Author name cluster

Yue Fan

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

14 papers

2 author rows

AAAI Conference 2026 Conference Paper

Learning to Generate and Extract: A Multi-Agent Collaboration Framework for Zero-Shot Document-Level Event Arguments Extraction

Guangjun Zhang
Hu Zhang
Yazhou Han
Yue Fan
Yuhang Shao
Hongye Tan
Ru Li

Document-level event argument extraction (DEAE) is essential for knowledge acquisition, aiming to extract participants of events from documents. In the zero-shot setting, existing methods employ LLMs to generate synthetic data to address the challenge posed by the scarcity of annotated data. However, relying solely on Event-type-only prompts makes it difficult for the generated content to accurately capture the contextual and structural relationships of unseen events. Moreover, ensuring the reliability and usability of synthetic data remains a significant challenge due to the absence of quality evaluation mechanisms. To this end, we introduce a multi-agent collaboration framework for zero-shot document-level event argument extraction (ZS-DEAE), which simulates the human collaborative cognitive process of “Propose–Evaluate–Revise.” Specifically, the framework comprises a generation agent and an evaluation agent. The generation agent synthesizes data for unseen events by leveraging knowledge from seen events, while the evaluation agent extracts arguments from the synthetic data and assesses their semantic consistency with the context. The evaluation results are subsequently converted into reward signals, with event structure constraints incorporated into the reward design to enable iterative optimization of both agents via reinforcement learning. In three zero-shot scenarios constructed from the RAMS and WikiEvents datasets, our method achieves improvements both in data generation quality and argument extraction performance, while the generated data also effectively enhances the zero-shot performance of other DEAE models.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes

Tianxu Wang
Zhuofan Zhang
Ziyu Zhu
Yue Fan
Jing Xiong
Pengxiang Li
Xiaojian (Shawn) Ma
Qing Li

3D visual grounding has made notable progress in localizing objects within complex 3D scenes. However, grounding referring expressions beyond objects in 3D scenes remains unexplored. In this paper, we introduce Anywhere3D-Bench, a holistic 3D visual grounding benchmark consisting of 2, 886 referring expression-3D bounding box pairs spanning four different grounding levels: human-activity areas, unoccupied space beyond objects, individual objects in the scene, and fine-grained object parts. We assess a range of state-of-the-art 3D visual grounding methods alongside large language models (LLMs) and multimodal LLMs (MLLMs) on Anywhere3D-Bench. Experimental results reveal that space-level and part-level visual grounding pose the greatest challenges: space-level tasks require a more comprehensive spatial reasoning ability, for example, modeling distances and spatial relations within 3D space, while part-level tasks demand fine-grained perception of object composition. Even the best performance model, OpenAI o4-mini, achieves only 23. 00% accuracy on space-level tasks and 31. 46% on part-level tasks, significantly lower than its performance on area-level and object-level tasks. These findings underscore a critical gap in current models’ capacity to understand and reason about 3D scenes beyond object-level semantics.

PDF Details

NeurIPS Conference 2025 Conference Paper

GRIT: Teaching MLLMs to Think with Images

Yue Fan
Xuehai He
Diji Yang
Kaizhi Zheng
Ching-Chen Kuo
Yuting Zheng
Xinze Guan
Xin Wang

Recent studies have demonstrated the efficacy of using Reinforcement Learning (RL) in building reasoning models that articulate chains of thoughts prior to producing final answers. However, despite ongoing advances that aim at enabling reasoning for vision-language tasks, existing open-source visual reasoning models typically generate reasoning content with pure natural language, lacking explicit integration of visual information. This limits their ability to produce clearly articulated and visually grounded reasoning chains. To this end, we propose Grounded Reasoning with Images and Texts (GRIT), a novel method for training MLLMs to think with images. GRIT introduces a grounded reasoning paradigm, in which models generate reasoning chains that interleave natural language and explicit bounding box coordinates. These coordinates point to regions of the input image that the model consults during its reasoning process. Additionally, GRIT is equipped with a reinforcement learning approach, GRPO-GR, built upon the GRPO algorithm. GRPO-GR employs robust rewards focused on the final answer accuracy and format of the grounded reasoning output, which eliminates the need for data with reasoning chain annotations or explicit bounding box labels. As a result, GRIT achieves exceptional data efficiency, requiring as few as 20 image-question-answer triplets from existing datasets. Comprehensive evaluations demonstrate that GRIT effectively trains MLLMs to produce coherent and visually grounded reasoning chains, showing a successful unification of reasoning and grounding abilities. All code, data, and checkpoints will be released.

