Publications (18)
Online Decision MetaMorphFormer: A Casual Transformer-Based Reinforcement Learning Framework of Universal Embodied Intelligence
Luo Ji, Runji Lin
Interactive artificial intelligence in the motion control field is an interesting topic, especially when universal knowledge is adaptive to multiple tasks and universal environment…
MARGE: Improving Math Reasoning for LLMs with Guided Exploration
Jingyue Gao, Runji Lin, Keming Lu +3
Large Language Models (LLMs) exhibit strong potential in mathematical reasoning, yet their effectiveness is often limited by a shortage of high-quality queries. This limitation nec…
Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models
Keming Lu, Hongyi Yuan, Runji Lin +4
The complementary potential of Large Language Models (LLM) assumes off-the-shelf LLMs have heterogeneous expertise in a wide range of domains and tasks so that an ensemble of LLMs…
Qwen Technical Report
Jinze Bai, Shuai Bai, Yunfei Chu +45
Large language models (LLMs) have revolutionized the field of artificial intelligence, enabling natural language processing tasks that were previously thought to be exclusive to hu…
Multi-Agent Reinforcement Learning is a Sequence Modeling Problem
Muning Wen, Jakub Grudzien Kuba, Runji Lin +4
Large sequence model (SM) such as GPT series and BERT has displayed outstanding performance and generalization capabilities on vision, language, and recently reinforcement learning…
The Lessons of Developing Process Reward Models in Mathematical Reasoning
Zhenru Zhang, Chujie Zheng, Yangzhen Wu +6
Process Reward Models (PRMs) emerge as a promising approach for process supervision in mathematical reasoning of Large Language Models (LLMs), which aim to identify and mitigate in…
Scalable Model-based Policy Optimization for Decentralized Networked Systems
Yali Du, Chengdong Ma, Yuchen Liu +4
Reinforcement learning algorithms require a large amount of samples; this often limits their real-world applications on even simple tasks. Such a challenge is more outstanding in m…
Online Merging Optimizers for Boosting Rewards and Mitigating Tax in Alignment
Keming Lu, Bowen Yu, Fei Huang +3
Effectively aligning Large Language Models (LLMs) with human-centric values while preventing the degradation of abilities acquired through Pre-training and Supervised Fine-tuning (…
#InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language Models
Keming Lu, Hongyi Yuan, Zheng Yuan +5
Foundation language models obtain the instruction-following ability through supervised fine-tuning (SFT). Diversity and complexity are considered critical factors of a successful S…
WorldPM: Scaling Human Preference Modeling
Binghai Wang, Runji Lin, Keming Lu +17
Motivated by scaling laws in language modeling that demonstrate how test loss scales as a power law with model and dataset sizes, we find that similar laws exist in preference mode…
Large Sequence Models for Sequential Decision-Making: A Survey
Muning Wen, Runji Lin, Hanjing Wang +6
Transformer architectures have facilitated the development of large-scale and general-purpose sequence models for prediction tasks in natural language processing and computer visio…
Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach
Weiyu Ma, Qirui Mi, Yongcheng Zeng +5
StarCraft II is a challenging benchmark for AI agents due to the necessity of both precise micro level operations and strategic macro awareness. Previous works, such as Alphastar a…
LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback
Bofei Gao, Zefan Cai, Runxin Xu +10
In recent progress, mathematical verifiers have achieved success in mathematical reasoning tasks by validating the correctness of solutions generated by policy models. However, exi…
Qwen2.5 Technical Report
Qwen, :, An Yang +41
In this report, we introduce Qwen2.5, a comprehensive series of large language models (LLMs) designed to meet diverse needs. Compared to previous iterations, Qwen 2.5 has been sign…
Qwen2 Technical Report
An Yang, Baosong Yang, Binyuan Hui +59
This report introduces the Qwen2 series, the latest addition to our large language models and large multimodal models. We release a comprehensive suite of foundational and instruct…
Contextual Transformer for Offline Meta Reinforcement Learning
Runji Lin, Ye Li, Xidong Feng +6
The pretrain-finetuning paradigm in large-scale sequence models has made significant progress in natural language processing and computer vision tasks. However, such a paradigm is…
Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement
An Yang, Beichen Zhang, Binyuan Hui +13
In this report, we present a series of math-specific large language models: Qwen2.5-Math and Qwen2.5-Math-Instruct-1.5B/7B/72B. The core innovation of the Qwen2.5 series lies in in…
ProcessBench: Identifying Process Errors in Mathematical Reasoning
Chujie Zheng, Zhenru Zhang, Beichen Zhang +6
As language models regularly make mistakes when solving math problems, automated identification of errors in the reasoning process becomes increasingly significant for their scalab…