Zheng Liu

13

Papers

630

Total Citations

Papers (13)

OmniGen: Unified Image Generation

Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding

MLVU: Benchmarking Multi-task Long Video Understanding

Making Text Embedders Few-Shot Learners

STI-Bench: Are MLLMs Ready for Precise Spatial-Temporal World Understanding?

Unveiling the Ignorance of MLLMs: Seeing Clearly, Answering Incorrectly

Noisy Label Calibration for Multi-View Classification

Enhancing Spectral GNNs: From Topology and Perturbation Perspectives

Fuzzy Multimodal Learning for Trusted Cross-modal Retrieval

MMCR: Benchmarking Cross-Source Reasoning in Scientific Papers

Learning to See in the Extremely Dark

You Should Learn to Stop Denoising on Point Clouds in Advance

MRR-FV: Unlocking Complex Fact Verification with Multi-Hop Retrieval and Reasoning