Yatao Bian

Assistant Professor@National University of Singapore·新加坡·OpenReview

研究方向

Machine learning · AI for Science · Large language models · Graph-language models · Graph neural networks · OOD robustness · Energy-based learning · Optimization · Drug AI

Yatao Bian

Learning to Learn with Contrastive Meta-Objective

3D-GSRD: 3D Molecular Graph Auto-Encoder with Selective Re-mask Decoding

Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization

InversionGNN: A Dual Path Network for Multi-Property Molecular Optimization

COME: Test-time Adaption by Conservatively Minimizing Entropy

Erasing Concept Combination from Text-to-Image Diffusion Model

Hierarchical Graph Tokenization for Molecule-Language Alignment

Measuring Diversity in Synthetic Datasets

GUMP: Alleviating Oversquashing with Unitary Message Passing

UniMoT: Unified Molecule-Text Language Model with Discrete Token Representation

Improving Molecule-Language Alignment with Hierarchical Graph Tokenization

Evaluating Diversity of LLM-generated Datasets: A Classification Perspective

ConML: A Universal Meta-Learning Framework with Task-Level Contrastive Learning

The Best of Both Worlds: On the Dilemma of Out-of-distribution Detection

Interpretable and Generalizable Graph Neural Networks via Subgraph Multilinear Extension

EBMDock: Neural Probabilistic Protein-Protein Docking via a Differentiable Energy Model

Enhancing Neural Subset Selection: Integrating Background Information into Set Representations

Trading-off Multiple Properties for Molecular Optimization

UniMoT: Unified Molecule-Text Language Model with Discrete Token Representation

Learning to Learn with Contrastive Meta-Objective