Author name cluster

Jinyu Yang

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.

6 papers

2 author rows

AAAI Conference 2025 Conference Paper

Harnessing Language Model for Cross-Heterogeneity Graph Knowledge Transfer

Jinyu Yang
Ruijia Wang
Cheng Yang
Bo Yan
Qimin Zhou
Yang Juan
Chuan Shi

Heterogeneous graphs (HGs) that contain various node and edge types are ubiquitous in real-world scenarios. Considering the common label sparsity problem in HGs, some researchers propose to pretrain on source HGs to extract general knowledge and then fine-tune on a target HG for knowledge transfer. However, existing methods often assume that source and target HGs share a single heterogeneity, meaning that they have the same types of nodes and edges, which contradicts the real-world scenarios requiring cross-heterogeneity transfer. Although a recent study has made some preliminary attempts in cross-heterogeneity learning, its definition of general knowledge heavily rely on human knowledge, which lacks flexibility and further leads to a suboptimal transfer. To address the problem, we propose a novel Language Model-enhanced Cross-Heterogeneity learning model, namely LMCH. Specifically, we first design a metapath-based corpus construction method to unify HG representations as languages. The corpora of source HGs are then used to fine-tune a pretrained Language Model (LM), enabling the LM to autonomously extract general knowledge across different HGs. Furthermore, to fully utilize the extensive unlabeled nodes in a few-labeled target HG, we propose an iterative training pipeline with the help of an extra Graph Neural Network (GNN) predictor, enhanced by LM-GNN contrastive alignment at the end of each iteration. Extensive experiments on four real-world datasets have demonstrated the superior performance of LMCH over state-of-the-art methods.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

OptiScene: LLM-driven Indoor Scene Layout Generation via Scaled Human-aligned Data Synthesis and Multi-Stage Preference Optimization

Yixuan Yang
Zhen Luo
Tongsheng Ding
Junru Lu
Mingqi Gao
Jinyu Yang
Victor Sanchez
Feng Zheng

Automatic indoor layout generation has attracted increasing attention due to its potential in interior design, virtual environment construction, and embodied AI. Existing methods fall into two categories: prompt-driven approaches that leverage proprietary LLM services (e. g. , GPT APIs), and learning-based methods trained on layout data upon diffusion-based models. Prompt-driven methods often suffer from spatial inconsistency and high computational costs, while learning-based methods are typically constrained by coarse relational graphs and limited datasets, restricting their generalization to diverse room categories. In this paper, we revisit LLM-based indoor layout generation and present 3D-SynthPlace, a large-scale dataset that combines synthetic layouts generated via a `GPT synthesize, Human inspect' pipeline, upgraded from the 3D-Front dataset. 3D-SynthPlace contains nearly 17, 000 scenes, covering four common room types—bedroom, living room, kitchen, and bathroom—enriched with diverse objects and high-level spatial annotations. We further introduce OptiScene, a strong open-source LLM optimized for indoor layout generation, fine-tuned based on our 3D-SynthPlace dataset through our two-stage training. For the warum-up stage I, we adopt supervised fine-tuning (SFT), which is taught to first generate high-level spatial descriptions then conditionally predict concrete object placements. For the reinforcing stage II, to better align the generated layouts with human design preferences, we apply multi-turn direct preference optimization (DPO), which significantly improving layout quality and generation success rates. Extensive experiments demonstrate that OptiScene outperforms traditional prompt-driven and learning-based baselines. Moreover, OptiScene shows promising potential in interactive tasks such as scene editing and robot navigation, highlighting its applicability beyond static layout generation.

PDF Details

IJCAI Conference 2024 Conference Paper

Place Anything into Any Video

Ziling Liu
Jinyu Yang
Mingqi Gao
Feng Zheng

Controllable video editing has demonstrated remarkable potential across diverse applications, particularly in scenarios where capturing or re-capturing real-world videos is either impractical or costly. This paper introduces a novel and efficient system named Place-Anything, which facilitates the insertion of any object into any video solely based on a picture or text description of the target object or element. The system comprises three modules: 3D generation, video reconstruction, and 3D target insertion. This integrated approach offers an efficient and effective solution for producing and editing high-quality videos by naturally inserting realistic objects. Through experiment, we demonstrate that our system can effortlessly place any object into any video using just a photograph of the object. Our demo video can be found at https: //youtu. be/afXqgLLRnTE. Please also visit our project page https: //place-anything. github. io to get more information.

