Yuliang Liu

ThinkOmni: Lifting Textual Reasoning to Omni-modal Scenarios via Guidance Decoding

Shuffle-R1: Efficient RL framework for Multimodal Large Language Models via Data-centric Dynamic Shuffle

VisuRiddles: Fine-grained Perception is a Primary Bottleneck for Multimodal Large Language Models in Abstract Visual Reasoning

SupGRPO: Enhancing GRPO with Matching-based Online SFT for Text Spotting

Mini-Monkey: Alleviating the Semantic Sawtooth Effect for Lightweight MLLMs via Complementary Image Pyramid

MSTAR: Box-free Multi-query Scene Text Retrieval with Attention Recycling

MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering

R-CoT: Reverse Chain-of-Thought Problem Generation for Geometric Reasoning in Large Multimodal Models

TextSquare: Scaling up Text-Centric Visual Instruction Tuning