Shijie Wang

Jinze Bai, Shuai Bai, Yunfei Chu et al. · pku, tsinghua

Large language models (LLMs) have revolutionized the field of artificial intelligence, enabling natural language processing tasks that were previously thought to be exclusive to humans. In this work, we introduce Qwen, the first installment of our large language model series. Qwen is a comprehensive language model series that encompasses distinct models with varying parameter counts. It includes Qwen, the base pretrained language models, and Qwen-Chat, the chat models finetuned with human alignment techniques. The base language models consistently demonstrate superior performance across a multitude of downstream tasks, and the chat models, particularly those trained using Reinforcement Learning from Human Feedback (RLHF), are highly competitive. The chat models possess advanced tool-use and planning capabilities for creating agent applications, showcasing impressive performance even when compared to bigger models on complex tasks like utilizing a code interpreter. Furthermore, we have developed coding-specialized models, Code-Qwen and Code-Qwen-Chat, as well as mathematics-focused models, Math-Qwen-Chat, which are built upon base language models. These models demonstrate significantly improved performance in comparison with open-source models, and slightly fall behind the proprietary models.

An Yang, Baosong Yang, Binyuan Hui et al.

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 instruction-tuned language models, encompassing a parameter range from 0.5 to 72 billion, featuring dense models and a Mixture-of-Experts model. Qwen2 surpasses most prior open-weight models, including its predecessor Qwen1.5, and exhibits competitive performance relative to proprietary models across diverse benchmarks on language understanding, generation, multilingual proficiency, coding, mathematics, and reasoning. The flagship model, Qwen2-72B, showcases remarkable performance: 84.2 on MMLU, 37.9 on GPQA, 64.6 on HumanEval, 89.5 on GSM8K, and 82.4 on BBH as a base language model. The instruction-tuned variant, Qwen2-72B-Instruct, attains 9.1 on MT-Bench, 48.1 on Arena-Hard, and 35.7 on LiveCodeBench. Moreover, Qwen2 demonstrates robust multilingual capabilities, proficient in approximately 30 languages, spanning English, Chinese, Spanish, French, German, Arabic, Russian, Korean, Japanese, Thai, Vietnamese, and more, underscoring its versatility and global reach. To foster community innovation and accessibility, we have made the Qwen2 model weights openly available on Hugging Face and ModelScope, and the supplementary materials including example code on GitHub. These platforms also include resources for quantization, fine-tuning, and deployment, facilitating a wide range of applications and research endeavors.

Kaiyan Zhang, Yuxin Zuo, Bingxiang He et al. · pku, tsinghua

In this paper, we survey recent advances in Reinforcement Learning (RL) for reasoning with Large Language Models (LLMs). RL has achieved remarkable success in advancing the frontier of LLM capabilities, particularly in addressing complex logical tasks such as mathematics and coding. As a result, RL has emerged as a foundational methodology for transforming LLMs into LRMs. With the rapid progress of the field, further scaling of RL for LRMs now faces foundational challenges not only in computational resources but also in algorithm design, training data, and infrastructure. To this end, it is timely to revisit the development of this domain, reassess its trajectory, and explore strategies to enhance the scalability of RL toward Artificial SuperIntelligence (ASI). In particular, we examine research applying RL to LLMs and LRMs for reasoning abilities, especially since the release of DeepSeek-R1, including foundational components, core problems, training resources, and downstream applications, to identify future opportunities and directions for this rapidly evolving area. We hope this review will promote future research on RL for broader reasoning models. Github: https://github.com/TsinghuaC3I/Awesome-RL-for-LRMs

Wenqi Fan, Shijie Wang, Jiani Huang et al.

Graphs play an important role in representing complex relationships in various domains like social networks, knowledge graphs, and molecular discovery. With the advent of deep learning, Graph Neural Networks (GNNs) have emerged as a cornerstone in Graph Machine Learning (Graph ML), facilitating the representation and processing of graph structures. Recently, LLMs have demonstrated unprecedented capabilities in language tasks and are widely adopted in a variety of applications such as computer vision and recommender systems. This remarkable success has also attracted interest in applying LLMs to the graph domain. Increasing efforts have been made to explore the potential of LLMs in advancing Graph ML's generalization, transferability, and few-shot learning ability. Meanwhile, graphs, especially knowledge graphs, are rich in reliable factual knowledge, which can be utilized to enhance the reasoning capabilities of LLMs and potentially alleviate their limitations such as hallucinations and the lack of explainability. Given the rapid progress of this research direction, a systematic review summarizing the latest advancements for Graph ML in the era of LLMs is necessary to provide an in-depth understanding to researchers and practitioners. Therefore, in this survey, we first review the recent developments in Graph ML. We then explore how LLMs can be utilized to enhance the quality of graph features, alleviate the reliance on labeled data, and address challenges such as graph heterogeneity and out-of-distribution (OOD) generalization. Afterward, we delve into how graphs can enhance LLMs, highlighting their abilities to enhance LLM pre-training and inference. Furthermore, we investigate various applications and discuss the potential future directions in this promising field.

Shijie Wang, Li Zhang, Xinyan Liang et al.

Multimodal learning typically utilizes multimodal joint loss to integrate different modalities and enhance model performance. However, this joint learning strategy can induce modality imbalance, where strong modalities overwhelm weaker ones and limit exploitation of individual information from each modality and the inter-modality interaction information. Existing strategies such as dynamic loss weighting, auxiliary objectives and gradient modulation mitigate modality imbalance based on joint loss. These methods remain fundamentally reactive, detecting and correcting imbalance after it arises, while leaving the competitive nature of the joint loss untouched. This limitation drives us to explore a new strategy for multimodal imbalance learning that does not rely on the joint loss, enabling more effective interactions between modalities and better utilization of information from individual modalities and their interactions. In this paper, we introduce Unidirectional Dynamic Interaction (UDI), a novel strategy that abandons the conventional joint loss in favor of a proactive, sequential training scheme. UDI first trains the anchor modality to convergence, then uses its learned representations to guide the other modality via unsupervised loss. Furthermore, the dynamic adjustment of modality interactions allows the model to adapt to the task at hand, ensuring that each modality contributes optimally. By decoupling modality optimization and enabling directed information flow, UDI prevents domination by any single modality and fosters effective cross-modal feature learning. Our experimental results demonstrate that UDI outperforms existing methods in handling modality imbalance, leading to performance improvement in multimodal learning tasks.

Hao Ma, Shijie Wang, Zhiqiang Pu et al.

Guiding the policy of multi-agent reinforcement learning to align with human common sense is a difficult problem, largely due to the complexity of modeling common sense as a reward, especially in complex and long-horizon multi-agent tasks. Recent works have shown the effectiveness of reward shaping, such as potential-based rewards, to enhance policy alignment. The existing works, however, primarily rely on experts to design rule-based rewards, which are often labor-intensive and lack a high-level semantic understanding of common sense. To solve this problem, we propose a hierarchical vision-based reward shaping method. At the bottom layer, a visual-language model (VLM) serves as a generic potential function, guiding the policy to align with human common sense through its intrinsic semantic understanding. To help the policy adapts to uncertainty and changes in long-horizon tasks, the top layer features an adaptive skill selection module based on a visual large language model (vLLM). The module uses instructions, video replays, and training records to dynamically select suitable potential function from a pre-designed pool. Besides, our method is theoretically proven to preserve the optimal policy. Extensive experiments conducted in the Google Research Football environment demonstrate that our method not only achieves a higher win rate but also effectively aligns the policy with human common sense.