collaborators

11 papers

cs.LG2026

Boundary Embedding Shaping with Adaptive Contrastive Learning for Graph Structural Disentanglement

Jiaqing Chen, Zidu Yin, Yichao Cai +4

Graph neural networks (GNNs) excel at aggregating neighbor information for classification, yet their performance is hindered by graph structural entanglement, where spurious correl…

cs.LG2026

The Geometric Mechanics of Contrastive Representation Learning: Alignment Potentials, Entropic Dispersion, and Cross-modal Divergence

Yichao Cai, Zhen Zhang, Yuhang Liu +1

While InfoNCE underlies modern contrastive learning, its geometric mechanisms remain under-characterized beyond the canonical alignment--uniformity decomposition. We develop a meas…

cs.LG2026

Learning Latent Dynamical Causal Processes for Single-Cell Perturbation Prediction

Wenkang Jiang, Yuhang Liu, Erdun Gao +3

Single-cell perturbation prediction aims to infer how cells respond to unseen interventions and to achieve out-of-distribution (OOD) generalization, providing a computational route…

cs.LG2026

S2Aligner: Pair-Efficient and Transferable Pre-Training for Sparse Text-Attributed Graphs

Yuhan Wang, Haopeng Zhang, Yibo Ding +6

Pre-training on text-attributed graphs (TAGs) is central to building transferable graph foundation models, where LLM-as-Aligner methods align graph and text representations through…

cs.LG2026

What Makes a Representation Good for Single-Cell Perturbation Prediction?

Wenkang Jiang, Yuhang Liu, Yichao Cai +5

Single-cell perturbation modeling is fundamental for understanding and predicting cellular responses to genetic perturbations. However, existing approaches, from causal representat…

cs.LG2026

I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data?

Yuhang Liu, Dong Gong, Yichao Cai +6

Recent empirical evidence shows that LLM representations encode human-interpretable concepts. Nevertheless, the mechanisms by which these representations emerge remain largely unex…