Ming Yan

21

Papers

784

Total Citations

Papers (21)

mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration

Hallucination Augmented Contrastive Learning for Multimodal Large Language Model

WritingBench: A Comprehensive Benchmark for Generative Writing

NeurIPS 2025arXiv

RELI11D: A Comprehensive Multimodal Human Motion Dataset and Method

SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference Optimization

TiMix: Text-Aware Image Mixing for Effective Vision-Language Pre-training

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization

Learning Trajectory-Word Alignments for Video-Language Tasks

BUS: Efficient and Effective Vision-Language Pre-Training with Bottom-Up Patch Summarization.

Shifting More Attention to Visual Backbone: Query-Modulated Refinement Networks for End-to-End Visual Grounding

ClimbingCap: Multi-Modal Dataset and Method for Rock Climbing in World Coordinate

RoDA: Robust Domain Alignment for Cross-Domain Retrieval Against Label Noise

DiDA: Disambiguated Domain Alignment for Cross-Domain Retrieval with Partial Labels

CIMI4D: A Large Multimodal Climbing Motion Dataset Under Human-Scene Interactions

HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training

Improved Visual Fine-tuning with Natural Language Supervision

Manifold denoising by Nonlinear Robust Principal Component Analysis

ErrorCompensatedX: error compensation for variance reduced algorithms

Communication-Efficient Topologies for Decentralized Learning with $O(1)$ Consensus Rate

FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction

$D^2$: Decentralized Training over Decentralized Data