29 citations · 30 across the 4 of their papers we have counts for
6 papers
Score Centering Stabilizes Off-policy Reinforcement Learning
Martin Marek, Max Ryabinin
Reinforcement learning (RL) of large language models is notoriously sensitive to small differences between training and inference engines, often referred to as the training-inferen…
Forgetting in Language Models: Capacity, Optimization, and Self-Generated Replay
Martin Marek, Dongkyu Cho, Shikai Qiu +3
Models trained on a new task typically degrade on prior tasks, a phenomenon known as forgetting. Traditionally, mitigating forgetting has required replaying stored exemplars from p…
Small Batch Size Training for Language Models: When Vanilla SGD Works, and Why Gradient Accumulation Is Wasteful
Martin Marek, Sanae Lotfi, Aditya Somasundaram +2
Conventional wisdom dictates that small batch sizes make language model pretraining and fine-tuning unstable, motivating gradient accumulation, which trades off the number of optim…
Can a Confident Prior Replace a Cold Posterior?
Martin Marek, Brooks Paige, Pavel Izmailov
Benchmark datasets used for image classification tend to have very low levels of label noise. When Bayesian neural networks are trained on these datasets, they often underfit, misr…
Image-Based Parking Space Occupancy Classification: Dataset and Baseline
Martin Marek
We introduce a new dataset for image-based parking space occupancy classification: ACPDS. Unlike in prior datasets, each image is taken from a unique view, systematically annotated…
An Annotation Saved is an Annotation Earned: Using Fully Synthetic Training for Object Instance Detection
Stefan Hinterstoisser, Olivier Pauly, Hauke Heibel +2
Deep learning methods typically require vast amounts of training data to reach their full potential. While some publicly available datasets exists, domain specific data always need…