AI.info

Yan Wang

Explore Yan Wang on AI.info.

• ProxyFL: A Proxy-Guided Framework for Federated Semi-Supervised Learning
• PVminer: A Domain-Specific Tool to Detect the Patient Voice in Patient Generated Data
• Eliminating VAE for Fast and High-Resolution Generative Detail Restoration
• From Representational Complementarity to Dual Systems: Synergizing VLM and Vision-Only Backbones for End-to-End Driving
• Advancing General-Purpose Reasoning Models with Modular Gradient Surgery
• MIRROR: Manifold Ideal Reference ReconstructOR for Generalizable AI-Generated Image Detection
• Re-understanding Graph Unlearning through Memorization
• TGIF: Text-Guided Layer Fusion Mitigates Hallucination in Multimodal LLMs
• The Illusion of Specialization: Unveiling the Domain-Invariant "Standing Committee" in Mixture-of-Experts Models
• Beyond Artifacts: Real-Centric Envelope Modeling for Reliable AI-Generated Image Detection
• Benchmarking and Enhancing VLM for Compressed Image Understanding
• GaussianImage++: Boosted Image Representation and Compression with 2D Gaussian Splatting
• Latent Chain-of-Thought World Modeling for End-to-End Driving
• DualFete: Revisiting Teacher-Student Interactions from a Feedback Perspective for Semi-supervised Medical Image Segmentation
• Commonality in Few: Few-Shot Multimodal Anomaly Detection via Hypergraph-Enhanced Memory
• Addressing Mark Imbalance in Integration-free Neural Marked Temporal Point Processes
• SparseWorld: A Flexible, Adaptive, and Efficient 4D Occupancy World Model Powered by Sparse and Dynamic Queries
• Video-STR: Reinforcing MLLMs in Video Spatio-Temporal Reasoning with Relation Graph
• FinAuditing: A Financial Taxonomy-Structured Multi-Document Benchmark for Evaluating LLMs