Yonggang Zhang

Enhancing LLMs for Knowledge Base Question Answering by Chain-of-Decomposition

Detecting Generated Images via Machine Unlearning

Semantic Voting: A Self-Evaluation-Free Approach for Efficient LLM Self-Improvement on Unverifiable Open-ended Tasks

FRAG: Filtering Noise Using Snippet-Level Query Relevance

R²AG: Learning to Reason, Retrieve, and Self-Evolve through a Multi-Branch Retrieval Tree

Learning Fast and Slow: Addressing Task-Imbalanced Continual Learning with Dual-Speed Adaptation

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

MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection

Detecting Generated Images by Fitting Natural Image Distributions

Epistemic Uncertainty for Generated Image Detection

Towards Generalizable Detector for Generated Image

Unlocker: Disentangle the Deadlock of Learning between Label-noisy and Long-tailed Data

FedGPS: Statistical Rectification Against Data Heterogeneity in Federated Learning

Hot-pluggable Federated Learning: Bridging General and Personalized FL via Dynamic Selection

Leveraging Submodule Linearity Enhances Task Arithmetic Performance in LLMs

Intention Model: A Novel Explanation for In-context Learning

Overfitting: An Unexpected Asset in AI‐Generated Image Detection

Enhancing Target-unspecific Tasks through a Features Matrix

Detecting Discrepancies Between Generated and Natural Images Using Uncertainty

Prompt Reverse Learning: Enhancing Visual Language Models for Rare Image Recognition

Deciphering and Enhancing Commonsense Reasoning in LLMs from the Perspective of Intrinsic Factual Knowledge Retrieval

Strengthening Federated Learning: Surrogate Data-Guided Aggregation for Robust Backdoor Defense

Consistency Verification for Detecting AI-Generated Images

Safeguarding System Prompts: A Surrogate-Based Defense Against Injection Attacks

Unveiling the Flow of Input-label Mappings for In-context Learning