5 papers
DANGERLENS: Probing Dangerous Representations Hidden by Safety Alignment
Tianzhuo Yang, Shaoheng Yan, Lin Lu +5
Safety alignment teaches language models to refuse harmful requests, yet the internal accessibility of hazardous concepts can retain traces of earlier training. Can checkpoints wit…
Toward Better Geometric Representations for Molecule Generative Models
Shaoheng Yan, Zian Li, Cai Zhou +3
Geometric representation-conditioned molecule generation provides an effective paradigm that decouples molecule representation modeling from structure generation. By decoupling mol…
FlashMol: High-Quality Molecule Generation in as Few as Four Steps
Xinyuan Wei, Zian Li, Shaoheng Yan +2
Generating chemically valid 3D molecular conformations is critical for computational drug discovery. Classical diffusion-based models like GeoLDM perform well but require hundreds…
LLMs Know More Than Words: A Genre Study with Syntax, Metaphor & Phonetics
Weiye Shi, Zhaowei Zhang, Shaoheng Yan +1
Large language models (LLMs) demonstrate remarkable potential across diverse language related tasks, yet whether they capture deeper linguistic properties, such as syntactic struct…
GeoRecon: Graph-Level Representation Learning for 3D Molecules via Reconstruction-Based Pretraining
Shaoheng Yan, Zian Li, Muhan Zhang
The pretraining-finetuning paradigm has powered major advances in domains such as natural language processing and computer vision, with representative examples including masked lan…