Yu Zhang(张宇)

Results 5 issues of Yu Zhang(张宇)

I am reaching out to seek assistance regarding my attempts to reproduce the experimental results mentioned in the GreaseLM paper, specifically concerning the utilization of the Aristo-RoBERTa encoder on the...

Hi there, We just proposed Question-guided Knowledge Graph Re-scoring and Injection for Knowledge Graph Question Answering in EMNLP 2024 Findings. This paper proposes modeling and denoising retrieved knowledge from KG...

In the InternVL2.5-MPO paper, the author mentioned that cot is not as effective as direct answer for MLLM. I wonder why cot is so bad for MLLM compared to LLM?...

Nice work! The Vision Token Merger method mentioned in TinyChart has been similarly explored in works like TextHawk and DocKylin. However, in those works, the merger is typically performed after...

Hi, in this paper, we systematically evaluate modality preference, which is the tendency to favor one modality over another when making decisions based on multimodal conflicting evidence. we propose a...