Weixing Chen

Weixing Chen

Causal Inference & Embodied AI

Welcome to Weixing Chenโ€™s Personal Homepage!

My research interests include causal inference ๐ŸŽฒ and embodied intelligence ๐Ÿค–. I aim to explore the associations between various modalities of information from a causal perspective, thereby enhancing the robustness and reliability of intelligent systems. I believe this approach can provide a strong foundation for embodied intelligence systems and medical image analysis, and facilitate the application of artificial intelligence in complex tasks.

I am currently pursuing a Ph.D. at the School of Computer Science at Sun Yat-sen University, under the supervision of Prof. Lin Liang and Prof. Liu Yang in the Human-Cyber-Physical Intelligence Integration (HCP-I2) Lab. In my spare time, I enjoy coding โŒจ, running ๐Ÿƒโ€โ™‚๏ธ, cycling ๐Ÿšดโ€โ™‚๏ธ, playing video games ๐ŸŽฎ, and cooking ๐Ÿฅ˜.

๐ŸŒŸ โ€œGreatness from small beginningsโ€ ๐ŸŒŸ

๐Ÿ’ฌ Research Interests

๐Ÿงฉ
Multi-modal Causality
Exploring causal relationships across multi-modal data to improve model robustness and generalization.
๐Ÿค–
Embodied AI
Developing intelligent agents that can perceive, reason, and interact with the physical world.
๐Ÿฉบ
Medical Image Analysis
Applying causal reasoning and deep learning to improve diagnostic accuracy and reliability.

๐Ÿ”ฅ News

  • 2026.05๐ŸŽ‰ Two papers are accepted by ICML 2026!
  • 2026.02๐ŸŽ‰ Two papers are accepted by CVPR 2026!
  • 2026.01๐ŸŽ‰ One paper is accepted by ICLR 2026!
  • 2025.11๐ŸŽ‰ One T-IP paper is selected as the ESI Highly Cited Paper!
  • 2025.09๐Ÿ† Obtained the Presidential Fellowship (ๆ ก้•ฟๅฅ–ๅญฆ้‡‘) 2024, Rank 1/61.
  • 2025.07๐ŸŽ‰ One paper is accepted by ACM MM 2025 Oral!
  • 2025.06๐ŸŽ‰ One paper is accepted by ICCV 2025!
  • 2025.05๐ŸŽ‰ Our Embodied AI Survey paper is accepted by IEEE/ASME T-Mechatronics!
  • 2025.05๐ŸŽ‰ One paper is accepted by IEEE T-IP!
  • 2025.04๐ŸŽ‰ Our CRA-GQA is selected as CVPR 2025 Highlight!
  • 2025.03๐ŸŽ‰ One paper is accepted by CMIG!
  • 2025.02๐ŸŽ‰ Three papers are accepted by CVPR 2025!
  • 2025.01๐ŸŽ‰ One paper is accepted by ICLR 2025!
  • 2024.09๐Ÿš€ I start pursuing PhD degree in SYSU!

๐Ÿ“– Experience

2025.01 โ€” 2025.10 Research Intern
Huawei Noah's Ark Lab, Shenzhen
2024.09 โ€” Present Ph.D. Student
School of Computer Science, Sun Yat-sen University
2020.09 โ€” 2023.06 M.S.
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences
2016.09 โ€” 2020.06 B.S.
College of Medicine and Biological Information Engineering, Northeastern University (Shenyang)

๐Ÿฅ‡ Honors and Awards

  • 2025Gold Reviewer of ICML 2026
  • 2025ESI Highly Cited Paper (IEEE T-IP)
  • 2024Presidential Fellowship (ๆ ก้•ฟๅฅ–ๅญฆ้‡‘), Sun Yat-sen University, Rank 1/61
  • 2024CVPR 2025 Highlight Paper

