Eran Malach
28 papers · 2017–2025 · 6 venues · across top CS/AI venues
This profile combines several different researchers. Authors are keyed by name, and this name's papers fall into 7 separate collaboration groups - the largest holds only 43% of them. Pick the group below that matches the researcher you mean. How a shared name is split.
Achievements are not shown for a combined profile - each one describes a single researcher's record, which this is not.
Which Eran Malach?
3 groups of papers that share co-authors internally but none with each other - each most likely a different researcher. Pick one to see its papers.
with Samy Jelassi, Sham M. Kakade, David Brandfonbrener
10 papers
· 2022–2025
· NeurIPS, ICML, ICLR
Hide ▲
A New Perspective on Shampoo's Preconditioner
ICLR 2025
LoRA Soups: Merging LoRAs for Practical Skill Composition Tasks
COLING 2025
Mixture of Parrots: Experts improve memorization more than reasoning
ICLR 2025
The Role of Sparsity for Length Generalization in LLMs
ICML 2025
Universal Length Generalization with Turing Programs
ICML 2025
Repeat After Me: Transformers are Better than State Space Models at Copying
ICML 2024
The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains
NeurIPS 2024
Transcendence: Generative Models Can Outperform The Experts That Train Them
NeurIPS 2024
Pareto Frontiers in Deep Feature Learning: Data, Compute, Width, and Luck
NeurIPS 2023
Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit
NeurIPS 2022
4 papers whose co-authors appear nowhere else under this name
DON’T STOP ME NOW: EMBEDDING BASED SCHEDULING FOR LLMS
ICLR 2025
The Power of Random Features and the Limits of Distribution-Free Gradient Descent
ICML 2025
Auto-Regressive Next-Token Predictors are Universal Learners
ICML 2024
On the Power of Decision Trees in Auto-Regressive Language Modeling
NeurIPS 2024