works on

From the 1 of 12 linked papers with an AI index.

collaborators

12 papers

cs.LG2026

Regularizing modality contribution drift in multimodal continual learning

Zhen Zhang, Jielei Chu, Bin Liu +1

The paper identifies a decision-level shift called Modality Contribution Drift in multimodal continual learning and introduces a regularization method (CMCDR) that preserves modali…

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

Causally Sufficient and Necessary Feature Expansion for Class-Incremental Learning

Zhen Zhang, Jielei Chu, Jiangtao Hu +4

Current expansion-based methods for Class Incremental Learning (CIL) effectively mitigate catastrophic forgetting by freezing old features. However, such task-specific features lea…

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…

cs.LG2026

Beyond DAGs: A Latent Partial Causal Model for Multimodal Learning

Yuhang Liu, Zhen Zhang, Dong Gong +6

Directed Acyclic Graphs (DAGs) are a standard tool in causal modeling, but their suitability for capturing the complexity of large-scale multimodal data is questionable. In practic…