Author name cluster

Zhiyang Chen

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.

8 papers

1 author row

AAAI Conference 2026 Conference Paper

Empowering DINO Representations for Underwater Instance Segmentation via Aligner and Prompter

Zhiyang Chen
Chen Zhang
Hao Fang
Runmin Cong

Underwater Instance Segmentation (UIS), integrating pixel-level understanding and instance-level discrimination, is a pivotal technology in marine resource exploration and ecological protection. In recent years, large-scale pretrained visual foundation models, exemplified by DINO, have advanced rapidly and demonstrated remarkable performance on complex downstream tasks. In this paper, we demonstrate that DINO can serve as an effective feature learner for UIS, and we introduce DiveSeg, a novel framework built upon two insightful components: (1) The AquaStyle Aligner, designed to embed underwater color style features into the DINO fine-tuning process, facilitating better adaptation to the underwater domain. (2) The ObjectPrior Prompter, which incorporates binary segmentation-based prompts to deliver object-level priors, provides essential guidance for instance segmentation task that requires both object- and instance-level reasoning. We conduct thorough experiments on the popular UIIS and USIS10K datasets, and the results show that DiveSeg achieves the state-of-the-art performance.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Minimum-Cost Network Flow with Dual Predictions

Zhiyang Chen
Hailong Yao
Xia Yin

Recent work has shown that machine-learned predictions can provably improve the performance of classic algorithms. In this work, we propose the first minimum-cost network flow algorithm augmented with a dual prediction. Our method is based on a classic minimum-cost flow algorithm, namely ε-relaxation. We provide time complexity bounds in terms of the infinity norm prediction error, which is both consistent and robust. We also prove sample complexity bounds for PAC-learning the prediction. We empirically validate our theoretical results on two applications of minimum-cost flow, i.e., traffic networks and chip escape routing, in which we learn a fixed prediction, and a feature-based neural network model to infer the prediction, respectively. Experimental results illustrate 12.74× and 1.64× average speedup on two applications.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Generalization Bounds for Model-based Algorithm Configuration

Zhiyang Chen
Hailong Yao
Xia Yin

Algorithm configuration, which involves selecting algorithm parameters based on sampled problem instances, is a crucial step in applying modern algorithms such as SAT solvers. Although prior work has attempted to understand the theoretical foundations of algorithm configuration, we still lack a comprehensive understanding of why practical algorithm configurators exhibit strong generalization performances in real-world scenarios. In this paper, through the lens of machine learning theory, we provide an algorithm-dependent generalization bound for the widely used model-based algorithm configurators under mild assumptions. Our approach is based on the algorithmic stability framework for generalization bounds. To the best of our knowledge, this is the first generalization bound that applies to a model closely approximating practical model-based algorithm configurators.

PDF Details

NeurIPS Conference 2025 Conference Paper

Reinforcing the Diffusion Chain of Lateral Thought with Diffusion Language Models

Zemin Huang
Zhiyang Chen
Zijun Wang
Tiancheng Li
Guo-Jun Qi

We introduce the Diffusion Chain of Lateral Thought (DCoLT), a reasoning framework for diffusion language models. DCoLT treats each intermediate step in the reverse diffusion process as a latent "thinking" action and optimizes the entire reasoning trajectory to maximize the reward on the correctness of the final answer with outcome-based Reinforcement Learning (RL). Unlike traditional Chain-of-Thought (CoT) methods that follow a causal, linear thinking process, DCoLT allows bidirectional, non-linear reasoning with no strict rule on grammatical correctness amid its intermediate steps of thought. We implement DCoLT on two representative Diffusion Language Models (DLMs). First, we choose SEDD as a representative continuous-time discrete diffusion model, where its concrete score derives a probabilistic policy to maximize the RL reward over the entire sequence of intermediate diffusion steps. We further consider the discrete-time masked diffusion language model -- LLaDA, and find that the order to predict and unmask tokens plays an essential role to optimize its RL action resulting from the ranking-based Unmasking Policy Module (UPM) defined by the Plackett-Luce model. Experiments on both math and code generation tasks show that using only public data and 16 H800 GPUs, DCoLT-reinforced DLMs outperform other DLMs trained by SFT or RL or even both. Notably, DCoLT-reinforced LLaDA boosts its reasoning accuracy by +9. 8%, +5. 7%, +11. 4%, +19. 5% on GSM8K, MATH, MBPP, and HumanEval.