PDF Details

NeSy Conference 2025 Conference Paper

JARVIS: A Neuro-Symbolic Commonsense Reasoning Framework for Conversational Embodied Agents

Kaizhi Zheng
Kaiwen Zhou 0002
Jing Gu
Yue Fan
Jialu Wang
Zonglin Di
Xuehai He
Xin Eric Wang

Building a conversational embodied agent to execute real-life tasks has been a long-standing yet quite challenging research goal, as it requires effective human-agent communication, multi-modal understanding, long-range sequential decision making, etc. Traditional symbolic methods have scaling and generalization issues, while end-to-end deep learning models suffer from data scarcity and high task complexity, and are often hard to explain. To benefit from both worlds, we propose JARVIS, a neuro-symbolic commonsense reasoning framework for modular, generalizable, and interpretable conversational embodied agents. First, it acquires symbolic representations by prompting large language models (LLMs) for language understanding and sub-goal planning, and by constructing semantic maps from visual observations. Then the symbolic module reasons for sub-goal planning and action generation based on task- and action-level common sense. Extensive experiments on the TEACh dataset validate the efficacy and efficiency of our JARVIS framework, which achieves state-of-the-art (SOTA) results on all three dialog-based embodied tasks, including Execution from Dialog History (EDH), Trajectory from Dialog (TfD), and Two-Agent Task Completion (TATC) (e. g. , our method boosts the unseen Success Rate on EDH from 6. 1% to 15. 8%). Moreover, we systematically analyze the essential factors that affect the task performance and also demonstrate the superiority of our method in few-shot settings.

Details

ICLR Conference 2025 Conference Paper

MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos

Xuehai He
Weixi Feng
Kaizhi Zheng
Yujie Lu
Wanrong Zhu
Jiachen Li
Yue Fan
Jianfeng Wang

Multimodal Language Language Models (MLLMs) demonstrate the emerging abilities of "world models"---interpreting and reasoning about complex real-world dynamics. To assess these abilities, we posit videos are the ideal medium, as they encapsulate rich representations of real-world dynamics and causalities. To this end, we introduce MMWorld, a new benchmark for multi-discipline, multi-faceted multimodal video understanding. MMWorld distinguishes itself from previous video understanding benchmarks with two unique advantages: (1) multi-discipline, covering various disciplines that often require domain expertise for comprehensive understanding; (2) multi-faceted reasoning, including explanation, counterfactual thinking, future prediction, etc. MMWorld consists of a human-annotated dataset to evaluate MLLMs with questions about the whole videos and a synthetic dataset to analyze MLLMs within a single modality of perception. Together, MMWorld encompasses 1,910 videos across seven broad disciplines and 69 subdisciplines, complete with 6,627 question-answer pairs and associated captions. The evaluation includes 4 proprietary and 11 open-source MLLMs, which struggle on MMWorld (e.g., GPT-4o performs the best with only 62.5% accuracy), showing large room for improvement. Further ablation studies reveal other interesting findings such as models' different skill sets from humans. We hope MMWorld can serve as an essential step towards world model evaluation in videos.

Details

ICLR Conference 2025 Conference Paper

Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage

Zhi Gao 0002
Bofei Zhang
Pengxiang Li 0002
Xiaojian Ma 0001
Tao Yuan
Yue Fan
Yuwei Wu 0001
Yunde Jia

The advancement of large language models (LLMs) prompts the development of multi-modal agents, which are used as a controller to call external tools, providing a feasible way to solve practical tasks. In this paper, we propose a multi-modal agent tuning method that automatically generates multi-modal tool-usage data and tunes a vision-language model (VLM) as the controller for powerful tool-usage reasoning. To preserve the data quality, we prompt the GPT-4o mini model to generate queries, files, and trajectories, followed by query-file and trajectory verifiers. Based on the data synthesis pipeline, we collect the MM-Traj dataset that contains 20K tasks with trajectories of tool usage. Then, we develop the T3-Agent via Trajectory Tuning on VLMs for Tool usage using MM-Traj. Evaluations on the GTA and GAIA benchmarks show that the T3-Agent consistently achieves improvements on two popular VLMs: MiniCPM-V-8.5B and Qwen2-VL-7B, which outperforms untrained VLMs by 20%, showing the effectiveness of the proposed data synthesis pipeline, leading to high-quality data for tool-usage capabilities.

