Author name cluster

Junfeng Yao

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.

11 papers

2 author rows

AAAI Conference 2026 Conference Paper

MGD:Mesh-guided Gaussians with Diffusion Priors for Dynamic Objects Reconstruction from Monocular RGB-D Video

Weixing Xie
Ying Ye
Xian Wu
Jintian Li
Bingchuan Li
Yanchen Lin
Junfeng Yao

Reconstructing dynamic objects from monocular RGB-D video is critical for advancing 3D vision applications and enhancing user experience. However, monocular RGB-D video provides limited 3D observations, making the reconstruction of unobserved regions highly under-constrained. Despite recent advances that combine neural implicit surfaces with diffusion models, the inherent limitations of implicit representations and the lack of effective guidance in diffusion priors lead to blurry appearance and inaccurate geometry in dynamic object reconstruction. To address the issue, we present MGD, which leverages scene-adaptive diffusion priors and Mesh-guided Gaussians for realistic rendering and geometrically accurate reconstruction of dynamic objects, including unobserved regions. The dynamic 3D objects reconstructed by MGD are represented using our proposed Mesh-guided Gaussians, which leverage global and local Gaussians to capture large-scale deformations and fine-grained appearance details, respectively. Additionally, in order to utilize depth information, we integrate a depth ControlNet into the diffusion model and conduct scene-adaptive fine-tuning. We design a self-generated image-pair strategy to produce image pairs used for fine-tuning. Extensive experiments demonstrate that MGD achieves state-of-the-art performance in both high-fidelity reconstruction and structural completeness, while maintaining real-time efficiency during training and rendering.

PDF Details DOI

AAAI Conference 2025 Conference Paper

SimRP: Syntactic and Semantic Similarity Retrieval Prompting Enhances Aspect Sentiment Quad Prediction

Zhongquan Jian
Yanhao Chen
Jiajian Li
Shaopan Wang
Xiangjian Zeng
Junfeng Yao
Xinying An
Qingqiang Wu

Aspect Sentiment Quad Prediction (ASQP) is the most complex subtask of Aspect-based Sentiment Analysis (ABSA), aiming to predict all sentiment quadruples within the given sentence. Due to the complexity of sentence syntaxes and the diversity of sentiment expressions, generative methods gradually become the mainstream approach in ASQP. However, existing generative models are constrained in the effectiveness of demonstrations. Semantically similar demonstrations help in judging sentiment categories and polarities but may confuse the model in recognizing aspect and opinion terms, which are more related to sentence syntaxes. To this end, we first develop Syn2Vec, a method for calculating syntactic vectors to support the retrieval of syntactically similar demonstrations. Then, we propose Syntactic and Semantic Similarity Retrieval Prompting (SimRP) to construct effective prompts by retrieving the most related demonstrations that are syntactically and semantically similar. With these related demonstrations, pre-trained generative models, especially Large Language Models (LLMs), can fully release their potential to recognize sentiment quadruples. Extensive experiments in Supervised Fine-Tuning (SFT) and In-context Learning (ICL) paradigms demonstrate the effectiveness of SimRP. Furthermore, we find that LLMs' capabilities in ASQP are severely underestimated by biased data annotations and the exact matching metric. We propose a novel constituent subtree-based fuzzy metric for more accurate and rational quadruple recognition.

PDF Details DOI

ECAI Conference 2024 Conference Paper

Lightweight Transformer for sEMG Gesture Recognition with Feature Distilled Variational Information Bottleneck

Zefeng Wang
Bingbing Hu
Junfeng Yao
Jinsong Su

Gesture recognition based on surface electromyography (sEMG) has seen considerable improvements in performance across various tasks and metrics with the rapid development of deep learning. However, challenges still exist in current deep neural networks for sEMG recognition. For instance, convolutional neural networks exhibit poor capturing of global features, recurrent neural networks have limited parallel processing capabilities, and their hybrids are usually more complex. Additionally, recent networks based on Transformers rarely consider the locality of attention and noise resistance. To fully explore the essence of sEMG sequences, and to make the model more lightweight and robust while ensuring feature learning performance, in this paper, we propose the feature distilled variational information bottleneck (FDVIB). Specifically, this method leverages knowledge distillation to learn from a high-precision teacher model at levels of feature and prediction, significantly reducing parameters and computations, and simplifying the structure. It also uses VIB to enhance the model’s robustness. We construct a Transformer model using the proposed method and conduct a series of evaluations. Experimental results show that our classification accuracy is competitive with state-of-the-art and also demonstrate the effectiveness of our method in enhancing model lightness and robustness.

