Mert Cemri

PhD student, University of California, Berkeley

Joined

May 2024

Names

Mert Cemri (Preferred)

Emails

****@berkeley.edu (Confirmed)

Personal Links

Google Scholar

Career & Education History

PhD student

University of California, Berkeley (berkeley.edu)

2023 – 2028

Advisors, Relations & Conflicts

PhD Advisor

Kannan Ramchandran

Present

PhD Advisor

Ion Stoica

Present

PhD Advisor

Alex Dimakis

Present

Expertise

Machine Learning

Present

Publications

COMPASS: A Multi-Turn Benchmark for Tool-Mediated Planning & Preference Optimization
Tian Qin, Haoping Bai, Ting-Yao Hu, Raviteja Vemulapalli, Hema Swetha Koppula, Bowen Jin, Zhiyang Xu, Mert Cemri, Jiarui Lu, Zirui Wang, Meng Cao
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
SPECS: Faster Test-Time Scaling through Speculative Drafts and Dynamic Switching
Mert Cemri, Nived Rajaraman, Rishabh Tiwari, Xiaoxuan Liu, Kurt Keutzer, Ion Stoica, Kannan Ramchandran, Ahmad Beirami, Ziteng Sun
- Submitted to ICLR 2026
- Readers: Everyone
Why Do Multi-Agent LLM Systems Fail?
Mert Cemri, Melissa Z Pan, Shuyi Yang, Lakshya A Agrawal, Bhavya Chopra, Rishabh Tiwari, Kurt Keutzer, Aditya Parameswaran, Dan Klein, Kannan Ramchandran, Matei Zaharia, Joseph E. Gonzalez, Ion Stoica
- NeurIPS 2025 LLM Evaluation Workshop Poster
- Readers: Everyone
SPECS: Faster Test-Time Scaling through Speculative Drafts
Mert Cemri, Nived Rajaraman, Rishabh Tiwari, Xiaoxuan Liu, Kurt Keutzer, Ion Stoica, Kannan Ramchandran, Ahmad Beirami, Ziteng Sun
- ES-FoMo III
- Readers: Everyone
Why Do Multi-Agent LLM Systems Fail?
Mert Cemri, Melissa Z Pan, Shuyi Yang, Lakshya A Agrawal, Bhavya Chopra, Rishabh Tiwari, Kurt Keutzer, Aditya Parameswaran, Dan Klein, Kannan Ramchandran, Matei Zaharia, Joseph E. Gonzalez, Ion Stoica
- NeurIPS 2025 Datasets and Benchmarks Track spotlight
- Readers: Everyone
Why Do Multiagent Systems Fail?
Melissa Z Pan, Mert Cemri, Lakshya A Agrawal, Shuyi Yang, Bhavya Chopra, Rishabh Tiwari, Kurt Keutzer, Aditya Parameswaran, Kannan Ramchandran, Dan Klein, Joseph E. Gonzalez, Matei Zaharia, Ion Stoica
- BuildingTrust
- Readers: Everyone
DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning
Hao Bai, Yifei Zhou, Mert Cemri, Jiayi Pan, Alane Suhr, Sergey Levine, Aviral Kumar
- ICML 2024 FM-Wild Workshop Poster
- Readers: Everyone
DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning
Hao Bai, Yifei Zhou, Mert Cemri, Jiayi Pan, Alane Suhr, Sergey Levine, Aviral Kumar
- MFM-EAI@ICML2024 Poster
- Readers: Everyone
Discrete Diffusion Posterior Sampling for Protein Design
Mert Cemri, Ajil Jalal, Kannan Ramchandran
- 2nd SPIGM @ ICML Poster
- Readers: Everyone
DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning
Yifei Zhou, Hao Bai, Mert Cemri, Jiayi Pan, Alane Suhr, Sergey Levine, Aviral Kumar
- AutoRL@ICML 2024
- Readers: Everyone

View all 11 publications

Co-Authors

View all 33 co-authors