papers

Publications (44)

cs.RO2026

A Dataset and Benchmark for Robotic Cloth Unfolding Grasp Selection: The ICRA 2024 Cloth Competition

Victor-Louis De Gusseme, Thomas Lips, Remko Proesmans +59

Robotic cloth manipulation suffers from a lack of standardized benchmarks and shared datasets for evaluating and comparing different approaches. To address this, we created a bench…

cs.CV2026

Continual Hand-Eye Calibration for Open-world Robotic Manipulation

Fazeng Li, Gan Sun, Chenxi Liu +3

Hand-eye calibration through visual localization is a critical capability for robotic manipulation in open-world environments. However, most deep learning-based calibration models…

physics.chem-ph2023

A Machine Learning Approach Based on Range Corrected Deep Potential Model for Efficient Vibrational Frequency Computation

Jitai Yang, Yang Cong, You Li +1

As an ensemble average result, vibrational spectrum simulation can be time-consuming with high accuracy methods. We present a machine learning approach based on the range-corrected…

cs.LG2019

Visual Tactile Fusion Object Clustering

Tao Zhang, Yang Cong, Gan Sun +2

Object clustering, aiming at grouping similar objects into one cluster with an unsupervised strategy, has been extensivelystudied among various data-driven applications. However, m…

cs.CV2023

InOR-Net: Incremental 3D Object Recognition Network for Point Cloud Representation

Jiahua Dong, Yang Cong, Gan Sun +4

3D object recognition has successfully become an appealing research topic in the real-world. However, most existing recognition models unreasonably assume that the categories of 3D…

cs.CR2020

Data Poisoning Attacks on Federated Machine Learning

Gan Sun, Yang Cong, Jiahua Dong +2

Federated machine learning which enables resource constrained node devices (e.g., mobile phones and IoT devices) to learn a shared model while keeping the training data local, can…

cs.CV2025

Domain Consistency Representation Learning for Lifelong Person Re-Identification

Shiben Liu, Huijie Fan, Qiang Wang +3

Lifelong person re-identification (LReID) exhibits a contradictory relationship between intra-domain discrimination and inter-domain gaps when learning from continuous data. Intra-…

q-bio.MN2011

Analysis of the impact degree distribution in metabolic networks using branching process approximation

Kazuhiro Takemoto, Takeyuki Tamura, Yang Cong +3

Theoretical frameworks to estimate the tolerance of metabolic networks to various failures are important to evaluate the robustness of biological complex systems in systems biology…

cs.LG2023

Self-paced Weight Consolidation for Continual Learning

Wei Cong, Yang Cong, Gan Sun +2

Continual learning algorithms which keep the parameters of new tasks close to that of previous tasks, are popular in preventing catastrophic forgetting in sequential task learning…

cs.CV2024

MuseumMaker: Continual Style Customization without Catastrophic Forgetting

Chenxi Liu, Gan Sun, Wenqi Liang +3

Pre-trained large text-to-image (T2I) models with an appropriate text prompt has attracted growing interests in customized images generation field. However, catastrophic forgetting…

cs.MM2015

User-Curated Image Collections: Modeling and Recommendation

Yuncheng Li, Yang Cong, Tao Mei +1

Most state-of-the-art image retrieval and recommendation systems predominantly focus on individual images. In contrast, socially curated image collections, condensing distinctive y…

cs.RO2026

GAPG: Geometry Aware Push-Grasping Synergy for Goal-Oriented Manipulation in Clutter

Lijingze Xiao, Jinhong Du, Yang Cong +2

Grasping target objects is a fundamental skill for robotic manipulation, but in cluttered environments with stacked or occluded objects, a single-step grasp is often insufficient.…

cs.CV2024

Marrying NeRF with Feature Matching for One-step Pose Estimation

Ronghan Chen, Yang Cong, Yu Ren

Given the image collection of an object, we aim at building a real-time image-based pose estimation method, which requires neither its CAD model nor hours of object-specific traini…

cs.CV2023

No One Left Behind: Real-World Federated Class-Incremental Learning

Jiahua Dong, Hongliu Li, Yang Cong +3

Federated learning (FL) is a hot collaborative training framework via aggregating model parameters of decentralized local clients. However, most FL methods unreasonably assume data…

cs.LG2019

Lifelong Spectral Clustering

Gan Sun, Yang Cong, Qianqian Wang +2

In the past decades, spectral clustering (SC) has become one of the most effective clustering algorithms. However, most previous studies focus on spectral clustering tasks with a f…

cs.LG2026

Federated Multi-Task Clustering

Suyan Dai, Gan Sun, Fazeng Li +3

Spectral clustering has emerged as one of the most effective clustering algorithms due to its superior performance. However, most existing models are designed for centralized setti…

cs.CV2022

The Devil is in the Pose: Ambiguity-free 3D Rotation-invariant Learning via Pose-aware Convolution

