Ming Li

36

Papers

239

Total Citations

Papers (36)

ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback

When Hypergraph Meets Heterophily: New Benchmark Datasets and Baseline

Synthetic-to-Real Self-supervised Robust Depth Estimation via Learning with Motion and Structure Priors

MDP3: A Training-free Approach for List-wise Frame Selection in Video-LLMs

SuperEdit: Rectifying and Facilitating Supervision for Instruction-Based Image Editing

EventGPT: Event Stream Understanding with Multimodal Large Language Models

EEE-Bench: A Comprehensive Multimodal Electrical And Electronics Engineering Benchmark

DHAKR: Learning Deep Hierarchical Attention-Based Kernelized Representations for Graph Classification

ML-GOOD: Towards Multi-Label Graph Out-Of-Distribution Detection

PVChat: Personalized Video Chat with One-Shot Learning

AUC Optimization from Multiple Unlabeled Datasets

HiFi-Portrait: Zero-shot Identity-preserved Portrait Generation with High-fidelity Multi-face Fusion

L3A: Label-Augmented Analytic Adaptation for Multi-Label Class Incremental Learning

SPADE: Spatial-Aware Denoising Network for Open-vocabulary Panoptic Scene Graph Generation with Long- and Local-range Context Reasoning

ProJudge: A Multi-Modal Multi-Discipline Benchmark and Instruction-Tuning Dataset for MLLM-based Process Judges

Deep Hypergraph Neural Networks with Tight Framelets

Slice-and-Pack: Tailoring Deep Models for Customized Requirements

FedVLA: Federated Vision-Language-Action Learning with Dual Gating Mixture-of-Experts for Robotic Manipulation

How Universal Polynomial Bases Enhance Spectral Graph Neural Networks: Heterophily, Over-smoothing, and Over-squashing

QBMK: Quantum-based Matching Kernels for Un-attributed Graphs

SphereFace: Deep Hypersphere Embedding for Face Recognition

Class Balanced Adaptive Pseudo Labeling for Federated Semi-Supervised Learning

FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation

Self-Supervised Geometric Features Discovery via Interpretable Attention for Vehicle Re-Identification and Beyond

STPrivacy: Spatio-Temporal Privacy-Preserving Action Recognition

AlignDet: Aligning Pre-training and Fine-tuning in Object Detection

Multi-Granularity Distillation Scheme towards Lightweight Semi-Supervised Semantic Segmentation

MODE: Multi-View Omnidirectional Depth Estimation with 360° Cameras

Ambiguity-Aware Abductive Learning

EFTViT: Efficient Federated Training of Vision Transformers with Masked Images on Resource-Constrained Clients

Multimodal Contrastive Learning for Cybersickness Recognition Using Brain Connectivity Graph Representation

EEG2Gaussian: Decoding and Visualizing Visual-Evoked EEG for VR Scenes Using 3D Gaussian Splatting

Zero-shot Video Moment Retrieval via Off-the-shelf Multimodal Large Language Models

Path Integral Based Convolution and Pooling for Graph Neural Networks

Few-Shot Non-Parametric Learning with Deep Latent Variable Model

When to Trust Your Simulator: Dynamics-Aware Hybrid Offline-and-Online Reinforcement Learning