3 citations · 3 across the 5 of their papers we have counts for
5 papers
TAC-Time: Texts as Channels For Multimodal Time Series Forecasting
Jiayi Liang, Xiaotian Gu, Xinyu Xie +2
Most existing time series forecasting methods rely solely on numerical observations, overlooking rich contextual information from auxiliary texts. Recent multimodal approaches atte…
Logic-Regularized Verifier Elicits Reasoning from LLMs
Xinyu Wang, Changzhi Sun, Lian Cheng +4
Verifiers are crucial components for enhancing modern LLMs' reasoning capability. Typicalverifiers require resource-intensive superviseddataset construction, which is costly and fa…
Stabilizing LLM Supervised Fine-Tuning via Explicit Distributional Control
Xinyu Wang, Changzhi Sun, Yuanbin Wu +1
Post-training large language models (LLMs) often suffers from catastrophic forgetting, where improvements on a target objective degrade previously acquired capabilities. Recent evi…
Length Generalization of Causal Transformers without Position Encoding
Jie Wang, Tao Ji, Yuanbin Wu +5
Generalizing to longer sentences is important for recent Transformer-based language models. Besides algorithms manipulating explicit position features, the success of Transformers…
Text2MDT: Extracting Medical Decision Trees from Medical Texts
Wei Zhu, Wenfeng Li, Xing Tian +6
Knowledge of the medical decision process, which can be modeled as medical decision trees (MDTs), is critical to build clinical decision support systems. However, the current MDT c…