15 citations · 15 across the 10 of their papers we have counts for
5 papers · 1 filter
Semifactual Credit-Augmented Policy Optimization
Junshu Pan, Zhizhang Fu, Shulin Huang +5
Reinforcement learning with verifiable rewards (RLVR) has improved the reasoning capabilities of large language models (LLMs), yet their predictions remain sensitive to task-irrele…
Mitigating Position Bias in Transformers via Layer-Specific Positional Embedding Scaling
Changze Lv, Zhenghua Wang, Yiran Ding +9
Large Language Models (LLMs) still struggle with the ``lost-in-the-middle'' problem, where critical information located in the middle of long-context inputs is often underrepresent…
GEESE: Genotype-aware End-to-End Spatio-temporal Embedding for Behavioral Phenotyping
Yiran Ding, Yuen Gao, Chunqi Qian +1
Behavioral phenotyping of genetic animal models currently requires labor-intensive manual feature engineering that limits reproducibility and scalability. We present GEESE, an end-…
AutoFigure-Edit: Generating Editable Scientific Illustration
Zhen Lin, Qiujie Xie, Minjun Zhu +10
High-quality scientific illustrations are essential for communicating complex scientific and technical concepts, yet existing automated systems remain limited in editability, styli…
Is Meta-Path Attention an Explanation? Evidence of Alignment and Decoupling in Heterogeneous GNNs
Maiqi Jiang, Noman Ali, Yiran Ding +1
Meta-path-based heterogeneous graph neural networks aggregate over meta-path-induced views, and their semantic-level attention over meta-path channels is widely used as a narrative…