Uri Alon
Research scientist at Google DeepMind; CMU LTI alum; works on retrieval-augmented LLMs and code intelligence (code2vec / code2seq).
- Role
- researcher
- Currently at
- Google DeepMind
- twitter.com/UriAlon1
- GitHub
- github.com/urialon
- Scholar
- scholar.google.com/citations
- Papers
- 11
Cite
Notes
Only stored in your browser.
Authored papers
11WebArena: A Realistic Web Environment for Building Autonomous Agents
ICLR
Unlimiformer: Long-Range Transformers with Unlimited Length Input
NeurIPS 2023 11
Learning Performance-Improving Code Edits
arXiv 2023
CodeBERTScore: Evaluating Code Generation with Pretrained Models of Code
arXiv 2023
Why do Nearest Neighbor Language Models Work?
arXiv 2023
On the Expressivity Role of LayerNorm in Transformers' Attention
arXiv 2023
Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval
arXiv 2022
DocPrompting: Generating Code by Retrieving the Docs
arXiv 2022
Language Models of Code are Few-Shot Commonsense Learners
arXiv 2022
How Attentive are Graph Attention Networks?
how-attentive-are-graph-attention-networks-1
code2seq: Generating Sequences from Structured Representations of Code
code2seq-generating-sequences-from-structured-1
Affiliations
Frequent co-authors
10from 11 papers
Graham Neubig
professor
Frank F. Xu
Shuyan Zhou
professor
Eran Yahav
Shaked Brody
Aman Madaan
Abishek Sridhar
researcher
Alexander Shypula
Amanda Bertsch
Amir Yazdanbakhsh