Linli Xu

6

Papers

1

Total Citations

Papers (6)

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models

Addressing Representation Collapse in Vector Quantized Models with One Linear Layer

S²MILE: Semantic-and-Structure-Aware Music-Driven Lyric Generation

Visual Hallucination Elevates Speech Recognition

HRVDA: High-Resolution Visual Document Assistant

Incorporating BERT into Parallel Sequence Decoding with Adapters