Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Information-Theoretic Requirements for Gradient-Based Task Affinity Estimation in Multi-Task Learning
Jasper Zhang, Bryan Cheng
Multi-task learning shows strikingly inconsistent results -- sometimes joint training helps substantially, sometimes it actively harms performance -- yet the field lacks a principl…
cs.LG2026
Single-Position Intervention Fails: Distributed Output Templates Drive In-Context Learning
Bryan Cheng, Jasper Zhang
Understanding how large language models encode task identity from few-shot demonstrations is a central open problem in mechanistic interpretability. Prior work uses linear probing…
cs.LG2026
When Does Context Help? A Systematic Study of Target-Conditional Molecular Property Prediction
Bryan Cheng, Jasper Zhang
We present the first systematic study of when target context helps molecular property prediction, evaluating context conditioning across 10 diverse protein families, 4 fusion archi…