11 papers
MEML-GRPO: Heterogeneous Multi-Expert Mutual Learning for RLVR Advancement
Weitao Jia, Jinghui Lu, Haiyang Yu +17
Recent advances demonstrate that reinforcement learning with verifiable rewards (RLVR) significantly enhances the reasoning capabilities of large language models (LLMs). However, s…
Benchmarking Vision-Language Models on Chinese Ancient Documents: From OCR to Knowledge Reasoning
Haiyang Yu, Yuchuan Wu, Fan Shi +18
Chinese ancient documents, invaluable carriers of millennia of Chinese history and culture, hold rich knowledge across diverse fields but face challenges in digitization and unders…
MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering
Jingqun Tang, Qi Liu, Yongjie Ye +14
Text-Centric Visual Question Answering (TEC-VQA) in its proper format not only facilitates human-machine interaction in text-centric visual environments but also serves as a de fac…
Advancing Sequential Numerical Prediction in Autoregressive Models
Xiang Fei, Jinghui Lu, Qi Sun +6
Autoregressive models have become the de facto choice for sequence generation tasks, but standard approaches treat digits as independent tokens and apply cross-entropy loss, overlo…
WildDoc: How Far Are We from Achieving Comprehensive and Robust Document Understanding in the Wild?
An-Lan Wang, Jingqun Tang, Liao Lei +10
The rapid advancements in Multimodal Large Language Models (MLLMs) have significantly enhanced capabilities in Document Understanding. However, prevailing benchmarks like DocVQA an…
Prolonged Reasoning Is Not All You Need: Certainty-Based Adaptive Routing for Efficient LLM/MLLM Reasoning
Jinghui Lu, Haiyang Yu, Siliang Xu +9
Recent advancements in reasoning have significantly enhanced the capabilities of Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) across diverse tasks. How…