7 papers
Multi-Branch Policy Optimization for Multimodal Large Language Models
Shuai Lyu, Yuning Gong, Ruiling Gao +7
Group-based reinforcement learning methods for multimodal large language models typically rely on trajectory-level credit assignment that applies a single advantage to all tokens i…
ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch
Zheng Liu, Honglin Lin, Chonghan Qin +13
Chart reasoning is a critical capability for Vision Language Models (VLMs). However, the development of open-source models is severely hindered by the lack of high-quality training…
Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs
Yu Li, Xiaoran Shang, Qizhi Pei +11
Post-training data plays a pivotal role in shaping the capabilities of Large Language Models (LLMs), yet datasets are often treated as isolated artifacts, overlooking the systemic…
Bidirectional Curriculum Generation: A Multi-Agent Framework for Data-Efficient Mathematical Reasoning
Boren Hu, Xiao Liu, Boci Peng +4
Enhancing mathematical reasoning in Large Language Models typically demands massive datasets, yet data efficiency remains a critical bottleneck. While Curriculum Learning attempts…
MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods
Honglin Lin, Zheng Liu, Yun Zhu +6
Recent advances in Vision Language Models (VLMs) have driven significant progress in visual reasoning. However, open-source VLMs still lag behind proprietary systems, largely due t…
OpenDataArena: A Fair and Open Arena for Benchmarking Post-Training Dataset Value
Mengzhang Cai, Xin Gao, Yu Li +13
The rapid evolution of Large Language Models (LLMs) is predicated on the quality and diversity of post-training datasets. However, a critical dichotomy persists: while models are r…