Weiqiang Wang

FakeXplain: AI-Generated Image Detection via Human-Aligned Grounded Reasoning

Veritas: Generalizable Deepfake Detection via Pattern-Aware Reasoning

Measuring Audio's Impact on Correctness: Audio-Contribution-Aware Post-Training of Large Audio Language Models

Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models

Rethinking Scale: How Multi-Agent Collaboration Enables Smaller Models to Rival GPT-4 in Video Understanding

JUMP: JOINTLY UTILIZING MISSINGNESS FOR PREDICTION ON INCOMPLETE TABULAR DATA

Zoom-In to Sort AI-Generated Images Out

TraPO: A Semi-Supervised Reinforcement Learning Framework for Boosting LLM Reasoning

SHAP-PGD: A Realistic Adversarial Attack on Tabular Data by Unifying Interpretability and Semantic Consistency

DS-VTON: An Enhanced Dual-Scale Coarse-to-Fine Framework for Virtual Try-On

Online Test-Time Adaptation in Tabular Data with Minimal High-Certainty Samples

OW-VAP: Visual Attribute Parsing for Open World Object Detection

Stochastic Layer-Wise Shuffle for Improving Vision Mamba Training

BiQAP: Neural Bi-level Optimization-based Framework for Solving Quadratic Assignment Problems

Interactions Exhibit Clustering Rhythm: A Prevalent Observation for Advancing Temporal Link Prediction

Mixture-of-Queries Transformer: Camouflaged Instance Segmentation via Queries Cooperation and Frequency Enhancement

Stochastic Layer-Wise Shuffle: A Good Practice to Improve Vision Mamba Training