI, #LLM, #RAG (Retrieval Augmented Generation), #Marketing #Analytics, #ecommerce, #ORMS

dirkvandenpoel's tweet image. We have lift-off at the 2025 @INFORMS Marketing Science Conference in Washington, DC. Hot topics include #GenAI, #LLM, #RAG (Retrieval Augmented Generation), #Marketing #Analytics, #ecommerce, #ORMS

Repost di BigData_UGent

Last week, the 2025 Edition of our “Current Data Science for Business Students Meet Alumni” Event took place at @UGentFEB (Ghent University). #ORMS #DataScience #DataAnalytics linkedin.com/pulse/current-…


Repost di BigData_UGent

Great panel discussion during the UGent FEB Research Day 2025 with representatives from Flanders Make, KPMG, OMP, UGent Industrial Research Fund. #PhDResearch #IndustrialResearchFund #Startups #GhentUniversity @CVAMO_UGent #ecosystem @UGentFEB


Repost di BigData_UGent

Great application of optimization techniques in sports: USA Cycling (@usacycling) has been awarded the 2025 @INFORMS Edelman Award at @2025_Analytics in Indianapolis, IN, the “Nobel Prize” of Operations Research, for its innovative use of O.R. and analytics in sports performance.

dirkvandenpoel's tweet image. Great application of optimization techniques in sports: USA Cycling (@usacycling) has been awarded the 2025 @INFORMS Edelman Award at @2025_Analytics in Indianapolis, IN, the “Nobel Prize” of Operations Research, for its innovative use of O.R. and analytics in sports performance.
dirkvandenpoel's tweet image. Great application of optimization techniques in sports: USA Cycling (@usacycling) has been awarded the 2025 @INFORMS Edelman Award at @2025_Analytics in Indianapolis, IN, the “Nobel Prize” of Operations Research, for its innovative use of O.R. and analytics in sports performance.
dirkvandenpoel's tweet image. Great application of optimization techniques in sports: USA Cycling (@usacycling) has been awarded the 2025 @INFORMS Edelman Award at @2025_Analytics in Indianapolis, IN, the “Nobel Prize” of Operations Research, for its innovative use of O.R. and analytics in sports performance.
dirkvandenpoel's tweet image. Great application of optimization techniques in sports: USA Cycling (@usacycling) has been awarded the 2025 @INFORMS Edelman Award at @2025_Analytics in Indianapolis, IN, the “Nobel Prize” of Operations Research, for its innovative use of O.R. and analytics in sports performance.

Repost di BigData_UGent

Elena Gerstmann (@egerstmann, Executive Director) takes the stage at the 2025 @INFORMS Analytics+ Conference. #Analytics @2025_Analytics #ORMS

dirkvandenpoel's tweet image. Elena Gerstmann (@egerstmann, Executive Director) takes the stage at the 2025 @INFORMS Analytics+ Conference. #Analytics @2025_Analytics #ORMS

Repost di BigData_UGent

Great talk by @MatthewALanham on the #data4good competition at @INFORMS#MAPD 2025 (Meeting of Analytics Program Directors at @2025_Analytics) in Indianapolis, IN #predictiveanalytics #analytics #machinelearning #INFORMS

dirkvandenpoel's tweet image. Great talk by @MatthewALanham on the #data4good competition at @INFORMS’  #MAPD 2025 (Meeting of Analytics Program Directors at @2025_Analytics) in Indianapolis, IN #predictiveanalytics #analytics #machinelearning #INFORMS

Repost di BigData_UGent

Congrats to Yaël, Wannes, and Brammert for receiving the Best Poster Award for End-to-End Design Operation. #Awesome #REMASC #FlandersMake

dirkvandenpoel's tweet image. Congrats to Yaël, Wannes, and Brammert for receiving the Best Poster Award for End-to-End Design Operation. #Awesome #REMASC #FlandersMake

Loading...

Something went wrong.


Something went wrong.