Jian Wu

CoLA: Co-Calibrated Logit Adjustment for Long-Tailed Semi-Supervised Learning

OptimSyn: Influence-Guided Rubrics Optimization for Synthetic Data Generation

MoL: Adaptive Mixture-of-Length Reasoning for Efficient Question Answering with Context

PostAlign: Multimodal Grounding as a Corrective Lens for MLLMs

Large Language Models Could Be Rote Learners

STORM: Benchmarking Visual Rating of MLLMs with a Comprehensive Ordinal Regression Dataset

Small Models are LLM Knowledge Triggers for Medical Tabular Prediction

Align-VL: Can Being Modest Help in the Alignment of Vision-Language Models?

AnyECG: Foundational Models for Electrocardiogram Analysis