Publications

TaskFrame: Connecting Task-Level Planning with Frame-Level Control for Game Agents

Guangzhi Wang^*, Junfu Pu^*, Yiran Wang^*, Xingyilang Yin^*, Honghao Chen, Cheng Cheng, Lingen Li, Yinan Zhou, Jiarui Wu, Yinuo Jiang, Hongbo Jin, Xiaodong Cun^†, Ying ShanG. Wang^*, J. Pu^*, Y. Wang^*, Xingyilang Yin^*, H. Chen, C. Cheng, L. Li, Y. Zhou, J. Wu, Y. Jiang, H. Jin, X. Cun^†, Y. Shan

arXiv 2026

Paper 🌐 Project Page

Connecting task-level planning with frame-level CUA control for game agents.

Player-1: Learning to Play from Synthetic Experience

Mingyu Ouyang, Yiran Wang, Siyuan Hu, Xingyilang Yin, Huiqiang Sun, Guangzhi Wang, Junfu Pu, Cheng Cheng, Honghao Chen, Ying Shan, Mike Zheng Shou, Hwee Tou NgM. Ouyang, Y. Wang, S. Hu, Xingyilang Yin, H. Sun, G. Wang, J. Pu, C. Cheng, H. Chen, Y. Shan, M. Z. Shou, H. T. Ng

arXiv 2026

Paper 🌐 Project Page GitHub

Learning transferable game control from synthetic experience.

GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay

Yiran Wang^*, Xingyilang Yin^*, Junfu Pu^*, Guangzhi Wang^*, Kaifeng Li, Mingyu Ouyang, Huiqiang Sun, Lingen Li, Cheng Cheng, Wangbo Yu, Honghao Chen, Xiaodong Cun^†, Chi-Man Pun, Zhiguo Cao, Ying ShanY. Wang^*, Xingyilang Yin^*, J. Pu^*, G. Wang^*, K. Li, M. Ouyang, H. Sun, L. Li, C. Cheng, W. Yu, H. Chen, X. Cun^†, C.-M. Pun, Z. Cao, Y. Shan

arXiv 2026

Paper 🌐 Project Page GitHub

A unified data and evaluation suite for gameplay capabilities across temporal horizons.

MLLM-4D: Towards Visual-based Spatial-Temporal Intelligence

Xingyilang Yin^*, Chengzhengxu Li^*, Jiahao Chang, Chi-Man Pun^†, Xiaodong Cun^†Xingyilang Yin^*, C. Li^*, J. Chang, C.-M. Pun^†, X. Cun^†

ICML 2026

Paper GitHub

Visual understanding and reasoning about how 3D space evolves over time.

GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors

Xingyilang Yin^*, Qi Zhang^*, Jiahao Chang, Ying Feng, Qingnan Fan, Xi Yang, Chi-Man Pun^†, Huaqi Zhang, Xiaodong Cun^†Xingyilang Yin^*, Q. Zhang^*, J. Chang, Y. Feng, Q. Fan, X. Yang, C.-M. Pun^†, H. Zhang, X. Cun^†

ICML 2026

Paper GitHub

Reference-guided video diffusion priors for restoring 3D Gaussian Splatting artifacts.

Unleashing the Multi-View Fusion Potential: Noise Correction in VLM for Open-Vocabulary 3D Scene Understanding

Xingyilang Yin^*, Jiale Wang^*, Xi Yang^†, Mutian Xu, Xu Gu, Nannan WangXingyilang Yin^*, J. Wang^*, X. Yang^†, M. Xu, X. Gu, N. Wang

TMM 2026

Paper

Reducing vision-language feature noise for open-vocabulary 3D understanding.

Associative Graph Convolution Network for Point Cloud Analysis

Xi Yang, Xingyilang Yin, Nannan Wang, Xinbo GaoX. Yang, Xingyilang Yin, N. Wang, X. Gao

Pattern Recognition 2025

Paper

Associative graph convolution for learning from unstructured point clouds.

SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Instance Segmentation

Mutian Xu, Xingyilang Yin, Lingteng Qiu, Yang Liu, Xin Tong, Xiaoguang Han^†M. Xu, Xingyilang Yin, L. Qiu, Y. Liu, X. Tong, X. Han^†

3DV 2025

Paper 🌐 Project Page GitHub

Locating prompts in 3D for view-consistent, zero-shot instance segmentation.

SA3DIP: Segment Any 3D Instance with Potential 3D Priors

Xi Yang, Xu Gu, Xingyilang Yin^†, Xinbo GaoX. Yang, X. Gu, Xingyilang Yin^†, X. Gao

NeurIPS 2024

Paper

Exploiting 3D priors for open-world 3D instance segmentation

PDNet architecture: hierarchical point-cloud processing with local and deformable aggregation modules

Point Deformable Network with Enhanced Normal Embedding for Point Cloud Analysis

Xingyilang Yin, Xi Yang^†, Liangchen Liu, Nannan Wang, Xinbo GaoXingyilang Yin, X. Yang^†, L. Liu, N. Wang, X. Gao

AAAI 2024

Paper

Deformable point processing for point cloud analysis