collaborators

6 papers

cs.LG2026

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training

Rachit Bansal, Clara Mohri, Tian Qin +2

The standard LLM training pipeline applies reinforcement learning (RL) only after pre-training and supervised fine-tuning (SFT). We question this status quo by training a LLM from…

cs.LG2026

Cost-Aware Learning

Clara Mohri, Amir Globerson, Haim Kaplan +2

We consider the problem of Cost-Aware Learning, where sampling different components of a finite-sum objective incurs different costs. The objective is to reach a target error while…

cs.SE2026

GenAI for Systems: Recurring Challenges and Design Principles from Software to Silicon

Arya Tschand, Chenyu Wang, Zishen Wan +21

Generative AI is reshaping how computing systems are designed, optimized, and built, yet research remains fragmented across software, architecture, and chip design communities. Thi…

cs.LG2025

Budgeted Multiple-Expert Deferral

Giulia DeSalvo, Clara Mohri, Mehryar Mohri +1

Learning to defer uncertain predictions to costly experts offers a powerful strategy for improving the accuracy and efficiency of machine learning systems. However, standard traini…

cs.LG2025

Fast Inference via Hierarchical Speculative Decoding

Clara Mohri, Haim Kaplan, Tal Schuster +2

Transformer language models generate text autoregressively, making inference latency proportional to the number of tokens generated. Speculative decoding reduces this latency witho…

cs.LG2025

Mixture of Parrots: Experts improve memorization more than reasoning

Samy Jelassi, Clara Mohri, David Brandfonbrener +7

The Mixture-of-Experts (MoE) architecture enables a significant increase in the total number of model parameters with minimal computational overhead. However, it is not clear what…