Ronghan Chen, Yang Cong

Rotation-invariant (RI) 3D deep learning methods suffer performance degradation as they typically design RI representations as input that lose critical global information comparing…

cs.CV2021

Unsupervised Dense Deformation Embedding Network for Template-Free Shape Correspondence

Ronghan Chen, Yang Cong, Jiahua Dong

Shape correspondence from 3D deformation learning has attracted appealing academy interests recently. Nevertheless, current deep learning based methods require the supervision of d…

cs.RO2026

SuperGrasp: Single-View Object Grasping via Superquadric Similarity Matching, Evaluation, and Refinement

Lijingze Xiao, Jinhong Du, Supeng Diao +2

Robotic grasping from single-view observations remains a critical challenge in manipulation. However, existing methods still struggle to generate reliable grasp candidates and stab…

cs.RO2025

Never-Ending Behavior-Cloning Agent for Robotic Manipulation

Wenqi Liang, Gan Sun, Yao He +3

Relying on multi-modal observations, embodied robots (e.g., humanoid robots) could perform multiple robotic manipulation tasks in unstructured real-world environments. However, mos…

cs.CV2026

UniMotion: A Unified Framework for Motion-Text-Vision Understanding and Generation

Ziyi Wang, Xinshun Wang, Shuang Chen +2

We present UniMotion, to our knowledge the first unified framework for simultaneous understanding and generation of human motion, natural language, and RGB images within a single a…

cs.CV2026

PixelVLA: Advancing Pixel-level Understanding in Vision-Language-Action Model

Wenqi Liang, Gan Sun, Yao He +5

Vision-Language-Action models (VLAs) are emerging as powerful tools for learning generalizable visuomotor control policies. However, current VLAs are mostly trained on large-scale…

cs.CV2025

TMUAD: Enhancing Logical Capabilities in Unified Anomaly Detection Models with a Text Memory Bank

Jiawei Liu, Jiahe Hou, Wei Wang +3

Anomaly detection, which aims to identify anomalies deviating from normal patterns, is challenging due to the limited amount of normal data available. Unlike most existing unified…

cs.CV2019

Semantic-Transferable Weakly-Supervised Endoscopic Lesions Segmentation

Jiahua Dong, Yang Cong, Gan Sun +1

Weakly-supervised learning under image-level labels supervision has been widely applied to semantic segmentation of medical lesions regions. However, 1) most existing models rely o…

cs.CV2020

An End-to-End Geometric Deficiency Elimination Algorithm for 3D Meshes

Bingtao Ma, Hongsen Liu, Liangliang Nan +1

The 3D mesh is an important representation of geometric data. In the generation of mesh data, geometric deficiencies (e.g., duplicate elements, degenerate faces, isolated vertices,…

cs.LG2019

Representative Task Self-selection for Flexible Clustered Lifelong Learning

Gan Sun, Yang Cong, Qianqian Wang +2

Consider the lifelong machine learning paradigm whose objective is to learn a sequence of tasks depending on previous experiences, e.g., knowledge library or deep network weights.…

cs.CV2024

Learning Generalizable 3D Manipulation With 10 Demonstrations

Yu Ren, Yang Cong, Ronghan Chen +1

Learning robust and generalizable manipulation skills from demonstrations remains a key challenge in robotics, with broad applications in industrial automation and service robotics…

cs.LG2017

Lifelong Metric Learning

Gan Sun, Yang Cong, Ji Liu +1

The state-of-the-art online learning approaches are only capable of learning the metric for predefined tasks. In this paper, we consider lifelong learning problem to mimic "human l…

cs.CV2024

SAGA: Surface-Aligned Gaussian Avatar

Ronghan Chen, Yang Cong, Jiayue Liu

This paper presents a Surface-Aligned Gaussian representation for creating animatable human avatars from monocular videos,aiming at improving the novel view and pose synthesis perf…

