Mang Ye

Optimizing ID Consistency in Multimodal Large Models: Facial Restoration via Alignment, Entanglement, and Disentanglement

Reasoning Self-Evaluation via Trajectory Dynamics Modeling

Generalizable Diabetic Retinopathy Grading via Knowledge Constrained Concept Learning

ThanoRA: Task Heterogeneity-Aware Multi-Task Low-Rank Adaptation

FedSDR: Federated Graph Learning with Structural Noise Detection and Reconstruction

MAPO: MIXED ADVANTAGE POLICY OPTIMIZATION

Catch Your Emotion: Sharpening Emotion Perception in Multimodal Large Language Models

DKDR: Dynamic Knowledge Distillation for Reliability in Federated Learning

Unbiased Prototype Consistency Learning for Multi-Modal and Multi-Task Object Re-Identification

GHOST: Generalizable One-Shot Federated Graph Learning with Proxy-Based Topology Knowledge Retention

Energy-based Backdoor Defense Against Federated Graph Learning

Adaptive Re-calibration Learning for Balanced Multimodal Intention Recognition

$S^2$FGL: Spatial Spectral Federated Graph Learning

Learn from Downstream and Be Yourself in Multimodal Large Language Models Fine-Tuning

OASIS: One-Shot Federated Graph Learning via Wasserstein Assisted Knowledge Integration

Towards Robust Parameter-Efficient Fine-Tuning for Federated Learning

Rethinking Fair Federated Learning from Parameter and Client View

PC-Net: Weakly Supervised Compositional Moment Retrieval via Proposal-Centric Network

MoodAngels: A Retrieval-augmented Multi-agent Framework for Psychiatry Diagnosis

Backdoor Cleaning without External Guidance in MLLM Fine-tuning

Multi-order Orchestrated Curriculum Distillation for Model-Heterogeneous Federated Graph Learning

Federated Disentangled Tuning with Textual Prior Decoupling and Visual Dynamic Adaptation

SPMC: Self-Purifying Federated Backdoor Defense via Margin Contribution

EAGLES: Towards Effective, Efficient, and Economical Federated Graph Learning via Unified Sparsification

Be Confident: Uncovering Overfitting in MLLM Multi-Task Tuning

CAN: Leveraging Clients As Navigators for Generative Replay in Federated Continual Learning

FedPHA: Federated Prompt Learning for Heterogeneous Client Adaptation

Splitting with Importance-aware Updating for Heterogeneous Federated Learning with Large Language Models

MOTION: Multi-Sculpt Evolutionary Coarsening for Federated Continual Graph Learning

Honey: Harmonizing Progressive Federated Learning via Elastic Synergy across Different Training Blocks

Divide And Conquer: Efficiently Decoupling Consensus And Divergence For Federated Large Language Model Fine-Tuning