Hui Wang

SecP-Tuning: Efficient Privacy-Preserving Prompt Tuning for Large Language Models via MPC

GEPO: Group Expectation Policy Optimization for Stable Heterogeneous Reinforcement Learning

Map as a Prompt: Learning Multi-Modal Spatial-Signal Foundation Models for Cross-scenario Wireless Localization

TS-DDAE: A Novel Temporal-Spectral Denoising Diffusion AutoEncoder for Wireless Signal Recognition Model Pre-training

Towards Human-Preferences Chinese Rewriting Evaluation: Prompt-Based Scoring with Large Language Models

Meta-Memory for Large Language Models

Simple Convergence Proof of Adam From a Sign-like Descent Perspective

AdmTree: Compressing Lengthy Context with Adaptive Semantic Trees

Centrality-guided Pre-training for Graph

Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent

SoftSignSGD(S3): An Enhanced Optimize for Practical DNN Training and Loss Spikes Minimization Beyond Adam