6 papers · 1 filter
RxnNano:Training Compact LLMs for Chemical Reaction and Retrosynthesis Prediction via Hierarchical Curriculum Learning
Ran Li, Shimin Di, Haowei LI +4
Chemical reaction prediction is pivotal for accelerating drug discovery and synthesis planning. Despite advances in data-driven models, current approaches are hindered by an overem…
Beyond Model Base Retrieval: Weaving Knowledge to Master Fine-grained Neural Network Design
Jialiang Wang, Hanmo Liu, Shimin Di +4
Designing high-performance neural networks for new tasks requires balancing optimization quality with search efficiency. Current methods fail to achieve this balance: neural archit…
Class-aware and Augmentation-free Contrastive Learning from Label Proportion
Jialiang Wang, Ning Zhang, Shimin Di +2
Learning from Label Proportion (LLP) is a weakly supervised learning scenario in which training data is organized into predefined bags of instances, disclosing only the class label…
Proficient Graph Neural Network Design by Accumulating Knowledge on Large Language Models
Jialiang Wang, Hanmo Liu, Shimin Di +4
High-level automation is increasingly critical in AI, driven by rapid advances in large language models (LLMs) and AI agents. However, LLMs, despite their general reasoning power,…
Cross-domain-aware Worker Selection with Training for Crowdsourced Annotation
Yushi Sun, Jiachuan Wang, Peng Cheng +3
Annotation through crowdsourcing draws incremental attention, which relies on an effective selection scheme given a pool of workers. Existing methods propose to select workers base…
Learning from Emergence: A Study on Proactively Inhibiting the Monosemantic Neurons of Artificial Neural Networks
Jiachuan Wang, Shimin Di, Lei Chen +1
Recently, emergence has received widespread attention from the research community along with the success of large-scale models. Different from the literature, we hypothesize a key…