PDF Details

JBHI Journal 2024 Journal Article

Evolutionary Ensemble Learning for EEG-Based Cross-Subject Emotion Recognition

Hanzhong Zhang
Tienyu Zuo
Zhiyang Chen
Xin Wang
Poly Z.H. Sun

Electroencephalogram (EEG) has been widely utilized in emotion recognition due to its high temporal resolution and reliability. However, the individual differences and non-stationary characteristics of EEG, along with the complexity and variability of emotions, pose challenges in generalizing emotion recognition models across subjects. In this paper, an end-to-end framework is proposed to improve the performance of cross-subject emotion recognition. A novel evolutionary programming (EP)-based optimization strategy with neural network (NN) as the base classifier termed NN ensemble with EP (EPNNE) is designed for cross-subject emotion recognition. The effectiveness of the proposed method is evaluated on the publicly available DEAP, FACED, SEED, and SEED-IV datasets. Numerical results demonstrate that the proposed method is superior to state-of-the-art cross-subject emotion recognition methods. The proposed end-to-end framework for cross-subject emotion recognition aids biomedical researchers in effectively assessing individual emotional states, thereby enabling efficient treatment and interventions.

Details DOI

NeurIPS Conference 2022 Conference Paper

Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Tasks

Zhiyang Chen
Yousong Zhu
Zhaowen Li
Fan Yang
Wei Li
Haixin Wang
Chaoyang Zhao
Liwei Wu

Visual tasks vary a lot in their output formats and concerned contents, therefore it is hard to process them with an identical structure. One main obstacle lies in the high-dimensional outputs in object-level visual tasks. In this paper, we propose an object-centric vision framework, Obj2Seq. Obj2Seq takes objects as basic units, and regards most object-level visual tasks as sequence generation problems of objects. Therefore, these visual tasks can be decoupled into two steps. First recognize objects of given categories, and then generate a sequence for each of these objects. The definition of the output sequences varies for different tasks, and the model is supervised by matching these sequences with ground-truth targets. Obj2Seq is able to flexibly determine input categories to satisfy customized requirements, and be easily extended to different visual tasks. When experimenting on MS COCO, Obj2Seq achieves 45. 7% AP on object detection, 89. 0% AP on multi-label classification and 65. 0% AP on human pose estimation. These results demonstrate its potential to be generally applied to different visual tasks. Code has been made available at: https: //github. com/CASIA-IVA-Lab/Obj2Seq.

PDF Details

NeurIPS Conference 2021 Conference Paper

MST: Masked Self-Supervised Transformer for Visual Representation

Zhaowen Li
Zhiyang Chen
Fan Yang
Wei Li
Yousong Zhu
Chaoyang Zhao
Rui Deng
Liwei Wu

Transformer has been widely used for self-supervised pre-training in Natural Language Processing (NLP) and achieved great success. However, it has not been fully explored in visual self-supervised learning. Meanwhile, previous methods only consider the high-level feature and learning representation from a global perspective, which may fail to transfer to the downstream dense prediction tasks focusing on local features. In this paper, we present a novel Masked Self-supervised Transformer approach named MST, which can explicitly capture the local context of an image while preserving the global semantic information. Specifically, inspired by the Masked Language Modeling (MLM) in NLP, we propose a masked token strategy based on the multi-head self-attention map, which dynamically masks some tokens of local patches without damaging the crucial structure for self-supervised learning. More importantly, the masked tokens together with the remaining tokens are further recovered by a global image decoder, which preserves the spatial information of the image and is more friendly to the downstream dense prediction tasks. The experiments on multiple datasets demonstrate the effectiveness and generality of the proposed method. For instance, MST achieves Top-1 accuracy of 76. 9% with DeiT-S only using 300-epoch pre-training by linear evaluation, which outperforms supervised methods with the same epoch by 0. 4% and its comparable variant DINO by 1. 0%. For dense prediction tasks, MST also achieves 42. 7% mAP on MS COCO object detection and 74. 04% mIoU on Cityscapes segmentation only with 100-epoch pre-training.

PDF Details

IJCAI Conference 2019 Conference Paper

Dual Self-Paced Graph Convolutional Network: Towards Reducing Attribute Distortions Induced by Topology

Liang Yang
Zhiyang Chen
Junhua Gu
Yuanfang Guo

The success of graph convolutional neural networks (GCNNs) based semi-supervised node classification is credited to the attribute smoothing (propagating) over the topology. However, the attributes may be interfered by the utilization of the topology information. This distortion will induce a certain amount of misclassifications of the nodes, which can be correctly predicted with only the attributes. By analyzing the impact of the edges in attribute propagations, the simple edges, which connect two nodes with similar attributes, should be given priority during the training process compared to the complex ones according to curriculum learning. To reduce the distortions induced by the topology while exploit more potentials of the attribute information, Dual Self-Paced Graph Convolutional Network (DSP-GCN) is proposed in this paper. Specifically, the unlabelled nodes with confidently predicted labels are gradually added into the training set in the node-level self-paced learning, while edges are gradually, from the simple edges to the complex ones, added into the graph during the training process in the edge-level self-paced learning. These two learning strategies are designed to mutually reinforce each other by coupling the selections of the edges and unlabelled nodes. Experimental results of transductive semi-supervised node classification on many real networks indicate that the proposed DSP-GCN has successfully reduced the attribute distortions induced by the topology while it gives superior performances with only one graph convolutional layer.

PDF Details