Matthew Riemer

PhD student, Computer Science, Montreal Institute for Learning Algorithms, University of Montreal, University of Montreal

Researcher, AI, International Business Machines

Joined

November 2016

Names

Matthew Riemer (Preferred)

Emails

****@us.ibm.com (Confirmed)

Personal Links

Google Scholar

DBLP

Career & Education History

PhD student

Computer Science, Montreal Institute for Learning Algorithms, University of Montreal, University of Montreal (mila.umontreal.ca)

2020 – Present

Researcher

AI, International Business Machines (ibm.com)

2012 – Present

Undergrad student

Engineering Physics, Cornell University (cornell.edu)

2008 – 2012

Advisors, Relations & Conflicts

PhD Advisor

Irina Rish

2020 – Present

Expertise

No areas of expertise listed

Publications

EpMAN: Episodic Memory AttentioN for Generalizing to Longer Contexts
Subhajit Chaudhury, Payel Das, Sarathkrishna Swaminathan, Georgios Kollias, Elliot Nelson, Khushbu Pahwa, Tejaswini Pedapati, Igor Melnyk, Matthew Riemer
- ACL
- Readers: Everyone
Emergent Reasoning via Recursive Latent Reinforcement Pretraining
Gopeshh Subbaraj, Istabrak Abbes, Artem Zholus, Matthew Riemer, Irina Rish, Sarath Chandar
- ICLR 2026 Workshop LLM Reasoning
- Readers: Everyone
Learning What to Remember for Non-Markovian Reinforcement Learning
Geraud Nangue Tasse, Matthew Riemer, Benjamin Rosman, Tim Klinger
- Submitted to ICLR 2026
- Readers: Everyone
Revisiting Replay and Gradient Alignment For Continual Pretraining of Large Language Models
Istabrak Abbes, Gopeshh Subbaraj, Matthew Riemer, Nizar Islah, Benjamin Thérien, Tsuguchika Tabaru, Hiroaki Kingetsu, Sarath Chandar, Irina Rish
- WiML @ NeurIPS 2025
- Readers: Everyone
The Shepherd Test: How Will SuperIntelligent Agents Balance Care and Control in Asymmetric Relationships?
Djallel Bouneffouf, Matthew Riemer, Kush R. Varshney
- NeurIPS 2025 LLM Evaluation Workshop Poster
- Readers: Everyone
Finding the FrameStack: Learning What to Remember for Non-Markovian Reinforcement Learning
Geraud Nangue Tasse, Matthew Riemer, Benjamin Rosman, Tim Klinger
- Finding the Frame (RLC 2025)
- Readers: Everyone
Position: Theory of Mind Benchmarks are Broken for Large Language Models
Matthew Riemer, Zahra Ashktorab, Djallel Bouneffouf, Payel Das, Miao Liu, Justin D. Weisz, Murray Campbell
- ICML 2025 Position Paper Track poster
- Readers: Everyone
Scopes of Alignment
Kush R. Varshney, Zahra Ashktorab, Djallel Bouneffouf, Matthew Riemer, Justin D. Weisz
- AAAI 2025 Workshop AIGOV Oral
- Readers: Everyone
Combining Domain and Alignment Vectors to Achieve Better Knowledge-Safety Trade-offs in LLMs
Megh Thakkar, Yash More, Quentin Fournier, Matthew Riemer, Pin-Yu Chen, Amal Zouaq, Payel Das, Sarath Chandar
- AFM 2024 Poster
- Readers: Everyone
Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous Inference
Matthew Riemer, Gopeshh Subbaraj, Glen Berseth, Irina Rish
- ICLR 2025 Poster
- Readers: Everyone

View all 41 publications

Co-Authors

View all 98 co-authors