Details

ICLR Conference 2025 Conference Paper

TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters

Haiyang Wang
Yue Fan
Muhammad Ferjad Naeem
Yongqin Xian
Jan Eric Lenssen
Liwei Wang 0001
Federico Tombari
Bernt Schiele

Transformers have become the predominant architecture in foundation models due to their excellent performance across various domains. However, the substantial cost of scaling these models remains a significant concern. This problem arises primarily from their dependence on a fixed number of parameters within linear projections. When architectural modifications (e.g., channel dimensions) are introduced, the entire model typically requires retraining from scratch. As model sizes continue growing, this strategy results in increasingly high computational costs and becomes unsustainable. To overcome this problem, we introduce Tokenformer, a natively scalable architecture that leverages the attention mechanism not only for computations among input tokens but also for interactions between tokens and model parameters, thereby enhancing architectural flexibility. By treating model parameters as tokens, we replace all the linear projections in Transformers with our token-parameter attention layer, where input tokens act as queries and model parameters as keys and values. This reformulation allows for progressive and efficient scaling without necessitating retraining from scratch. Our model scales from 124M to 1.4B parameters by incrementally adding new key-value parameter pairs, achieving performance comparable to Transformers trained from scratch while greatly reducing training costs. Code and models are available at {\color{red}\url{https://github.com/Haiyang-W/TokenFormer.git}}

Details

ECAI Conference 2023 Conference Paper

Attention Based Models for Cell Type Classification on Single-Cell RNA-Seq Data

Tianxu Wang
Yue Fan
Xiuli Ma

Cell type classification serves as one of the most fundamental analyses in bioinformatics. It helps recognizing various cells in cancer microenvironment, discovering new cell types and facilitating other downstream tasks. Single-cell RNA-sequencing (scRNA-seq) technology can profile the whole transcriptome of each cell, thus enabling cell type classification. However, high-dimensional scRNA-seq data pose serious challenges on cell type classification. Existing methods either classify the cells with reliance on the prior knowledge or by using neural networks whose massive parameters are hard to interpret. In this paper, we propose two novel attention-based models for cell type classification on single-cell RNA-seq data. The first model, Cell Feature Attention Network (CFAN), captures the features of a cell and performs attention model on them. To further improve interpretation, the second model, Cell-Gene Representation Attention Network (CGRAN), directly concretizes tokens as cells and genes and uses the cell representation renewed by self-attention over the cell and the genes to predict cell type. Both models show excellent performance in cell type classification; additionally, the key genes with high attention weights in CGRAN indicate and identify the marker genes of the cell types, thus proving the model’s biological interpretation.

Details

ICLR Conference 2023 Conference Paper

FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning

Yidong Wang 0003
Hao Chen 0102
Qiang Heng
Wenxin Hou
Yue Fan
Zhen Wu 0002
Jindong Wang 0001
Marios Savvides

Semi-supervised Learning (SSL) has witnessed great success owing to the impressive performances brought by various methods based on pseudo labeling and consistency regularization. However, we argue that existing methods might fail to utilize the unlabeled data more effectively since they either use a pre-defined / fixed threshold or an ad-hoc threshold adjusting scheme, resulting in inferior performance and slow convergence. We first analyze a motivating example to obtain intuitions on the relationship between the desirable threshold and model's learning status. Based on the analysis, we hence propose FreeMatch to adjust the confidence threshold in a self-adaptive manner according to the model's learning status. We further introduce a self-adaptive class fairness regularization penalty to encourage the model for diverse predictions during the early training stage. Extensive experiments indicate the superiority of FreeMatch especially when the labeled data are extremely rare. FreeMatch achieves 5.78%, 13.59%, and 1.28% error rate reduction over the latest state-of-the-art method FlexMatch on CIFAR-10 with 1 label per class, STL-10 with 4 labels per class, and ImageNet with 100 labels per class, respectively. Moreover, FreeMatch can also boost the performance of imbalanced SSL. The codes can be found at https://github.com/microsoft/Semi-supervised-learning.

Details

ICLR Conference 2023 Conference Paper

SoftMatch: Addressing the Quantity-Quality Tradeoff in Semi-supervised Learning

Hao Chen 0102
Ran Tao 0013
Yue Fan
Yidong Wang 0003
Jindong Wang 0001
Bernt Schiele
Xing Xie 0001
Bhiksha Raj

The critical challenge of Semi-Supervised Learning (SSL) is how to effectively leverage the limited labeled data and massive unlabeled data to improve the model's generalization performance. In this paper, we first revisit the popular pseudo-labeling methods via a unified sample weighting formulation and demonstrate the inherent quantity-quality trade-off problem of pseudo-labeling with thresholding, which may prohibit learning. To this end, we propose SoftMatch to overcome the trade-off by maintaining both high quantity and high quality of pseudo-labels during training, effectively exploiting the unlabeled data. We derive a truncated Gaussian function to weight samples based on their confidence, which can be viewed as a soft version of the confidence threshold. We further enhance the utilization of weakly-learned classes by proposing a uniform alignment approach. In experiments, SoftMatch shows substantial improvements across a wide variety of benchmarks, including image, text, and imbalanced classification.

