Qiwei Huang explains how we use Late Materialization (LM) in the Apache Rust Parquet reader to accelerate filtering. LM can describe several techniques, but this is a core one (also applies to joins, Top-K, etc) https://t.co/F4Lqc29IeH

In the past few years, we’ve seen a cambrian explosion of new columnar formats, challenging the hegemony of Parquet. Presumably, the design of yore is not going to cut it moving forward. I spent some time to understand how things actually changed. https://t.co/BxtXabynQ8

"Column Storage for the AI Era" Enjoyed reading this post about the current state and future of #Parquet, by Julien Le Dem (@J_). New encodings, championed by new columnar formats like Lance, taking advantage of SIMD, etc. Exciting times. 👉 https://t.co/uuYRrnbJqf

Thanks to https://t.co/jc4P72tdmO, we are hosting a DataFusion meetup in Stockholm Date: Thursday March 5, 2026: 17:30 - 20:00 Signup:

There is some crazy (good) activity on the @ApacheParquet mailing list for new encodings. A sample: PFOR, FSST, ALP, Strings and Cascaded Encodings. 🤯 Huge kudos to Arnav Balyan, Prateek Gaur, and Micah Kornfield for driving this. https://t.co/YRE13QEm2j

Here are the slides and recordings from our Boston DataFusion Meetup in September: Youtube: https://t.co/TGgK79oKjd Slides (pdf): https://t.co/kSKpuTFRux

DataFusion 51.0.0 Release Notes: https://t.co/Si4f1g4JNE

Why rebuild the wheel? @olimpiupop talks with @andrewlamb1111 about how Apache Arrow, Parquet, and the FDAP stack are letting database teams focus on innovation instead of reinventing the basics. https://t.co/9EfG3SgcXq

Building Modern Databases with the FDAP Stack • Andrew Lamb & Olimpiu Pop • GOTO 2025 https://t.co/R5ty8GtDdo

Does anyone know a good academic / industrial overview of how to implement (not use) LATERAL joins in SQL? It keeps coming up in @ApacheDataFusio and I need to get reasonable background on it. https://t.co/8mZXmOxDuP

Save the date -- Wednesday July 22, 2026 for the first Apache DataFusion meetup in Denver:

Jobs at F5 for working in Arrow and @ApacheDataFusio :

One fun nugget from the Boston @ApacheDataFusio meetup on Wednesday: DataDog reports they run 68+million queries per hour with DataFusion

Coming soon in arrow-rs: adaptive predicate pushdown https://t.co/72KRzneR8e (aka we are really close to turning on late materialization by default in parquet scans in @ApacheDataFusio )

An interesting take on the composable data stack: a unified distributed execution framework (Sail) will drive innovation in distributed systems implementation the way @ApacheDataFusio et. al have been driving innovation in the computation layer

Here is a nice examination of the benefits of building new systems using the extensibility of @ApacheDataFusio vs other systems.

In the eternal struggle between Good vs Evil, Blur vs Oasis, and @duckdb vs @ApacheDataFusio , we just switched to DataFusion after 18 months, while keeping our #FaaS magic intact: https://t.co/wF2GsLkPHq

"If you want to go fast, go alone; If you want to go far, go together" New Apache Parquet Community page is up: https://t.co/brxdfHc6Kc

We are holding the next @ApacheDataFusio meetup next Wednesday Nov 12 in Boston.

If anyone wants to know why Xiangpeng Hao is a great mentor, they can read this response: https://t.co/Zvu9c046DJ