Scholar
Leshem Choshen
Google Scholar ID: 8b8IhUYAAAAJ
MIT, IBM AI research
Model Recycling
Evolving Collaborative Pretraining
Evaluation
Model Merging
Open the Black Box
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
3,516
H-index
30
i10-index
52
Publications
20
Co-authors
25
list available
Contact
Email
leshem.choshen@mail.huji.ac.il
CV
Open ↗
Twitter
Open ↗
GitHub
Open ↗
Publications
35 items
Mediocrity is the key for LLM as a Judge Anchor Selection
2026
Cited
0
CUBE: A Standard for Unifying Agent Benchmarks
2026
Cited
0
Resolving Interference (RI): Disentangling Models for Improved Model Merging
2026
Cited
0
Do LLMs Benefit From Their Own Words?
2026
Cited
0
General Agent Evaluation
2026
Cited
0
BabyLM Turns 4: Call for Papers for the 2026 BabyLM Workshop
2026
Cited
0
When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation
2026
Cited
0
Robustness as an Emergent Property of Task Performance
2026
Cited
0
Load more
Resume (English only)
Academic Achievements
Paper 'DissentQA' received a Best Paper Award (AC)
Involved in organizing BabyLM 2024
Involved in organizing the LLM Merging Competition
Research featured in The New York Times (on BabyLM)
Published work on open human feedback on AlphaXiv (arXiv:2408.16961)
Co-authors
25 total
Omri Abend
Faculty member, Hebrew University of Jerusalem
Colin Raffel
University of Toronto, Vector Institute and Hugging Face
Ethan Gotlieb Wilcox
Asst. Prof. of Computational Linguistics @Georgetown. Previous: Postdoc @ETH, PhD @ Harvard
Aaron Mueller
Boston University
Alex Warstadt
Assistant Professor, UC San Diego
Mohit Bansal
Parker Distinguished Professor, Computer Science, UNC Chapel Hill
Prateek Yadav
PhD, University of North Carolina Chapel Hill
Mikhail Yurochkin
Staff AI Scientist, IFM MBZUAI, ex MIT-IBM Watson AI Lab
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up