Weiping Wang

Dynamic Early Exit in Reasoning Models

Elastic MoE: Unlocking the Inference-Time Scalability of Mixture-of-Experts

FN-NOW: A Communication-Efficient Newton-Type Federated Learning via Low-Rank Hessian Approximation

NeedleInATable: Exploring Long-Context Capability of Large Language Models towards Long-Structured Tables

SSTAG: Structure-Aware Self-Supervised Learning Method for Text-Attributed Graphs

RealEra:Semantic-level Concept Erasure via Neighbor-Concept Mining