cs.CV2020

Weakly-Supervised Cross-Domain Adaptation for Endoscopic Lesions Segmentation

Jiahua Dong, Yang Cong, Gan Sun +3

Weakly-supervised learning has attracted growing research attention on medical lesions segmentation due to significant saving in pixel-level annotation cost. However, 1) most exist…

cs.RO2025

OpenVLN: Open-world Aerial Vision-Language Navigation

Peican Lin, Gan Sun, Chenxi Liu +3

Vision-language models (VLMs) have been widely-applied in ground-based vision-language navigation (VLN). However, the vast complexity of outdoor aerial environments compounds data…

cs.CV2023

Gradient-Semantic Compensation for Incremental Semantic Segmentation

Wei Cong, Yang Cong, Jiahua Dong +2

Incremental semantic segmentation aims to continually learn the segmentation of new coming classes without accessing the training data of previously learned classes. However, most…

cs.CV2020

CSCL: Critical Semantic-Consistent Learning for Unsupervised Domain Adaptation

Jiahua Dong, Yang Cong, Gan Sun +2

Unsupervised domain adaptation without consuming annotation process for unlabeled target data attracts appealing interests in semantic segmentation. However, 1) existing methods ne…

cs.CV2020

I3DOL: Incremental 3D Object Learning without Catastrophic Forgetting

Jiahua Dong, Yang Cong, Gan Sun +2

3D object classification has attracted appealing attentions in academic researches and industrial applications. However, most existing methods need to access the training data of p…

cs.CV2020

L3DOC: Lifelong 3D Object Classification

Yuyang Liu, Yang Cong, Gan Sun

3D object classification has been widely-applied into both academic and industrial scenarios. However, most state-of-the-art algorithms are facing with a fixed 3D object classifica…

cs.RO2021

Generative Partial Visual-Tactile Fused Object Clustering

Tao Zhang, Yang Cong, Gan Sun +3

Visual-tactile fused sensing for object clustering has achieved significant progresses recently, since the involvement of tactile modality can effectively improve clustering perfor…

cs.RO2026

Towards Human-like Physical Intelligence: Lifelong Vision-Language-Action Learning for Robotic Manipulation

Yao He, Gan Sun, Wenqi Liang +2

The paper introduces LifelongVLA, a framework that enables robots to continuously learn new manipulation tasks by using a dual-timescale adaptation mechanism and a cache-efficient…

#lifelong learning#vision-language-action#robotic manipulation#adaptive adapters
cs.CV2024

Cs2K: Class-specific and Class-shared Knowledge Guidance for Incremental Semantic Segmentation

Wei Cong, Yang Cong, Yuyang Liu +1

Incremental semantic segmentation endeavors to segment newly encountered classes while maintaining knowledge of old classes. However, existing methods either 1) lack guidance from…

cs.CV2020

What Can Be Transferred: Unsupervised Domain Adaptation for Endoscopic Lesions Segmentation

Jiahua Dong, Yang Cong, Gan Sun +2

Unsupervised domain adaptation has attracted growing research attention on semantic segmentation. However, 1) most existing models cannot be directly applied into lesions transfer…

cs.CV2023

Create Your World: Lifelong Text-to-Image Diffusion

Gan Sun, Wenqi Liang, Jiahua Dong +3

Text-to-image generative models can produce diverse high-quality images of concepts with a text prompt, which have demonstrated excellent ability in image generation, image transla…

cs.CV2023

Heterogeneous Forgetting Compensation for Class-Incremental Learning

Jiahua Dong, Wenqi Liang, Yang Cong +1

Class-incremental learning (CIL) has achieved remarkable successes in learning new classes consecutively while overcoming catastrophic forgetting on old categories. However, most e…

cs.LG2021

Evolving Metric Learning for Incremental and Decremental Features

Jiahua Dong, Yang Cong, Gan Sun +3

Online metric learning has been widely exploited for large-scale data classification due to the low computational cost. However, amongst online practical scenarios where the featur…

cs.CV2026

Crafting Your Evolving Dreams: Concept-Incremental Versatile Customization

Jiahua Dong, Wenqi Liang, Hongliu Li +7

Custom diffusion models (CDMs) have garnered significant interest owing to their remarkable capacity for generating personalized concepts. However, the majority of CDMs unrealistic…

cs.CV2023

Federated Incremental Semantic Segmentation

Jiahua Dong, Duzhen Zhang, Yang Cong +3

Federated learning-based semantic segmentation (FSS) has drawn widespread attention via decentralized training on local clients. However, most FSS models assume categories are fixe…