PDF Details DOI

IROS Conference 2024 Conference Paper

Towards Unconstrained Collision Injury Protection Data Sets: Initial Surrogate Experiments for the Human Hand

Robin Jeanne Kirschner
Jinyu Yang
Edonis Elshani
Carina Micheler
Tobias Leibbrand
Dirk Müller
Claudio Glowalla
Nader Rajaei

Safety for physical human-robot interaction (pHRI) is a major concern for all application domains. While current standardization for industrial robot applications provide safety constraints that address the onset of pain in blunt impacts, these impact thresholds are difficult to use on edged or pointed impactors. The most severe injuries occur in constrained contact scenarios, where crushing is possible. Nevertheless, situations potentially resulting in constrained contact only occur in certain areas of a workspace and design or organisational approaches can be used to avoid them. What remains are risks to the human physical integrity caused by unconstrained accidental contacts, which are difficult to avoid while maintaining robot motion efficiency. Nevertheless, the probability and severity of injuries occurring with edged or pointed impacting objects in unconstrained collisions is hardly researched. In this paper, we propose an experimental setup and procedure using two pendulums modeling human hands and arms and robots to understand the injury potential of unconstrained collisions of human hands with edged objects. Pig feet are used as ex vivo surrogate samples - as these closely resemble the physiological characteristics of human hands - to create an initial injury database on the severity of injuries caused by unconstrained edged or pointed impacts. For the effective mass range of typical lightweight robots, the data obtained show low probabilities of injuries such as skin cuts or bone/tendon injuries in unconstrained collisions when the velocity is reduced to < 0. 5 m/s. Additionally, distinct differences between injury probability of the finger substitutes and the back of the hand substitutes are observed. The proposed experimental setups and procedures should be complemented by sufficient human modeling, e. g. the effective masses of human body parts, and will eventually lead to a complete understanding of the biomechanical injury potential in pHRI.

Details

AAAI Conference 2021 Conference Paper

Hierarchical Graph Capsule Network

Jinyu Yang
Peilin Zhao
Yu Rong
Chaochao Yan
Chunyuan Li
Hehuan Ma
Junzhou Huang

Graph Neural Networks (GNNs) draw their strength from explicitly modeling the topological information of structured data. However, existing GNNs suffer from limited capability in capturing the hierarchical graph representation which plays an important role in graph classification. In this paper, we innovatively propose hierarchical graph capsule network (HGCN) that can jointly learn node embeddings and extract graph hierarchies. Specifically, disentangled graph capsules are established by identifying heterogeneous factors underlying each node, such that their instantiation parameters represent different properties of the same entity. To learn the hierarchical representation, HGCN characterizes the part-whole relationship between lower-level capsules (part) and higherlevel capsules (whole) by explicitly considering the structure information among the parts. Experimental studies demonstrate the effectiveness of HGCN and the contribution of each component. Code: https: //github. com/uta-smile/HGCN

PDF Details

NeurIPS Conference 2020 Conference Paper

RetroXpert: Decompose Retrosynthesis Prediction Like A Chemist

Chaochao Yan
Qianggang Ding
Peilin Zhao
Shuangjia Zheng
Jinyu Yang
Yang Yu
Junzhou Huang

Retrosynthesis is the process of recursively decomposing target molecules into available building blocks. It plays an important role in solving problems in organic synthesis planning. To automate or assist in the retrosynthesis analysis, various retrosynthesis prediction algorithms have been proposed. However, most of them are cumbersome and lack interpretability about their predictions. In this paper, we devise a novel template-free algorithm for automatic retrosynthetic expansion inspired by how chemists approach retrosynthesis prediction. Our method disassembles retrosynthesis into two steps: i) identify the potential reaction center of the target molecule through a novel graph neural network and generate intermediate synthons, and ii) generate the reactants associated with synthons via a robust reactant generation model. While outperforming the state-of-the-art baselines by a significant margin, our model also provides chemically reasonable interpretation.

PDF Details