JWJunjie Wang

Junjie Wang

*This is an algorithmically generated author record based on publicly available information.

Junjie Wang has a total of 36 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Evolver: Turning Agent Exploration into Evolving Capabilities

    by Haoyang Zhang, Qumeng Sun, Xiao Zhang, Xiang Liu, Zhidong Fan, Junjie Wang

    Agent exploration produces valuable procedural knowledge, yet much of this experience remains confined to transient execution traces and is not systematically reused. We introduce Evolver, an experience-driven framework that transforms agent exploration into persistent, reusable capabilities without updating foundation model parameters. Built around structured Gene assets, Evolver integrates experience acquisition, retrieval, and feedback-guided evolution to support experience-conditioned execution across existing agent harnesses. We evaluate Evolver using Claude Code and Codex, two foundation model configurations, and four benchmarks: Terminal-Bench 2.1, SWE-bench Multilingual, SWE-rebench, and GAIA. On a selected diagnostic set of 320 paired executions, Evolver improves task success from 83.13% to 87.50% (+4.38 percentage points) while reducing recorded task-execution token consumption by 24.24%. Furthermore, among 265 pairs successful under both conditions, token consumption decreases by 17.57%, demonstrating efficiency benefits even when task success is preserved. These findings suggest that persistent procedural experience can improve both task effectiveness and execution efficiency, providing a practical foundation for transforming agent exploration into evolving capabilities.

  • Open Access

    BREV-RAG: Beyond Relevance-based EValuation of RAG systems: A SIGIR-AP 2025 Workshop Proposal

    by Tetsuya Sakai, Sijie Tao, Zhicheng Dou, Junjie Wang, Haoxiang Shi, Nuo Chen, Atsushi Keyaki

  • Open Access

    Data-Efficient Massive Tool Retrieval: A Reinforcement Learning Approach for Query-Tool Alignment with Language Models

    by Yuxiang Zhang, Xin Fan, Junjie Wang, Chongxian Chen, Fan Mo, Tetsuya Sakai, Hayato Yamana

    Recent advancements in large language models (LLMs) integrated with external tools and APIs have successfully addressed complex tasks by using in-context learning or fine-tuning. Despite this progress, the vast scale of tool retrieval remains challenging due to stringent input length constraints. In response, we propose a pre-retrieval strategy from an extensive repository, effectively framing the problem as the massive tool retrieval (MTR) task. We introduce the MTRB (massive tool retrieval benchmark) to evaluate real-world tool-augmented LLM scenarios with a large number of tools. This benchmark is designed for low-resource scenarios and includes a diverse collection of tools with descriptions refined for consistency and clarity. It consists of three subsets, each containing 90 test samples and 10 training samples. To handle the low-resource MTR task, we raise a new query-tool alignment (QTA) framework leverages LLMs to enhance query-tool alignment by rewriting user queries through ranking functions and the direct preference optimization (DPO) method. This approach consistently outperforms existing state-of-the-art models in top-5 and top-10 retrieval tasks across the MTRB benchmark, with improvements up to 93.28% based on the metric Sufficiency@k, which measures the adequacy of tool retrieval within the first k results. Furthermore, ablation studies validate the efficacy of our framework, highlighting its capacity to optimize performance even with limited annotated samples. Specifically, our framework achieves up to 78.53% performance improvement in Sufficiency@k with just a single annotated sample. Additionally, QTA exhibits strong cross-dataset generalizability, emphasizing its potential for real-world applications.


  • Open Access

    SSR: Solving Named Entity Recognition Problems via a Single-stream Reasoner

    by Yuxiang Zhang, Junjie Wang, Xinyu Zhu, Tetsuya Sakai, Hayato Yamana

    Information Extraction (IE) focuses on transforming unstructured data into structured knowledge, of which Named Entity Recognition (NER) is a fundamental component. In the realm of Information Retrieval (IR), effectively recognizing entities can substantially enhance the precision of search and recommendation systems. Existing methods frame NER as a sequence labeling task, which requires extra data and, therefore may be limited in terms of sustainability. One promising solution is to employ a Machine Reading Comprehension (MRC) approach for NER tasks, thereby eliminating the dependence on additional data. This process encounters key challenges, including: (1) Unconventional predictions; (2) Inefficient multi-stream processing; (3) Absence of a proficient reasoning strategy. To this end, we present the Single-Stream Reasoner (SSR), a solution utilizing a reasoning strategy and standardized inputs. This yields a type-agnostic solution for both flat and nested NER tasks, without the need for additional data. On ten NER benchmarks, SSR achieved state-of-the-art results, highlighting its robustness. Furthermore, we illustrated its efficiency through convergence, inference speed, and low-resource scenario performance comparisons. Our architecture displays adaptability and can effortlessly merge with various foundational models and reasoning strategies, fostering advancements in both the IR and IE fields.


