2 papers
cs.LG2026
Post-Training Science for Supervised Fine-Tuning
Charles O'Neill, Mudith Jayasekara, Harry Partridge
Every supervised fine-tuning run forces the same chain of decisions, such as learning rate, batch size, LoRA or full fine-tuning, how many epochs, which optimiser, and what data to…
cs.LG2026
Still: Amortized KV Cache Compaction in a Single Forward Pass
Charles O'Neill, Alex Sandomirsky, Harry Partridge +2
The KV cache is the memory bottleneck of long-horizon language model deployment. Practically, a deployable compactor must be lightweight enough to call during inference, expressive…