activity
20242026
most citedThe Pitfalls of Memorization: When Memorization Hurts Generalization

1 citations · 1 across the 4 of their papers we have counts for

collaborators

7 papers

cs.LG2026

ReasonCACHE: Teaching LLMs To Reason Without Weight Updates

Sharut Gupta, Phillip Isola, Stefanie Jegelka +4

Can Large language models (LLMs) learn to reason without any weight update and only through in-context learning (ICL)? ICL is strikingly sample-efficient, often learning from only…

cs.LG2025

Why Less is More (Sometimes): A Theory of Data Curation

Elvis Dohmatob, Mohammad Pezeshki, Reyhane Askari-Hemmat

This paper introduces a theoretical framework to resolve a central paradox in modern machine learning: When is it better to use less data? This question has become critical as clas…

cs.LG2025

Iterative Amortized Inference: Unifying In-Context Learning and Learned Optimizers

Sarthak Mittal, Divyat Mahajan, Guillaume Lajoie +1

Modern learning systems increasingly rely on amortized learning - the idea of reusing computation or inductive biases shared across tasks to enable rapid generalization to novel pr…

cs.CL2025

Unveiling Simplicities of Attention: Adaptive Long-Context Head Identification

Konstantin Donhauser, Charles Arnal, Mohammad Pezeshki +3

The ability to process long contexts is crucial for many natural language processing tasks, yet it remains a significant challenge. While substantial progress has been made in enha…

cs.LG2025

Steering Large Language Model Activations in Sparse Spaces

Reza Bayat, Ali Rahimi-Kalahroudi, Mohammad Pezeshki +2

A key challenge in AI alignment is guiding large language models (LLMs) to follow desired behaviors at test time. Activation steering, which modifies internal model activations dur…

cs.LG2025

Improving the Scaling Laws of Synthetic Data with Deliberate Practice

Reyhane Askari-Hemmat, Mohammad Pezeshki, Elvis Dohmatob +6

Inspired by the principle of deliberate practice in human learning, we propose Deliberate Practice for Synthetic Data Generation (DP), a novel framework that improves sample effici…