Author name cluster

Zhanglin Peng

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.

5 papers

2 author rows

EAAI Journal 2025 Journal Article

A novel integrated prediction method using adaptive mode decomposition, attention mechanism and deep learning for coking products prices

Xuhui Zhu
Chenggong Ma
Hao Lei
Pingfan Xia
zhanglin peng

Accurate prediction of coking product prices is crucial for enhancing production efficiency, cost optimization, and profit maximization in smart coking facilities. To address the volatility caused by nonlinear factors such as raw material costs, substitutes, macroeconomic indicators, sudden events, policy changes, and market behaviors, we propose a novel integrated prediction method for coking product price prediction. This method combines Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) for signal decomposition, Bidirectional Encoder Representations from Transformers (BERT) for natural language processing, attention mechanisms (AT) to weigh feature importance, and an ensemble of Bidirectional Gated Recurrent Unit, Bidirectional Long Short-Term Memory, and Gated Recurrent Unit, abbreviated BBG, for robust feature extraction. We design a feature selection strategy to avoid data leakage and improve the predictive ability of the model, and describe a method to maintain textual data information integrity when combining data from different sources. Experimental results on coke and methanol datasets show that our approach retains multi-source text richness improves predictive capability, and outperforms other state-of-the-art methods, providing an effective tool for developing smart coke plants.

Details DOI

NeurIPS Conference 2025 Conference Paper

GauDP: Reinventing Multi-Agent Collaboration through Gaussian-Image Synergy in Diffusion Policies

Ziye Wang
Li Kang
Yiran Qin
Jiahua Ma
zhanglin peng
Lei Bai
Ruimao Zhang

Despite significant advances in robotic policy generation, effective coordination in embodied multi-agent systems remains a fundamental challenge—particularly in scenarios where agents must balance individual perspectives with global environmental awareness. Existing approaches often struggle to balance fine-grained local control with comprehensive scene understanding, resulting in limited scalability and compromised collaboration quality. In this paper, we present GauDP, a novel Gaussian-image synergistic representation that facilitates scalable, perception-aware imitation learning in multi-agent collaborative systems. Specifically, GauDP reconstructs a globally consistent 3D Gaussian field from local-view RGB images, allowing all agents to dynamically query task-relevant features from a shared scene representation. This design facilitates both fine-grained control and globally coherent behavior without requiring additional sensing modalities. We evaluate GauDP on the RoboFactory benchmark, which includes diverse multi-arm manipulation tasks. Our method achieves superior performance over existing image-based methods and approaches the effectiveness of point-cloud-driven methods, while maintaining strong scalability as the number of agents increases. Extensive ablations and visualizations further demonstrate the robustness and efficiency of our unified local-global perception framework for multi-agent embodied learning.

PDF Details

NeurIPS Conference 2023 Conference Paper

Foundation Model is Efficient Multimodal Multitask Model Selector

Fanqing Meng
Wenqi Shao
zhanglin peng
Chonghe Jiang
Kaipeng Zhang
Yu Qiao
Ping Luo

This paper investigates an under-explored but important problem: given a collection of pre-trained neural networks, predicting their performance on each multi-modal task without fine-tuning them, such as image recognition, referring, captioning, visual question answering, and text question answering. A brute-force approach is to finetune all models on all target datasets, bringing high computational costs. Although recent-advanced approaches employed lightweight metrics to measure models’ transferability, they often depend heavily on the prior knowledge of a single task, making them inapplicable in a multi-modal multi-task scenario. To tackle this issue, we propose an efficient multi-task model selector (EMMS), which employs large-scale foundation models to transform diverse label formats such as categories, texts, and bounding boxes of different downstream tasks into a unified noisy label embedding. EMMS can estimate a model’s transferability through a simple weighted linear regression, which can be efficiently solved by an alternating minimization algorithm with a convergence guarantee. Extensive experiments on 5 downstream tasks with 24 datasets show that EMMS is fast, effective, and generic enough to assess the transferability of pre-trained models, making it the first model selection method in the multi-task scenario. For instance, compared with the state- of-the-art method LogME enhanced by our label embeddings, EMMS achieves 9. 0%, 26. 3%, 20. 1%, 54. 8%, 12. 2% performance gain on image recognition, referring, captioning, visual question answering, and text question answering, while bringing 5. 13×, 6. 29×, 3. 59×, 6. 19×, and 5. 66× speedup in wall-clock time, respectively. The code is available at https: //github. com/OpenGVLab/Multitask-Model-Selector.

PDF Details

ICML Conference 2019 Conference Paper

Differentiable Dynamic Normalization for Learning Deep Representation

Ping Luo 0002
Zhanglin Peng
Wenqi Shao
Ruimao Zhang
Jiamin Ren
Lingyun Wu

This work presents Dynamic Normalization (DN), which is able to learn arbitrary normalization operations for different convolutional layers in a deep ConvNet. Unlike existing normalization approaches that predefined computations of the statistics (mean and variance), DN learns to estimate them. DN has several appealing benefits. First, it adapts to various networks, tasks, and batch sizes. Second, it can be easily implemented and trained in a differentiable end-to-end manner with merely small number of parameters. Third, its matrix formulation represents a wide range of normalization methods, shedding light on analyzing them theoretically. Extensive studies show that DN outperforms its counterparts in CIFAR10 and ImageNet.

Details

IJCAI Conference 2016 Conference Paper

Geometric Scene Parsing with Hierarchical LSTM

zhanglin peng
Ruimao Zhang
Xiaodan Liang
Xiaobai Liu
Liang Lin

This paper addresses the problem of geometric scene parsing, i. e. simultaneously labeling geometric surfaces (e. g. sky, ground and vertical plane) and determining the interaction relations (e. g. layering, supporting, siding and affinity) between main regions. This problem is more challenging than the traditional semantic scene labeling, as recovering geometric structures necessarily requires the rich and diverse contextual information. To achieve these goals, we propose a novel recurrent neural network model, named Hierarchical Long Short-Term Memory (H-LSTM). It contains two coupled sub-networks: the Pixel LSTM (P-LSTM) and the Multi-scale Super-pixel LSTM (MS-LSTM) for handling the surface labeling and relation prediction, respectively. The two sub-networks provide complementary information to each other to exploit hierarchical scene contexts, and they are jointly optimized for boosting the performance. Our extensive experiments show that our model is capable of parsing scene geometric structures and outperforming several state-of-the-art methods by large margins. In addition, we show promising 3D reconstruction results from the still images based on the geometric parsing.

PDF Details