Feng Hong

EAAI Journal 2026 Journal Article

FishMotionNet: Integrating hydrological factors and fishing motion patterns for enhanced vessel trajectory prediction

• Guitong Yang
• Guiyuan Jiang
• Jiaqi Yang
• Feng Hong
• Peilan He
• Zhongning Zhao

NeurIPS Conference 2025 Conference Paper

Learning to Instruct for Visual Instruction Tuning

• Zhihan Zhou
• Feng Hong
• JIAAN LUO
• Yushi Ye
• Jiangchao Yao
• Dongsheng Li
• Bo Han
• Ya Zhang

We propose L2T, an advancement of visual instruction tuning (VIT). While VIT equips Multimodal LLMs (MLLMs) with promising multimodal capabilities, the current design choices for VIT often result in overfitting and shortcut learning, potentially degrading performance. This gap arises from an overemphasis on instruction-following abilities, while neglecting the proactive understanding of visual information. Inspired by this, L2T adopts a simple yet effective approach by incorporating the loss function into both the instruction and response sequences. It seamlessly expands the training data, and regularizes the MLLMs from overly relying on language priors. Based on this merit, L2T achieves a significant relative improvement of up to 9% on comprehensive multimodal benchmarks, requiring no additional training data and incurring negligible computational overhead. Surprisingly, L2T attains exceptional fundamental visual capabilities, yielding up to an 18% improvement in captioning performance, while simultaneously alleviating hallucination in MLLMs. Github code: https: //github. com/Feng-Hong/L2T.

NeurIPS Conference 2025 Conference Paper

Long-tailed Recognition with Model Rebalancing

• JIAAN LUO
• Feng Hong
• Qiang Hu
• Xiaofeng Cao
• Feng Liu
• Jiangchao Yao

Long-tailed recognition is ubiquitous and challenging in deep learning and even in the downstream finetuning of foundation models, since the skew class distribution generally prevents the model generalization to the tail classes. Despite the promise of previous methods from the perspectives of data augmentation, loss rebalancing and decoupled training etc. , consistent improvement in the broad scenarios like multi-label long-tailed recognition is difficult. In this study, we dive into the essential model capacity impact under long-tailed context, and propose a novel framework, Model Rebalancing (MORE), which mitigates imbalance by directly rebalancing the model's parameter space. Specifically, MORE introduces a low-rank parameter component to mediate the parameter space allocation guided by a tailored loss and sinusoidal reweighting schedule, but without increasing the overall model complexity or inference costs. Extensive experiments on diverse long-tailed benchmarks, spanning multi-class and multi-label tasks, demonstrate that MORE significantly improves generalization, particularly for tail classes, and effectively complements existing imbalance mitigation methods. These results highlight MORE's potential as a robust plug-and-play module in long-tailed settings.

IJCAI Conference 2025 Conference Paper

Non-collective Calibrating Strategy for Time Series Forecasting

• Bin Wang
• Yongqi Han
• Minbo Ma
• Tianrui Li
• Junbo Zhang
• Feng Hong
• Yanwei Yu

Deep learning-based approaches have demonstrated significant advancements in time series forecasting. Despite these ongoing developments, the complex dynamics of time series make it challenging to establish the rule of thumb for designing the golden model architecture. In this study, we argue that refining existing advanced models through a universal calibrating strategy can deliver substantial benefits with minimal resource costs, as opposed to elaborating and training a new model from scratch. We first identify a multi-target learning conflict in the calibrating process, which arises when optimizing variables across time steps, leading to the underutilization of the model's learning capabilities. To address this issue, we propose an innovative calibrating strategy called Socket+Plug (SoP). This approach retains an exclusive optimizer and early-stopping monitor for each predicted target within each Plug while keeping the fully trained Socket backbone frozen. The model-agnostic nature of SoP allows it to directly calibrate the performance of any trained deep forecasting models, regardless of their specific architectures. Extensive experiments on various time series benchmarks and a spatio-temporal meteorological ERA5 dataset demonstrate the effectiveness of SoP, achieving up to a 22% improvement even when employing a simple MLP as the Plug (highlighted in Figure 1).