  • Open Access

    Modeling Multimodal Uncertainties via Probability Distribution Encoders Included Vision-Language Models

    by Junjie Wang, Yatai Ji, Yuxiang Zhang, Yanru Zhu, Tetsuya Sakai

    In the field of multimodal understanding and generation, tackling inherent uncertainties is essential for mitigating ambiguous interpretations across multiple targets. We introduce the Probability Distribution Encoder (PDE), a versatile, plug-and-play module that utilizes sequence-level and feature-level interactions to model these uncertainties as probabilistic distributions. Furthermore, we demonstrate its adaptability by seamlessly integrating PDE into established frameworks, culminating in models like SWINPDE. Compared to previous methods, our probabilistic approach substantially enriches multimodal semantic understanding. In addition to specific tasks, the unlabeled data contains rich prior knowledge, especially multimodal uncertainties. However, current pre-training methods are designed based on point representations, which hinders the effective functioning of our distribution representations. Therefore, we incorporate this uncertainty modeling into three new pre-training strategies: Distribution-based Vision-Language Contrastive Learning (D-VLC), Distribution-based Masked Language Modeling (D-MLM), and Distribution-based Image-Text Matching (D-ITM). Empirical experiments show that our models achieve State-of-the-Art (SOTA) results in a range of downstream tasks, including image-text retrieval, visual question answering, visual reasoning, visual entailment and video captioning. Furthermore, the qualitative results reveal several superior properties conferred by our methods, such as improved semantic expressiveness over point representations, and the ability to generate diverse yet accurate predictions.


  • Open Access

    Zero-Shot Learners for Natural Language Understanding via a Unified Multiple-Choice Perspective

    by Junjie Wang, Ping Yang, Ruyi Gan, Yuxiang Zhang, Jiaxing Zhang, Tetsuya Sakai

    Zero-shot learning is an approach where models generalize to unseen tasks without direct training on them. We introduce the Unified Multiple-Choice (UniMC) framework, which is format-independent, compatible with various formats, and applicable to tasks like text classification and sentiment analysis. Furthermore, we design a two-stage tuning method, initially training on multiple-choice formats to develop format-agnostic capabilities, and subsequently enabling direct predictions on unseen tasks for zero-shot learning. Our methodology avoids issues in large-scale models like FLAN, enhancing generalization and reducing parameters. In experiments, UniMC shows State-of-the-Art (SOTA) performance across out-of-domain and in-domain benchmarks, with only 235M parameters, far fewer than previous methods. Moreover, the UniMC-Chinese model excels beyond human performance on benchmarks like EPRSTMT and CHID-FC, underscoring its generalization capacity across languages. Additionally, ablation experiments demonstrate the effectiveness of our design.


  • Open Access

    EALM: Introducing Multidimensional Ethical Alignment in Conversational Information Retrieval

    by Yiyao Yu, Junjie Wang, Yuxiang Zhang, Lin Zhang, Yujiu Yang, Tetsuya Sakai


  • Open Access

    Towards No.1 in CLUE Semantic Matching Challenge: Pre-trained Language Model Erlangshen with Propensity-Corrected Loss

    by Junjie Wang, Yuxiang Zhang, Ping Yang, Ruyi Gan

    This report describes a pre-trained language model Erlangshen with propensity-corrected loss, the No.1 in CLUE Semantic Matching Challenge. In the pre-training stage, we construct a dynamic masking strategy based on knowledge in Masked Language Modeling (MLM) with whole word masking. Furthermore, by observing the specific structure of the dataset, the pre-trained Erlangshen applies propensity-corrected loss (PCL) in the fine-tuning phase. Overall, we achieve 72.54 points in F1 Score and 78.90 points in Accuracy on the test set. Our code is publicly available at: https://github.com/IDEA-CCNL/Fengshenbang-LM/tree/hf-ds/fengshen/examples/clue_sim.

  • Open Access

    Generating Adversarial Samples For Training Wake-up Word Detection Systems Against Confusing Words

    by Haoxu Wang, Yan Jia, Zeqing Zhao, Xuyang Wang, Junjie Wang, Ming Li

    Wake-up word detection models are widely used in real life, but suffer from severe performance degradation when encountering adversarial samples. In this paper we discuss the concept of confusing words in adversarial samples. Confusing words are commonly encountered, which are various kinds of words that sound similar to the predefined keywords. To enhance the wake word detection system's robustness against confusing words, we propose several methods to generate the adversarial confusing samples for simulating real confusing words scenarios in which we usually do not have any real confusing samples in the training set. The generated samples include concatenated audio, synthesized data, and partially masked keywords. Moreover, we use a domain embedding concatenated system to improve the performance. Experimental results show that the adversarial samples generated in our approach help improve the system's robustness in both the common scenario and the confusing words scenario. In addition, we release the confusing words testing database called HI-MIA-CW for future research.

  • Open Access

    Heterogeneous Graph-based Knowledge Transfer for Generalized Zero-shot Learning

    by Junjie Wang, Xiangfeng Wang, Bo Jin, Junchi Yan, Wenjie Zhang, Hongyuan Zha

    Generalized zero-shot learning (GZSL) tackles the problem of learning to classify instances involving both seen classes and unseen ones. The key issue is how to effectively transfer the model learned from seen classes to unseen classes. Existing works in GZSL usually assume that some prior information about unseen classes are available. However, such an assumption is unrealistic when new unseen classes appear dynamically. To this end, we propose a novel heterogeneous graph-based knowledge transfer method (HGKT) for GZSL, agnostic to unseen classes and instances, by leveraging graph neural network. Specifically, a structured heterogeneous graph is constructed with high-level representative nodes for seen classes, which are chosen through Wasserstein barycenter in order to simultaneously capture inter-class and intra-class relationship. The aggregation and embedding functions can be learned through graph neural network, which can be used to compute the embeddings of unseen classes by transferring the knowledge from their neighbors. Extensive experiments on public benchmark datasets show that our method achieves state-of-the-art results.