1 citations · 1 across the 15 of their papers we have counts for
7 papers · 1 filter
Do LLMs Truly Generalize in the Molecular Domain? A Perturbation-Based Analysis
Jiatong Li, Weida Wang, Changmeng Zheng +4
Large Language Models (LLMs) have recently shown promise in molecular discovery, yet a gap remains between their probabilistic nature over discrete sequential tokens and the rigid…
Energy-Guided Generative Modeling for Low-Energy Molecular Structure Discovery
Guikun Xu, Xiaohan Yi, Ziqiao Meng +2
Exploring molecular energy landscapes and identifying ground-state conformations are central challenges in computational chemistry. However, generating diverse low-energy conformer…
Question-Adaptive Graph Learning for Multi-hop Retrieval Augmented Generation
Yuchen Yan, Peiyan Zhang, Zhihua Liu +4
Retrieval-augmented generation (RAG) has demonstrated its ability to enhance Large Language Models (LLMs) by integrating external knowledge sources. However, multi-hop questions, w…
CrystalDiT: A Diffusion Transformer for Crystal Generation
Xiaohan Yi, Guikun Xu, Xi Xiao +4
We present CrystalDiT, a diffusion transformer for crystal structure generation that achieves state-of-the-art performance by challenging the trend of architectural complexity. Ins…
Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization
Qingyang Zhang, Haitao Wu, Changqing Zhang +2
Existing methods to enhance the reasoning capability of large language models predominantly rely on supervised fine-tuning (SFT) followed by reinforcement learning (RL) on reasonin…
One Fits All: Learning Fair Graph Neural Networks for Various Sensitive Attributes
Yuchang Zhu, Jintang Li, Yatao Bian +2
Recent studies have highlighted fairness issues in Graph Neural Networks (GNNs), where they produce discriminatory predictions against specific protected groups categorized by sens…
Rethinking and Simplifying Bootstrapped Graph Latents
Wangbin Sun, Jintang Li, Liang Chen +3
Graph contrastive learning (GCL) has emerged as a representative paradigm in graph self-supervised learning, where negative samples are commonly regarded as the key to preventing m…