Mingli Song

19

Papers

47

Total Citations

Papers (19)

Training-Free Pretrained Model Merging

PatchDPO: Patch-level DPO for Finetuning-free Personalized Image Generation

Dataset Ownership Verification in Contrastive Pre-trained Models

Holistic Semantic Representation for Navigational Trajectory Generation

Angle Robustness Unmanned Aerial Vehicle Navigation in GNSS-Denied Scenarios

D^2-DPM: Dual Denoising for Quantized Diffusion Probabilistic Models

Dataset Ownership Verification for Pre-trained Masked Models

Agent-Aware Training for Agent-Agnostic Action Advising in Deep Reinforcement Learning

Disentangled Table-Graph Representation for Interpretable Transmission Line Fault Location

Spatial-Temporal Forgery Trace based Forgery Image Identification

Global Attribute-Association Pattern Aggregation for Graph Fraud Detection

Association Pattern-enhanced Molecular Representation Learning

Cooperative Policy Agreement: Learning Diverse Policy for Offline MARL

Non-stationary Online Convex Optimization with Arbitrary Delays

Progressive Feature Self-Reinforcement for Weakly Supervised Semantic Segmentation

Sampling-Resilient Multi-Object Tracking

Boosting MLLM Reasoning with Text-Debiased Hint-GRPO

Training Data Provenance Verification: Did Your Model Use Synthetic Data from My Generative Model for Training?

Tree of Preferences for Diversified Recommendation

NeurIPS 2025arXiv