Chengqi Zhang

Paradigm Shift of GNN Explainer from Label Space to Prototypical Representation Space

Estimating Time Series Foundation Model Transferability via In-Context Learning

JailbreakLoRA: Your Downloaded LoRA from Sharing Platforms might be Unsafe

Symmetry-Guaranteed Prediction of High-Order Tensor Properties for Crystalline Materials via Irreducible Decomposition

Combining-on-Graph: Structured Reasoning of LLMs with Knowledge Graph

WALL-E: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents

Biologically Plausible Brain Graph Transformer

Efficient Personalized Adaptation for Physiological Signal Foundation Model

Rethinking The Reliability of Representation Engineering in Large Language Models

Exploring the Discriminative Capability of LLMs in In-context Learning

Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning

WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents