9 citations · 9 across the 5 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
PACT: Preserving Anchored Cores in Task-vectors for Model Merging
Ningyuan Shi, Zhipeng Zhou, Hao Wang +2
Model merging has emerged as a training-free alternative to multi-task learning, aiming to combine multiple task-specific fine-tuned models into a single multi-task model. Most exi…
cs.LG2021
Counterfactual Adversarial Learning with Representation Interpolation
Wei Wang, Boxin Wang, Ning Shi +4
Deep learning models exhibit a preference for statistical fitting over logical reasoning. Spurious correlations might be memorized when there exists statistical bias in training da…