Details

AAAI Conference 2023 Conference Paper

LagNet: Deep Lagrangian Mechanics for Plug-and-Play Molecular Representation Learning

Chunyan Li
Junfeng Yao
Jinsong Su
Zhaoyang Liu
Xiangxiang Zeng
Chenxi Huang

Molecular representation learning is a fundamental problem in the field of drug discovery and molecular science. Whereas incorporating molecular 3D information in the representations of molecule seems beneficial, which is related to computational chemistry with the basic task of predicting stable 3D structures (conformations) of molecules. Existing machine learning methods either rely on 1D and 2D molecular properties or simulate molecular force field to use additional 3D structure information via Hamiltonian network. The former has the disadvantage of ignoring important 3D structure features, while the latter has the disadvantage that existing Hamiltonian neural network must satisfy the “canonial” constraint, which is difficult to be obeyed in many cases. In this paper, we propose a novel plug-and-play architecture LagNet by simulating molecular force field only with parameterized position coordinates, which implements Lagrangian mechanics to learn molecular representation by preserving 3D conformation without obeying any additional restrictions. LagNet is designed to generate known conformations and generalize for unknown ones from molecular SMILES. Implicit positions in LagNet are learned iteratively using discrete-time Lagrangian equations. Experimental results show that LagNet can well learn 3D molecular structure features, and outperforms previous state-of-the-art baselines related molecular representation by a significant margin.

PDF Details DOI

JBHI Journal 2022 Journal Article

3DMol-Net: Learn 3D Molecular Representation Using Adaptive Graph Convolutional Network Based on Rotation Invariance

Chunyan Li
Wei Wei
Jin Li
Junfeng Yao
Xiangxiang Zeng
Zhihan Lv

Studying the deep learning-based molecular representation has great significance on predicting molecular property, promoted the development of drug screening and new drug discovery, and improving human well-being for avoiding illnesses. It is essential to learn the characterization of drug for various downstream tasks, such as molecular property prediction. In particular, the 3D structure features of molecules play an important role in biochemical function and activity prediction. The 3D characteristics of molecules largely determine the properties of the drug and the binding characteristics of the target. However, most current methods merely rely on 1D or 2D properties while ignoring the 3D topological structure, thereby degrading the performance of molecular inferring. In this paper, we propose 3DMol-Net to enhance the molecular representation, considering both the topology and rotation invariance (RI) of the 3D molecular structure. Specifically, we construct a molecular graph with soft relations related to the spatial arrangement of the 3D coordinates to learn 3D topology of arbitrary graph structure and employ an adaptive graph convolutional network to predict molecular properties and biochemical activities. Comparing with current graph-based methods, 3DMol-Net demonstrates superior performance in terms of both regression and classification tasks. Further verification of RI and visualization also show better robustness and representation capacity of our model.

Details DOI

JAIR Journal 2022 Journal Article

AAN+: Generalized Average Attention Network for Accelerating Neural Transformer

Biao Zhang
Deyi Xiong
Yubin Ge
Junfeng Yao
Hao Yue
Jinsong Su

Transformer benefits from the high parallelization of attention networks in fast training, but it still suffers from slow decoding partially due to the linear dependency O(m) of the decoder self-attention on previous target words at inference. In this paper, we propose a generalized average attention network (AAN+) aiming at speeding up decoding by reducing the dependency from O(m) to O(1). We find that the learned self-attention weights in the decoder follow some patterns which can be approximated via a dynamic structure. Based on this insight, we develop AAN+, extending our previously proposed average attention (Zhang et al., 2018a, AAN) to support more general position- and content-based attention patterns. AAN+ only requires to maintain a small constant number of hidden states during decoding, ensuring its O(1) dependency. We apply AAN+ as a drop-in replacement of the decoder selfattention and conduct experiments on machine translation (with diverse language pairs), table-to-text generation and document summarization. With masking tricks and dynamic programming, AAN+ enables Transformer to decode sentences around 20% faster without largely compromising in the training speed and the generation performance. Our results further reveal the importance of the localness (neighboring words) in AAN+ and its capability in modeling long-range dependency.

PDF Details DOI

IJCAI Conference 2021 Conference Paper

A Structure Self-Aware Model for Discourse Parsing on Multi-Party Dialogues

Ante Wang
Linfeng Song
Hui Jiang
Shaopeng Lai
Junfeng Yao
Min Zhang
Jinsong Su

Conversational discourse structures aim to describe how a dialogue is organized, thus they are helpful for dialogue understanding and response generation. This paper focuses on predicting discourse dependency structures for multi-party dialogues. Previous work adopts incremental methods that take the features from the already predicted discourse relations to help generate the next one. Although the inter-correlations among predictions considered, we find that the error propagation is also very serious and hurts the overall performance. To alleviate error propagation, we propose a Structure Self-Aware (SSA) model, which adopts a novel edge-centric Graph Neural Network (GNN) to update the information between each Elementary Discourse Unit (EDU) pair layer by layer, so that expressive representations can be learned without historical predictions. In addition, we take auxiliary training signals (e. g. structure distillation) for better representation learning. Our model achieves the new state-of-the-art performances on two conversational discourse parsing benchmarks, largely outperforming the previous methods.

