Xinyu Zhao

FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoning

Select the Key, Then Generate the Rest: Improving Multi-Modal Learning with Limited Data Budget

Learning Flexible Large Multimodal Models with Arbitrary Modality Combinations

Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction

$UQ-Merge$: UNCERTAINTY GUIDED MULTIMODAL LARGE LANGUAGE MODEL MERGING

Understanding Prejudice and Fidelity of Diverge-to-Converge Multi-Agent Systems

Beyond Fixed Resolution: Enhancing VLLMs with Adaptive Input Scaling

GraphRCG: Self-Conditioned Graph Generation