Jonathan Halcrow
@jhalcrow
Followers
227
Following
2K
Media
49
Statuses
981
RT @BahareFatemi: Think your LLM is smart? Try Big-Bench EXTRA Hard. The real test. #Reasoning #Benchmark #LLM.
0
5
0
RT @BahareFatemi: While I'm at home with my newborn (๐ถ๐ปโค๏ธ), you can still catch my work at #NeurIPS๐งต:.
0
5
0
RT @BahareFatemi: Think your LLM is a time wizard? ๐ง One might think they answer temporal questions through reasoning, but under the hood tโฆ.
0
10
0
RT @tsitsulin_: ๐จ Transformer theory alert ๐จ. What algorithms can transformers execute efficiently?. Our preprint sheds some light on reasoโฆ.
0
60
0
We'll be demoing some of our work on graphs and LLMs later today at ICLR. If you are around stop by and say Hey!.
At 3:15pm today, the #ICLR2024 Google booth will host @phanein, @BahareFatemi, and @jhalcrow for a talk on finding the correct graph inductive bias for Graph ML and developing strategies to convert graphs into language-like formats for LLMs.
0
0
2
RT @BahareFatemi: Talk Like a Graph or Let Your Graph Do the Talking ๐ง ๐ธ๏ธ.New paper alert ๐จ: we show how GNNs can effectively encode graph-sโฆ.
0
9
0
RT @tsitsulin_: ๐๐๐ญ ๐๐จ๐ฎ๐ซ ๐๐ซ๐๐ฉ๐ก ๐๐จ ๐ญ๐ก๐ ๐๐๐ฅ๐ค๐ข๐ง๐ : ๐๐ง๐๐จ๐๐ข๐ง๐ ๐๐ญ๐ซ๐ฎ๐๐ญ๐ฎ๐ซ๐๐ ๐๐๐ญ๐ ๐๐จ๐ซ ๐๐๐๐ฌ. Don't know what to do with your graphs in 2024? Shove theโฆ.
0
43
0
RT @BahareFatemi: New paper alert ๐จ: "Talk Like a Graph" studies the problem of encoding graph-structured data, paving the way for AI to beโฆ.
0
38
0
RT @tsitsulin_: Check out latest and greatest in data selection with graphs! The paper features:.๐คฏ A hardness theorem for training data selโฆ.
0
3
0
RT @tsitsulin_: Aloha! ๐ค๐บ๐ด. Check out our 3 papers today at @TAGinDS!.(11AM p.) Learning Large Graph Property Prediction via Graph Segmentโฆ.
0
3
0
RT @phanein: ๐ Aloha and good morning! ๐ #ICML2023 is shaping up to be the most exciting #MachineLearning conference yet, and I'm proud thโฆ.
0
6
0
Heading out to ICML! Catch me Sunday at the Expo and come learn about TF-GNN Check this thread for some other work by my group:.
1) Knowledge Hypergraph Embedding Meets Relational Algebra ( Tuesday 2-3:30pm. We proposed an embedding-based model for relational hypergraphs that provably represents some relational algebra operations. Joint work with @PerouzT @dvazquezcv @davpoole.
0
2
6
RT @BahareFatemi: 2) UGSL: A Unified Framework for Benchmarking Graph Structure Learning ( Friday 11:10-12pm. TLDR:โฆ.
openreview.net
Graph neural networks (GNNs) demonstrate outstanding performance in a broad range of applications. While the majority of GNN applications assume that a graph structure is given, some recent methods...
0
4
0
RT @tsitsulin_: ๐ฅInternship opportunity (fall/summer'23) in the Graph Mining team @ Google! Join us to work on cutting edge research in graโฆ.
0
24
0
Announcing Graph Mining Atlanta!. I'm hiring for a new branch of my team (part of Google Research) in Atlanta this summer. To see more about what we do see our talks from NeurIPS 2020 and our team page
linkedin.com
Announcing Graph Mining: Atlanta! This summer I'll be moving to Atlanta and am #hiring to staff up a new branch of my team at Google based there. We work on algorithms for unsupervised and semi-sup...
1
1
3