Weizhi Zhang

Sample Lottery: Unsupervised Discovery of Critical Instances for LLM Reasoning

PRISM: Partial-label Relational Inference with Spatial and Spectral Cues

Learn to Merge: Meta-Learning for Adaptive Multi-Task Model Merging

PSG-Agent: Personality-Aware Safety Guardrail for LLM-based Agents

PersonaAgent: When Large Language Model Agents Meet Personalization at Test Time

Property-aware Reinforcement Learning with Retrieval Enhancement for Controllable 3D Molecule Generation

Text-guided Group Mixup with Canonical Mining for Imbalanced Graph Clustering

DeepResearchGuard: Deep Research with Open Domain Evaluation and Multi-Stage Guardrails for Safety

Dynamic Bundling with Large Language Models for Zero-Shot Inference on Text-Attributed Graphs

Beyond Directed Acyclic Computation Graph with Cyclic Neural Network

NODE-SAT: Temporal Graph Learning with Neural ODE-Guided Self-Attention