23 papers
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…
Heterogeneous Adaptive Policy Optimization: Tailoring Optimization to Every Token's Nature
Zheng Liu, Mengjie Liu, Siwei Wen +4
Using entropy as a measure of heterogeneity to guide optimization has emerged as a crucial research direction in Reinforcement Learning for LLMs. However, existing methods typicall…
DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models
Hao Liang, Zhengyang Zhao, Meiyi Qiang +22
Data-centric training has emerged as a promising direction for improving large language models (LLMs) by optimizing not only model parameters but also the selection, composition, a…
Let's Verify Math Questions Step by Step
Chengyu Shen, Zhen Hao Wong, Runming He +8
Large Language Models (LLMs) have recently achieved remarkable progress in mathematical reasoning. To enable such capabilities, many existing works distill strong reasoning models…
Learning What Reinforcement Learning Can't: Interleaved Online Fine-Tuning for Hardest Questions
Lu Ma, Hao Liang, Meiyi Qiang +9
Recent advances in large language model (LLM) reasoning have shown that sophisticated behaviors such as planning and self-reflection can emerge through reinforcement learning (RL).…
pQuant: Towards Effective Low-Bit Language Models via Decoupled Linear Quantization-Aware Training
Wenzheng Zhang, Bingzheng Liu, Yang Hu +3
Quantization-Aware Training from scratch has emerged as a promising approach for building efficient large language models (LLMs) with extremely low-bit weights (sub 2-bit), which c…