4 papers
Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs
Yue Cheng, Jiajun Zhang, Xiaohui Gao +3
Reinforcement Learning with Verifiable Reward (RLVR) is empirically shown to notably enhance the reasoning performance of large language models (LLMs), particularly in mathematics…
Jacobian-Based Interpretation of Nonlinear Neural Encoding Model
Xiaohui Gao, Haoran Yang, Yue Cheng +4
In recent years, the alignment between artificial neural network (ANN) embeddings and blood oxygenation level dependent (BOLD) responses in functional magnetic resonance imaging (f…
LCGC: Learning from Consistency Gradient Conflicting for Class-Imbalanced Semi-Supervised Debiasing
Weiwei Xing, Yue Cheng, Hongzhu Yi +5
Classifiers often learn to be biased corresponding to the class-imbalanced dataset, especially under the semi-supervised learning (SSL) set. While previous work tries to appropriat…
LOCAL: Learning with Orientation Matrix to Infer Causal Structure from Time Series Data
Jiajun Zhang, Boyang Qiang, Xiaoyu Guo +3
Discovering the underlying Directed Acyclic Graph (DAG) from time series observational data is highly challenging due to the dynamic nature and complex nonlinear interactions betwe…