Authors

Michael Psenka

Publications 2

Preprint Open access

The Optimization Landscape of Learning Compacted Context Models

Thomas Villeneuve, Alex Sandomirsky, Charles O'Neill et al. · 2026

Many works approach continual learning through the lens of infinite context windows. As an agent puts more observation into context (concretely the KV cache), compacting said context is akin to direct memory manipulation, without affecting the base model's weights. Many works pose KV compaction as an optimization probl …

Preprint Open access

Fitting Vision Adapters at Frontier Scales

Jaehoon Lee, Harry Partridge, Mudith Jayasekara et al. · 2026

Training a small projector between a frozen vision encoder and language model is an established approach to multimodal learning. As the parameter count of language models scales dramatically, we revisit which vision capabilities this approach can add while keeping their pretrained weights fixed. Here we train a 50M par …

Co-authors