PDF Details DOI

JAIR Journal 2021 Journal Article

An External Knowledge Enhanced Graph-based Neural Network for Sentence Ordering

Yongjing Yin
Shaopeng Lai
Linfeng Song
Chulun Zhou
Xianpei Han
Junfeng Yao
Jinsong Su

As an important text coherence modeling task, sentence ordering aims to coherently organize a given set of unordered sentences. To achieve this goal, the most important step is to effectively capture and exploit global dependencies among these sentences. In this paper, we propose a novel and flexible external knowledge enhanced graph-based neural network for sentence ordering. Specifically, we first represent the input sentences as a graph, where various kinds of relations (i.e., entity-entity, sentence-sentence and entity-sentence) are exploited to make the graph representation more expressive and less noisy. Then, we introduce graph recurrent network to learn semantic representations of the sentences. To demonstrate the effectiveness of our model, we conduct experiments on several benchmark datasets. The experimental results and in-depth analysis show our model significantly outperforms the existing state-of-the-art models.

PDF Details DOI

AAAI Conference 2021 Conference Paper

Improving Tree-Structured Decoder Training for Code Generation via Mutual Learning

Binbin Xie
Jinsong Su
Yubin Ge
Xiang Li
Jianwei Cui
Junfeng Yao
Bin Wang

Code generation aims to automatically generate a piece of code given an input natural language utterance. Currently, among dominant models, it is treated as a sequence-to-tree task, where a decoder outputs a sequence of actions corresponding to the pre-order traversal of an Abstract Syntax Tree. However, such a decoder only exploits the preorder traversal based preceding actions, which are insufficient to ensure correct action predictions. In this paper, we first throughly analyze the context modeling difference between neural code generation models with different traversals based decodings (preorder traversal vs breadth-first traversal), and then propose to introduce a mutual learning framework to jointly train these models. Under this framework, we continuously enhance both two models via mutual distillation, which involves synchronous executions of two one-to-one knowledge transfers at each training step. More specifically, we alternately choose one model as the student and the other as its teacher, and require the student to fit the training data and the action prediction distributions of its teacher. By doing so, both models can fully absorb the knowledge from each other and thus could be improved simultaneously. Experimental results and in-depth analysis on several benchmark datasets demonstrate the effectiveness of our approach. We release our code at https: //github. com/DeepLearnXMU/CGML.

PDF Details

AIJ Journal 2019 Journal Article

Exploiting reverse target-side contexts for neural machine translation via asynchronous bidirectional decoding

Jinsong Su
Xiangwen Zhang
Qian Lin
Yue Qin
Junfeng Yao
Yang Liu

Based on a unified encoder-decoder framework with attentional mechanism, neural machine translation (NMT) models have attracted much attention and become the mainstream in the community of machine translation. Generally, the NMT decoders produce translation in a left-to-right way. As a result, only left-to-right target-side contexts from the generated translations are exploited, while the right-to-left target-side contexts are completely unexploited for translation. In this paper, we extend the conventional attentional encoder-decoder NMT framework by introducing a backward decoder, in order to explore asynchronous bidirectional decoding for NMT. In the first step after encoding, our backward decoder learns to generate the target-side hidden states in a right-to-left manner. Next, in each timestep of translation prediction, our forward decoder concurrently considers both the source-side and the reverse target-side hidden states via two attention models. Compared with previous models, the innovation in this architecture enables our model to fully exploit contexts from both source side and target side, which improve translation quality altogether. We conducted experiments on NIST Chinese-English, WMT English-German and Finnish-English translation tasks to investigate the effectiveness of our model. Experimental results show that (1) our improved RNN-based NMT model achieves significant improvements over the conventional RNNSearch by 1. 44/-3. 02, 1. 11/-1. 01, and 1. 23/-1. 27 average BLEU and TER points, respectively; and (2) our enhanced Transformer outperforms the standard Transformer by 1. 56/-1. 49, 1. 76/-2. 49, and 1. 29/-1. 33 average BLEU and TER points, respectively. We released our code at https: //github. com/DeepLearnXMU/ABD-NMT.

Details DOI

IJCAI Conference 2015 Conference Paper

Discriminative Reordering Model Adaptation via Structural Learning

Biao Zhang
Jinsong Su
Deyi Xiong
Hong Duan
Junfeng Yao

Reordering model adaptation remains a big challenge in statistical machine translation because reordering patterns of translation units often vary dramatically from one domain to another. In this paper, we propose a novel adaptive discriminative reordering model (DRM) based on structural learning, which can capture correspondences among reordering features from two different domains. Exploiting both in-domain and out-of-domain monolingual corpora, our model learns a shared feature representation for cross-domain phrase reordering. Incorporating features of this representation, the DRM trained on out-of-domain corpus generalizes better to in-domain data. Experiment results on the NIST Chinese-English translation task show that our approach significantly outperforms a variety of baselines.

PDF Details