๐ŸŒ  Academic Activities

Reviewer for Journals

IEEE TPAMI IEEE T-IP IEEE TNNLS IEEE T-MM Pattern Recognition Visual Computer

Reviewer for Conferences

CVPR ICCV ECCV AAAI NeurIPS ICLR ICML ACM MM

๐Ÿ“ Publications

* Equal contribution

2026 7 papers

CVPR 2026 Learning to See and Act: Task-Aware Virtual View Exploration for Robotic Manipulation
Yongjie Bai, Zhouxia Wang, Yang Liu, ..., Weixing Chen, et al.
ICML 2026 DDP-WM: Disentangled Dynamics Prediction for Efficient World Models
Shicheng Yin, Kaixuan Yin, Weixing Chen, et al.
ICLR 2026 AlphaAgentEvo: Evolution-Oriented Alpha Mining via Self-Evolving Agentic Reinforcement Learning
Ziyi Tang, Xuexiong Yin, Weixing Chen, et al.
Preprint EG-VQA: Benchmarking Verifiable Video Question Answering with Grounded Temporal Evidence
Linpeng Huang, Weixing Chen, Zexin Chen, et al.
ICML 2026 PhyScene3D: Physically Consistent Interactive 3D Tabletop Scene Generation
Weixing Chen, Zhuoqian Feng, Yang Liu, et al.
Preprint Not All Tokens Matter Equally: Dynamic In-context Vector Distillation with Decisive-Token Supervision for Long-form Medical Report Generation
Ning Wu, Rui Liu, Xinkun Lin, Weixing Chen, et al.
CVPR 2026 LASAR: Towards Spatio-temporal Reasoning with Latent Cognitive Map
Jinzhou Tang, Sidi Liu, Waikit Xiu, Weixing Chen, Keze Wang

2025 12 papers

IEEE/ASME T-Mech Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI
Yang Liu, Weixing Chen, Yongjie Bai, et al.
IEEE T-IP Cross-Modal Causal Representation Learning for Radiology Report Generation
Weixing Chen, Yang Liu, Ce Wang, et al.
CVPR 2025 Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark and Method
Xinshuai Song, Weixing Chen, Yang Liu, et al.
ICCV 2025 Beyond the Destination: A Novel Benchmark for Exploration-Aware Embodied Question Answering
Kaixuan Jiang, Yang Liu, Weixing Chen, et al.
CVPR 2025 Highlight Cross-Modal Causal Relation Alignment for Video Question Grounding
Weixing Chen, Yang Liu, Binglin Chen, et al.
ACM MM 2025 Oral 3DAffordSplat: Efficient Affordance Reasoning with 3D Gaussians
Zeming Wei, Junyi Lin, Yang Liu, Weixing Chen, et al.
CVPR 2025 DSPNet: Dual-Vision Scene Perception for Robust 3D Question Answering
Jingzhou Luo, Yang Liu, Weixing Chen, et al.
ICLR 2025 A Multiscale Frequency Domain Causal Framework for Enhanced Pathological Analysis
Xiaoyu Cui*, Weixing Chen*, Jiandong Su*, et al.
CMIG Feature-Targeted Deep Learning Framework for Pulmonary Tumorous Cone-Beam CT (CBCT) Enhancement with Multi-Task Customized Perceptual Loss and Feature-Guided CycleGAN
Jiarui Zhu, Hongfei Sun, Weixing Chen, et al.
Preprint DART: Differentiable Dynamic Adaptive Region Tokenizer for Vision Foundation Models
Shicheng Yin, Kaixuan Yin, Yang Liu, Weixing Chen, Liang Lin
Preprint AutoLayout: Closed-Loop Layout Synthesis via Slow-Fast Collaborative Reasoning
Weixing Chen, Dafeng Chi, Yang Liu, et al.
LNCS 2025 GeoGRPO: Investigating the Stepwise-GRPO Enhancement in RLHF Framework
Kecheng Liang, Xinyu Li, Weixing Chen, Yang Liu

2024 2 papers

Pattern Recognition Global Contrast-Masked Autoencoders Are Powerful Pathological Representation Learners
Hao Quan, Xingyu Li, Weixing Chen, et al.
Preprint VisionGRU: A Linear-Complexity RNN Model for Efficient Image Analysis
Shicheng Yin, Kaixuan Yin, Weixing Chen, et al.

2023 4 papers

Preprint Towards CausalGPT: A Multi-Agent Approach for Faithful Knowledge Reasoning via Promoting Causal Consistency in LLMs
Ziyi Tang, Ruilin Wang, Weixing Chen, et al.
CMIG Learning How to Detect: A Deep Reinforcement Learning Method for Whole-Slide Melanoma Histopathology Images
Tingting Zheng, Weixing Chen, Shuqin Li, et al.
Preprint CausalVLR: A Toolbox and Benchmark for Visual-Linguistic Causal Reasoning
Yang Liu, Weixing Chen, Guanbin Li, Liang Lin
PRCV 2023 VCD: Visual Causality Discovery for Cross-Modal Question Reasoning
Yang Liu, Ying Tan, Jingzhou Luo, Weixing Chen