Details

IJCAI Conference 2022 Conference Paper

Multi-Vector Embedding on Networks with Taxonomies

Yue Fan
Xiuli Ma

A network can effectively depict close relationships among its nodes, with labels in a taxonomy describing the nodes' rich attributes. Network embedding aims at learning a representation vector for each node and label to preserve their proximity, while most existing methods suffer from serious underfitting when dealing with datasets with dense node-label links. For instance, a node could have dozens of labels describing its diverse properties, causing the single node vector overloaded and hard to fit all the labels. We propose HIerarchical Multi-vector Embedding (HIME), which solves the underfitting problem by adaptively learning multiple 'branch vectors' for each node to dynamically fit separate sets of labels in a hierarchy-aware embedding space. Moreover, a 'root vector' is learned for each node based on its branch vectors to better predict the sparse but valuable node-node links with the knowledge of its labels. Experiments reveal HIME’s comprehensive advantages over existing methods on tasks such as proximity search, link prediction and hierarchical classification.

PDF Details DOI

NeurIPS Conference 2022 Conference Paper

USB: A Unified Semi-supervised Learning Benchmark for Classification

Yidong Wang
Hao Chen
Yue Fan
Wang Sun
Ran Tao
Wenxin Hou
Renjie Wang
Linyi Yang

Semi-supervised learning (SSL) improves model generalization by leveraging massive unlabeled data to augment limited labeled samples. However, currently, popular SSL evaluation protocols are often constrained to computer vision (CV) tasks. In addition, previous work typically trains deep neural networks from scratch, which is time-consuming and environmentally unfriendly. To address the above issues, we construct a Unified SSL Benchmark (USB) for classification by selecting 15 diverse, challenging, and comprehensive tasks from CV, natural language processing (NLP), and audio processing (Audio), on which we systematically evaluate the dominant SSL methods, and also open-source a modular and extensible codebase for fair evaluation of these SSL methods. We further provide the pre-trained versions of the state-of-the-art neural models for CV tasks to make the cost affordable for further tuning. USB enables the evaluation of a single SSL algorithm on more tasks from multiple domains but with less cost. Specifically, on a single NVIDIA V100, only 39 GPU days are required to evaluate FixMatch on 15 tasks in USB while 335 GPU days (279 GPU days on 4 CV datasets except for ImageNet) are needed on 5 CV tasks with TorchSSL.

PDF Details

AAAI Conference 2021 Conference Paper

Gene Regulatory Network Inference using 3D Convolutional Neural Network

Yue Fan
Xiuli Ma

Gene regulatory networks (GRNs) consist of gene regulations between transcription factors (TFs) and their target genes. Single-cell RNA sequencing (scRNA-seq) brings both opportunities and challenges to the inference of GRNs. On the one hand, scRNA-seq data reveals statistic information of gene expressions at the single-cell resolution, which is conducive to the construction of GRNs; on the other hand, noises and dropouts pose great difficulties on the analysis of scRNA-seq data, causing low prediction accuracy by traditional methods. In this paper, we propose 3D Co-Expression Matrix Analysis (3DCEMA), which predicts regulatory relationships by classifying 3D co-expression matrices of gene triplets using a 3D convolutional neural network. We found that by introducing a third gene as a comparison factor, our method can avoid the disturbance of noises and dropouts, and significantly increase the prediction accuracy of regulations between gene pairs. Compared with other existing GRN inference algorithms on both in-silico datasets and scRNA-Seq datasets, our algorithm based on deep learning shows higher stability and accuracy in the task of GRN inference.

PDF Details

IROS Conference 2020 Conference Paper

Learn by Observation: Imitation Learning for Drone Patrolling from Videos of A Human Navigator

Yue Fan
Shilei Chu
Wei Zhang 0021
Ran Song 0001
Yibin Li 0001

We present an imitation learning method for autonomous drone patrolling based only on raw videos. Different from previous methods, we propose to let the drone learn patrolling in the air by observing and imitating how a human navigator does it on the ground. The observation process enables the automatic collection and annotation of data using inter-frame geometric consistency, resulting in less manual effort and high accuracy. Then a newly designed neural network is trained based on the annotated data to predict appropriate directions and translations for the drone to patrol in a lane-keeping manner as humans. Our method allows the drone to fly at a high altitude with a broad view and low risk. It can also detect all accessible directions at crossroads and further carry out the integration of available user instructions and autonomous patrolling control commands. Extensive experiments are conducted to demonstrate the accuracy of the proposed imitating learning process as well as the reliability of the holistic system for autonomous drone navigation. The codes, datasets as well as video demonstrations are available at https://vsislab.github.io/uavpatrol.

Details