NeurIPS Conference 2024 Conference Paper

Revive Re-weighting in Imbalanced Learning by Density Ratio Estimation

• JIAAN LUO
• Feng Hong
• Jiangchao Yao
• Bo Han
• Ya Zhang
• Yanfeng Wang

In deep learning, model performance often deteriorates when trained on highly imbalanced datasets, especially when evaluation metrics require robust generalization across underrepresented classes. To address the challenges posed by imbalanced data distributions, this study introduces a novel method utilizing density ratio estimation for dynamic class weight adjustment, termed as Re-weighting with Density Ratio (RDR). Our method adaptively adjusts the importance of each class during training, mitigates overfitting on dominant classes and enhances model adaptability across diverse datasets. Extensive experiments conducted on various large scale benchmark datasets validate the effectiveness of our method. Results demonstrate substantial improvements in generalization capabilities, particularly under severely imbalanced conditions.

NeurIPS Conference 2023 Conference Paper

Combating Representation Learning Disparity with Geometric Harmonization

• Zhihan Zhou
• Jiangchao Yao
• Feng Hong
• Ya Zhang
• Bo Han
• Yanfeng Wang

Self-supervised learning (SSL) as an effective paradigm of representation learning has achieved tremendous success on various curated datasets in diverse scenarios. Nevertheless, when facing the long-tailed distribution in real-world applications, it is still hard for existing methods to capture transferable and robust representation. The attribution is that the vanilla SSL methods that pursue the sample-level uniformity easily leads to representation learning disparity, where head classes with the huge sample number dominate the feature regime but tail classes with the small sample number passively collapse. To address this problem, we propose a novel Geometric Harmonization (GH) method to encourage the category-level uniformity in representation learning, which is more benign to the minority and almost does not hurt the majority under long-tailed distribution. Specially, GH measures the population statistics of the embedding space on top of self-supervised learning, and then infer an fine-grained instance-wise calibration to constrain the space expansion of head classes and avoid the passive collapse of tail classes. Our proposal does not alter the setting of SSL and can be easily integrated into existing methods in a low-cost manner. Extensive results on a range of benchmark datasets show the effectiveness of \methodspace with high tolerance to the distribution skewness.

AAAI Conference 2021 Conference Paper

A Bottom-Up DAG Structure Extraction Model for Math Word Problems

• Yixuan Cao
• Feng Hong
• Hongwei Li
• Ping Luo

Research on automatically solving mathematical word problems (MWP) has a long history. Most recent works adopt the Seq2Seq approach to predict the result equations as a sequence of quantities and operators. Although result equations can be written as a sequence, it is essentially a structure. More precisely, it is a Direct Acyclic Graph (DAG) whose leaf nodes are the quantities, and internal and root nodes are arithmetic or comparison operators. In this paper, we propose a novel Seq2DAG approach to extract the equation set directly as a DAG structure. It extracts the structure in a bottom-up fashion by aggregating quantities and sub-expressions layer by layer iteratively. The advantages of our approach are threefold: it is intrinsically suitable to solve multivariate problems, it always outputs valid structure, and its computation satisfies commutative law for +, × and =. Experimental results on DRAW1K and Math23K datasets demonstrate that our model outperforms state-of-the-art deep learning methods. We also conduct detailed analysis on the results to show the strengths and limitations of our approach.

IJCAI Conference 2021 Conference Paper

Learning to Learn Personalized Neural Network for Ventricular Arrhythmias Detection on Intracardiac EGMs

• Zhenge Jia
• Zhepeng Wang
• Feng Hong
• Lichuan PING
• Yiyu Shi
• Jingtong Hu

Life-threatening ventricular arrhythmias (VAs) detection on intracardiac electrograms (IEGMs) is essential to Implantable Cardioverter Defibrillators (ICDs). However, current VAs detection methods count on a variety of heuristic detection criteria, and require frequent manual interventions to personalize criteria parameters for each patient to achieve accurate detection. In this work, we propose a one-dimensional convolutional neural network (1D-CNN) based life-threatening VAs detection on IEGMs. The network architecture is elaborately designed to satisfy the extreme resource constraints of the ICD while maintaining high detection accuracy. We further propose a meta-learning algorithm with a novel patient-wise training tasks formatting strategy to personalize the 1D-CNN. The algorithm generates a well-generalized model initialization containing across-patient knowledge, and performs a quick adaptation of the model to the specific patient's IEGMs. In this way, a new patient could be immediately assigned with personalized 1D-CNN model parameters using limited input data. Compared with the conventional VAs detection method, the proposed method achieves 2. 2% increased sensitivity for detecting VAs rhythm and 8. 6% increased specificity for non-VAs rhythm.

EAAI Journal 2019 Journal Article

Workflow difference detection based on basis paths

• Bin Cao
• Feng Hong
• Jiaxing Wang
• Jing Fan
• Mingqi Lv