Tag
SAGE introduces a CLIP-based framework for time series forecasting that combines temporal, textual, and visual semantic information to improve accuracy, achieving state-of-the-art performance on long-term benchmarks.
This paper proposes CURL, a plug-in adapter that uses estimator uncertainty to allocate pretrained LLM semantic capacity for improving heterogeneous treatment effect (CATE) estimation. It introduces two role-conditioned prompts to construct assignment- and heterogeneity-oriented representations, improving ten host learners on four benchmarks.
Proposes SSDAU, a structured semantic data augmentation method for joint entity and relation extraction that preserves semantic structure by segmenting text based on entity labels and using BERTTopic for topic consistency, significantly outperforming existing augmentation methods.