Matthew Riemer

Computer Science · Physical Sciences

14h-index1.1kcitations68works0.12yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Reinforcement Learning in Robotics(26), Domain Adaptation and Few-Shot Learning(12), Topic Modeling(11), Natural Language Processing Techniques(5), Neural Networks and Applications(5)

Publications68 total

The Shepherd Test: How Will Super Intelligent Agents Balance Care and Control in Asymmetric Relationships?
Underline Science Inc.·2026Open Access
The Effectiveness of Approximate Regularized Replay for Efficient Supervised Fine-Tuning of Large Language Models
ArXiv.org·2025Open Access
The Effectiveness of Approximate Regularized Replay for Efficient Supervised Fine-Tuning of Large Language Models
arXiv (Cornell University)·2025Open Access
Beyond Sliding Windows: Learning to Manage Memory in Non-Markovian Environments
arXiv (Cornell University)·2025Open Access
Beyond Sliding Windows: Learning to Manage Memory in Non-Markovian Environments
ArXiv.org·2025Open Access
Revisiting Replay and Gradient Alignment for Continual Pre-Training of Large Language Models
arXiv (Cornell University)·2025Open Access
The Ultimate Test of Superintelligent AI Agents: Can an AI Balance Care and Control in Asymmetric Relationships?
arXiv (Cornell University)·2025Open Access
Handling Delay in Real-Time Reinforcement Learning
arXiv (Cornell University)·2025Open Access
Contextual Value Alignment
2025
EpMAN: Episodic Memory AttentioN for Generalizing to Longer Contexts
arXiv (Cornell University)·2025Open Access
Scopes of Alignment
arXiv (Cornell University)·2025Open Access
EpMAN: Episodic Memory AttentioN for Generalizing to Longer Contexts
2025
Combining Domain and Alignment Vectors Provides Better Knowledge-Safety Trade-offs in LLMs
2025Open Access
Position: Theory of Mind Benchmarks are Broken for Large Language Models
arXiv (Cornell University)·2024Open Access
Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous Inference
arXiv (Cornell University)·2024Open Access
Combining Domain and Alignment Vectors to Achieve Better Knowledge-Safety Trade-offs in LLMs
arXiv (Cornell University)·2024Open Access
A Deep Dive into the Trade-Offs of Parameter-Efficient Preference Alignment Techniques
arXiv (Cornell University)·2024Open Access
Contextual Moral Value Alignment Through Context-Based Aggregation
arXiv (Cornell University)·2024· 1 citedOpen Access
Balancing Context Length and Mixing Times for Reinforcement Learning at Scale
2024
A Deep Dive into the Trade-Offs of Parameter-Efficient Preference Alignment Techniques
2024· 2 citedOpen Access
page 1 of 4Next →

Frequent Co-authors

Gerald Tesauro(22), Tim Klinger(14), Dong Ki Kim(9), Miao Liu(9), Jonathan P. How(9), Miao Liu(7), Irina Rish(7), Murray Campbell(7), Ignacio Cases(6), Payel Das(6), Tyler Malloy(6), Chris R. Sims(6), Shayegan Omidshafiei(5), Golnaz Habibi(5), Sebastian Lopez-Cot(5), Khimya Khetarpal(4), Clemens Rosenbaum(4), Elham Khabiri(4), Djallel Bouneffouf(4), Robert Ajemian(3)